October 2022 arXiv papers — page 95

Agnieszka Lipska, Jerzy Stefanowski

This work is aimed at the experimental studying the influence of local data characteristics and drifts on the difficulties of learning various online classifiers from multi-class imbalanced data streams. Firstly we present a categorization of these data factors and drifts in the context of imbalanced streams, then we introduce the generators of synthetic str

Omar French, Fan Guo, Qile Zhang, Dmitri Uzdensky

Magnetic reconnection in the relativistic regime has been proposed as an important process for the efficient production of nonthermal particles and high-energy emissions. Using fully kinetic particle-in-cell simulations, we investigate how guide-field strength and domain size affect characteristic spectral features and acceleration processes. We study two st

Hazem Fahmy, Mohamed A. Abd El Ghany, Gerd Baumann

This article examines a symbolic numerical approach to optimize a vehicle's track for autonomous driving and collision avoidance. The new approach uses the classical cost function definition incorporating the essential aspects of the dynamic state of the vehicle as position, orientation, time sampling, and constraints on slip angles of tires. The optimizatio

Hazem Fahmy, Fabrizio Pastore, Lionel Briand

We present HUDD, a tool that supports safety analysis practices for systems enabled by Deep Neural Networks (DNNs) by automatically identifying the root causes for DNN errors and retraining the DNN. HUDD stands for Heatmap-based Unsupervised Debugging of DNNs, it automatically clusters error-inducing images whose results are due to common subsets of DNN neur

Naoki Kobayashi, Tsutomu Hirao, Hidetaka Kamigaito, Manabu Okumura

To promote and further develop RST-style discourse parsing models, we need a strong baseline that can be regarded as a reference for reporting reliable experimental results. This paper explores a strong baseline by integrating existing simple parsing strategies, top-down and bottom-up, with various transformer-based pre-trained language models. The experimen

R. Alvarez Garrote, J. Cuervo, P. C. Magalhães, J. R. Peláez

The LHCb collaboration has recently reported the largest CP violation effect from a single amplitude, as well as other giant CP asymmetries in several $B$-meson decays into three charmless light mesons. It is also claimed that this is predominantly due to $\pi\pi\rightarrow K\bar K$ rescattering in the final state, particularly in the 1 to 1.5 GeV region. In

Juncheng Liu, Bryan Hooi, Kenji Kawaguchi, Xiaokui Xiao

Recently, implicit graph neural networks (GNNs) have been proposed to capture long-range dependencies in underlying graphs. In this paper, we introduce and justify two weaknesses of implicit GNNs: the constrained expressiveness due to their limited effective range for capturing long-range dependencies, and their lack of ability to capture multiscale informat

Afif Elghraoui, Faramarz Valafar

Background: DNA, RNA, and protein sequence motifs can be recognition sites for biological functions such as regulation, DNA base modification, and molecular binding in general. The gain and loss of such motifs can carry important consequences. When comparing sequences, the analysis of individual variants does not impart an understanding of the impact on thes

Z. A. Mansurov, G. T. Smagulova, F. R. Sultanov, B. B. Kaidar

The main research efforts are aimed at finding inexpensive materials that can be converted into nanostructured carbon-containing materials, such as activated carbon and graphene. Rice husks are one such material, especially in developing countries, where more than 95% of Rice husks are produced worldwide. Although numerous studies have been conducted on the

Adriaan P Hilbers, David J Brayshaw, Axel Gandy

The growth in variable renewables such as solar and wind is increasing the impact of climate uncertainty in energy system planning. Addressing this ideally requires high-resolution time series spanning at least a few decades. However, solving capacity expansion planning models across such datasets often requires too much computing time or memory. To reduce c

Adrian Bojko, Romain Dupont, Mohamed Tamaazousti, Hervé Le Borgne

Visual SLAM - Simultaneous Localization and Mapping - in dynamic environments typically relies on identifying and masking image features on moving objects to prevent them from negatively affecting performance. Current approaches are suboptimal: they either fail to mask objects when needed or, on the contrary, mask objects needlessly. Thus, we propose a novel

Tianying Ji, Yu Luo, Fuchun Sun, Mingxuan Jing

Designing and analyzing model-based RL (MBRL) algorithms with guaranteed monotonic improvement has been challenging, mainly due to the interdependence between policy optimization and model learning. Existing discrepancy bounds generally ignore the impacts of model shifts, and their corresponding algorithms are prone to degrade performance by drastic model up

Yisha Yao

In this note, we study irreducible unitary representations of special linear groups of lower ranks, in terms of the matrix models of Gelfand-Naimark and Gelfand-Graev. Review of existing literature is provided. We also add some new calculation based on existing theory.

Shaoming Xu, Ankush Khandelwal, Xiang Li, Xiaowei Jia

In many environmental applications, recurrent neural networks (RNNs) are often used to model physical variables with long temporal dependencies. However, due to mini-batch training, temporal relationships between training segments within the batch (intra-batch) as well as between batches (inter-batch) are not considered, which can lead to limited performance

Veronica Ballerini, Brunero Liseo

We introduce a method to make inference on the composition of a heterogeneous population using survey data, accounting for the possibility that capture heterogeneity is related to key survey variables. To deal with nonignorable nonresponse, we combine different data sources and propose the use of Fisher's noncentral hypergeometric model in a Bayesian framewo

Haifeng Li, Jun Cao, Jiawei Zhu, Qinyao Luo

The pretasks are mainly built on mutual information estimation, which requires data augmentation to construct positive samples with similar semantics to learn invariant signals and negative samples with dissimilar semantics in order to empower representation discriminability. However, an appropriate data augmentation configuration depends heavily on lots of

Qi Zhang, Yifei Wang, Yisen Wang

Masked Autoencoders (MAE) based on a reconstruction task have risen to be a promising paradigm for self-supervised learning (SSL) and achieve state-of-the-art performance across different benchmark datasets. However, despite its impressive empirical success, there is still limited theoretical understanding of it. In this paper, we propose a theoretical under

Jan N. Fuhg, Craig M. Hamel, Kyle Johnson, Reese Jones

The development of accurate constitutive models for materials that undergo path-dependent processes continues to be a complex challenge in computational solid mechanics. Challenges arise both in considering the appropriate model assumptions and from the viewpoint of data availability, verification, and validation. Recently, data-driven modeling approaches ha

Vanja Nikolić, Belkacem Said-Houari

High frequencies at which ultrasonic waves travel give rise to nonlinear phenomena. In thermoviscous fluids, these are captured by Blackstock's acoustic wave equation with strong damping. We revisit in this work its well-posedness analysis. By exploiting the parabolic-like character of this equation due to strong dissipation, we construct a time-weighted ene

Alexander Buchholz, Ben London, Giuseppe di Benedetto, Thorsten Joachims

A critical need for industrial recommender systems is the ability to evaluate recommendation policies offline, before deploying them to production. Unfortunately, widely used off-policy evaluation methods either make strong assumptions about how users behave that can lead to excessive bias, or they make fewer assumptions and suffer from large variance. We ta

Anthony Zador, Sean Escola, Blake Richards, Bence Ölveczky

Neuroscience has long been an essential driver of progress in artificial intelligence (AI). We propose that to accelerate progress in AI, we must invest in fundamental research in NeuroAI. A core component of this is the embodied Turing test, which challenges AI animal models to interact with the sensorimotor world at skill levels akin to their living counte

Joseph A. Vincent, Mac Schwager

Neural networks are increasingly used in robotics as policies, state transition models, state estimation models, or all of the above. With these components being learned from data, it is important to be able to analyze what behaviors were learned and how this affects closed-loop performance. In this paper we take steps toward this goal by developing methods

Alexander Buchholz, Vito Bellini, Giuseppe Di Benedetto, Yannik Stein

A/B tests serve the purpose of reliably identifying the effect of changes introduced in online services. It is common for online platforms to run a large number of simultaneous experiments by splitting incoming user traffic randomly in treatment and control groups. Despite a perfect randomization between different groups, simultaneous experiments can interac

Ivan Damnjanović, Slobodan Filipovski, Dragan Stevanović

We investigate the spectral properties of balanced trees and dendrimers, with a view toward unifying and improving the existing results. Here we find a semi-factorized formula for their characteristic polynomials. Afterwards, we determine their spectra via the aforementioned factors. In the end, we analyze the behavior of the energy of dendrimers and compute

Yitao Peng, Yihang Liu, Longzhen Yang, Lianghua He

The interpretability of neural networks has recently received extensive attention. Previous prototype-based explainable networks involved prototype activation in both reasoning and interpretation processes, requiring specific explainable structures for the prototype, thus making the network less accurate as it gains interpretability. Therefore, the decouplin

Abdelhamid Salem, Xiao Tong, Ang Li, Christos Masouros

Non-orthogonal multiple access (NOMA) is a powerful transmission technique that enhances the spectral efficiency of communication links, and is being investigated for 5G standards and beyond. A major drawback of NOMA is the need to apply successive interference cancellation (SIC) at the receiver on a symbol-by-symbol basis, which limits its practicality. To

Ivan Damnjanović

A circulant nut graph is a non-trivial simple graph whose adjacency matrix is a circulant matrix of nullity one such that its non-zero null space vectors have no zero elements. The study of circulant nut graphs was originally initiated by Ba\v{s}i\'c et al. [Art Discrete Appl. Math. 5(2) (2021) #P2.01], where a conjecture was made regarding the existence of

Shuaifeng Li, Panayotis G. Kevrekidis, Jinkyu Yang

Elastic topological states have been receiving increased intention in numerous scientific and engineering fields due to their defect-immune nature, resulting in applications of vibration control and information processing. Here, we present the data-driven discovery of elastic topological states using dynamic mode decomposition (DMD). The DMD spectrum and DMD

Yiqiao Jin, Yunsheng Bai, Yanqiao Zhu, Yizhou Sun

Open Source Software (OSS) is forming the spines of technology infrastructures, attracting millions of talents to contribute. Notably, it is challenging and critical to consider both the developers' interests and the semantic features of the project code to recommend appropriate development tasks to OSS developers. In this paper, we formulate the novel probl

Zainab A. Jawad, Ahmed J. Obaid

Nowadays, People prefer to follow the latest news on social media, as it is cheap, easily accessible, and quickly disseminated. However, it can spread fake or unreliable, low-quality news that intentionally contains false information. The spread of fake news can have a negative effect on people and society. Given the seriousness of such a problem, researcher

Ángel de la Vega Jiménez

Currently, the diagnosis of Alzheimer's disease is a complex and error-prone process. Improving this diagnosis could allow earlier detection of the disease and improve the quality of life of patients and their families. For this work, we will use 249 brain images from two modalities: PET and MRI, taken from the ADNI database, and labelled into three classes

Kaiyu Li, Daniel Giles, Toni Karvonen, Serge Guillas

Multilevel Monte Carlo is a key tool for approximating integrals involving expensive scientific models. The idea is to use approximations of the integrand to construct an estimator with improved accuracy over classical Monte Carlo. We propose to further enhance multilevel Monte Carlo through Bayesian surrogate models of the integrand, focusing on Gaussian pr

Chowdhury Mohammad Sakib Anwar, Jorge Bruno, Sonali SenGupta

We model a dynamic public good contribution game, where players are (naturally) formed into groups. The groups are exogenously placed in a sequence, with limited information available to players about their groups' position in the sequence. Contribution decisions are made by players simultaneously and independently, and the groups' total contribution is made

Cathia Le Hasif, Andrea Araldo, Stefania Dumbrava, Dimitri Watel

This paper proposes an approach to analyze the impact of multimodal Public Transit (PT), combining conventional fixed-route transit and Demand-Responsive Transit (DRT), on equality in transport accessibility distribution. We construct a graph model of multimodal PT in Neo4j, based on General Transit Feed Specification (GTFS) data, modeling DRT analytically (

Dimitris Bertsimas, Kosuke Imai, Michael Lingzhi Li

We consider the estimation of average treatment effects in observational studies and propose a new framework of robust causal inference with unobserved confounders. Our approach is based on distributionally robust optimization and proceeds in two steps. We first specify the maximal degree to which the distribution of unobserved potential outcomes may deviate

CMS Collaboration

The path-length dependent parton energy loss within the dense partonic medium created in lead-lead collisions at a nucleon-nucleon center-of-mass energy of $\sqrt{s_\mathrm{NN}}$ = 5.02 TeV is studied by determining the azimuthal anisotropies for dijets with high transverse momentum. The data were collected by the CMS experiment in 2018 and correspond to an

Marcel Dengler

For two different scenarios regarding thin elastic structures, described by 2d-F\"oppl-von K\'arm\'an plate models, we obtain energy scaling laws. Firstly, assuming the reference geometry being that of a singular excess-cone, we obtain fairly optimal upper- and lower energy bounds and we highlight how those bounds scale wrt. the thickness-parameter $h.$ Seco

Haoran Xu, Li Jiang, Jianxiong Li, Xianyuan Zhan

Offline reinforcement learning (RL) methods can generally be categorized into two types: RL-based and Imitation-based. RL-based methods could in principle enjoy out-of-distribution generalization but suffer from erroneous off-policy evaluation. Imitation-based methods avoid off-policy evaluation but are too conservative to surpass the dataset. In this study,

Francesco Giovanni Celiberto

Unraveling the inner dynamics of gluons and quarks inside nucleons is a primary target of studies at new-generation colliding machines. Finding an answer to fundamental problems of Quantum ChromoDynamics, such as the origin of nucleon mass and spin, strongly depends on our ability of reconstructing the 3D motion of partons inside the parent hadrons. We prese

Mario Giulianelli, Arabella Sinclair, Raquel Fernández

Speakers repeat constructions frequently in dialogue. Due to their peculiar information-theoretic properties, repetitions can be thought of as a strategy for cost-effective communication. In this study, we focus on the repetition of lexicalised constructions -- i.e., recurring multi-word units -- in English open-domain spoken dialogues. We hypothesise that s

Alan Chang, Georgios Dosidis, Jongchon Kim

We study spherical analogues of Nikodym sets and related maximal functions. In particular, we prove sharp $L^p$-estimates for Nikodym maximal functions associated with spheres. As a corollary, any Nikodym set for spheres must have full Hausdorff dimension. In addition, we consider a class of maximal functions which contains the spherical maximal function as

Umut Demir, Nazim Kemal Ure

In this work we propose a reinforcement learning (RL) framework that controls the density of a large-scale swarm for engaging with adversarial swarm attacks. Although there is a significant amount of existing work in applying artificial intelligence methods to swarm control, analysis of interactions between two adversarial swarms is a rather understudied are

Hugo Jaquard, Michaël Fanuel, Pierre-Olivier Amblard, Rémi Bardenet

We introduce new smoothing estimators for complex signals on graphs, based on a recently studied Determinantal Point Process (DPP). These estimators are built from subsets of edges and nodes drawn according to this DPP, making up trees and unicycles, i.e., connected components containing exactly one cycle. We provide a Julia implementation of these estimator

Omar Ali, Alexandre Bone, Caterina Accardo, Omar Belkouchi

Surgical resections are the most prevalent curative treatment for primary liver cancer. Tumors located in critical positions are known to complexify liver resections (LR). While experienced surgeons in specialized medical centers may have the necessary expertise to accurately anticipate LR complexity, and prepare accordingly, an objective method able to repr

Palash Panja, Wei Jia, Alec Nelson, Brian McPherson

A machine learning architecture composed of convolutional long short-term memory (convLSTM) is developed to predict spatio-temporal parameters in the SACROC oil field, Texas, USA. The spatial parameters are recorded at the end of each month for 30 years (360 months), approximately 83% (300 months) of which is used for training and the rest 17% (60 months) is

Vesselin Drensky

The variety of bicommutative algebras consists of all nonassociative algebras satisfying the polynomial identities of right- and left-commutativity $(x_1x_2)x_3=(x_1x_3)x_2$ and $x_1(x_2x_3)=x_2(x_1x_3)$. Let $F_d$ be the free $d$-generated bicommutative algebra over a field $K$ of characteristic 0. We study the algebra $F_d^G$ of invariants of a subgroup $G

Animesh Chaturvedi

Call Graph evolution analytics can aid a software engineer when maintaining or evolving a software system. This paper proposes Call Graph Evolution Analytics to extract information from an evolving call graph ECG = CG_1, CG_2,... CG_N for their version series VS = V_1, V_2, ... V_N of an evolving software system. This is done using Call Graph Evolution Rules

J. Corrigan, J. P. Dodson, Brandur Thorgrimsson, Samuel F. Neyens

A primary method of reading out a quantum dot hybrid qubit involves projection of the logical basis onto distinct charge states that are readily detected by an integrated charge sensing dot. However, in the simplest configuration, the excited charge state decays rapidly, making single-shot readout challenging. Here, we demonstrate a readout procedure where t

Simon Halvdansson

On a locally compact group we introduce covariant quantization schemes and analogs of phase space representations as well as mixed-state localization operators. These generalize corresponding notions for the affine group and the Heisenberg group. The approach is based on associating to a square integrable representation of the locally compact group two types

Tianjun Gan, Sharon X. Wang, Songhu Wang, Shude Mao

We present an estimate of the occurrence rate of hot Jupiters ($7\ R_{\oplus}\leq R_{p}\leq 2\ R_{J}$, $0.8 \leq P_{b}\leq 10$ days) around early-type M dwarfs based on stars observed by TESS during its Primary Mission. We adopt stellar parameters from the TESS Input Catalog, and construct a sample of 60,819 M dwarfs with $10.5 \leq T_{\rm mag}\leq 13.5$, ef

David Gamarnik, Cristopher Moore, Lenka Zdeborová

In this review article, we discuss connections between the physics of disordered systems, phase transitions in inference problems, and computational hardness. We introduce two models representing the behavior of glassy systems, the spiked tensor model and the generalized linear model. We discuss the random (non-planted) versions of these problems as prototyp

Paul Balmer, Martin Gallauer

We consider the derived category of permutation modules over a finite group, in positive characteristic. We stratify this tensor triangulated category using Brauer quotients. We describe the set underlying the tt-spectrum of compact objects, and discuss several examples.

Alexander I. Suciu

We explore various formality and finiteness properties in the differential graded algebra models for the Sullivan algebra of piecewise polynomial rational forms on a space. The 1-formality property of the space may be reinterpreted in terms of the filtered and graded formality properties of the Malcev Lie algebra of its fundamental group, while some of the f

Djamel Eddine Amir, Mathieu Hoyrup

A compact set has computable type if any homeomorphic copy of the set which is semicomputable is actually computable. Miller proved that finite-dimensional spheres have computable type, Iljazovi\'c and other authors established the property for many other sets, such as manifolds. In this article we propose a theoretical study of the notion of computable type

Nicolás A. Barnafi, Luis Miguel De Oliveira Vilaca, Michel C. Milinkovitch, Ricardo Ruiz-Baier

We propose a new mathematical model for the interaction of skin cell populations with fibroblast growth factor and bone morphogenetic protein, occurring within deformable porous media. The equations for feather primordia pattering are based on the work by K.J. Painter et al. [J. Theoret. Biol., 437 (2018) 225--238]. We perform a linear stability analysis to

Panagiotis Kasnesis, Christos Chatzigeorgiou, Dimitrios G. Kogias, Charalampos Z. Patrikakis

Efficient and quick remote communication in search and rescue operations can be life-saving for the first responders. However, while operating on the field means of communication based on text, image and audio are not suitable for several disaster scenarios. In this paper, we present a smartwatch-based application, which utilizes a Deep Learning (DL) model,

Herman Verlinde

We introduce a new probe designed to keep track of the quantum information content of a Hawking pair as a function of the distance from the black hole horizon. We compute the entropy content of this Hawking pair probe via a semi-classical replica method that relies on free field Wick contractions and their leading order gravitational back reaction on the bla

Runkai Zhao, Heng Wang, Chaoyi Zhang, Weidong Cai

Digital neuron reconstruction from 3D microscopy images is an essential technique for investigating brain connectomics and neuron morphology. Existing reconstruction frameworks use convolution-based segmentation networks to partition the neuron from noisy backgrounds before applying the tracing algorithm. The tracing results are sensitive to the raw image qu

Ryuhei Kohno, Kyongmo An, Eric Clot, Vladimir V. Naletov

This review provides a comprehensive study of the nonlinear transport properties of magnons, which are electrically emitted or absorbed inside extended YIG films by spin transfer effects via a YIG$\vert$Pt interface. Our purpose is to experimentally elucidate the pertinent picture behind the asymmetric electrical variation of the magnon transconductance anal

Jinpeng Hu, Zhihong Chen, Yang Liu, Xiang Wan

The impression is crucial for the referring physicians to grasp key information since it is concluded from the findings and reasoning of radiologists. To alleviate the workload of radiologists and reduce repetitive human labor in impression writing, many researchers have focused on automatic impression generation. However, recent works on this task mainly su

Julian Koellermeier, Giovanni Samaey

Projective Integration methods are explicit time integration schemes for stiff ODEs with large spectral gaps. In this paper, we show that all existing Projective Integration methods can be written as Runge-Kutta methods with an extended Butcher tableau including many stages. We prove consistency and order conditions of the Projective Integration methods usin

Tibin M. Thomas, Pallab Sinha Mahapatra, Ranjan Ganguly, Manish K. Tiwari

Condensing atmospheric water vapor on surfaces is a sustainable approach to potentially address the potable water crisis. However, despite extensive research, a key question remains: what is the physical mechanism governing the condensation from humid air and how significantly does it differ from pure steam condensation? The answer may help define an optimal

Lianna Hambardzumyan, Hamed Hatami, Ndiamé Ndiaye

We give a simple construction of $n\times n$ Boolean matrices with $\Omega(n^{4/3})$ zero entries that are free of $2 \times 2$ all-zero submatrices and have covering number $O(\log^4(n))$. This construction provides an explicit counterexample to a conjecture of Pudl\'{a}k, R\"{o}dl and Savick\'{y} and Research Problems 1.33, 4.9, 11.17 of Jukna [Boolean fun

Shohei Watabe, Michael Zach Serikow, Shiro Kawabata, Alexandre Zagoskin

The development of percolation theory was historically shaped by its numerous applications in various branches of science, in particular in statistical physics, and was mainly constrained to the case of Euclidean spaces. One of its central concepts, the percolation transition, is defined through the appearance of the infinite cluster, and therefore cannot be

Uli Fahrenberg, Krzysztof Ziemiański

We establish a Myhill-Nerode type theorem for higher-dimensional automata (HDAs), stating that a language is regular if and only if it has finite prefix quotient. HDAs extend standard automata with additional structure, making it possible to distinguish between interleavings and concurrency. We also introduce deterministic HDAs and show that not all HDAs are

Raffaele Argiento, Riccardo Corradin, Alessandra Guglielmi, Ettore Lanzarone

Motivated by the problem of accurately predicting gap times between successive blood donations, we present here a general class of Bayesian nonparametric models for clustering. These models allow for prediction of new recurrences, accommodating covariate information that describes the personal characteristics of the sample individuals. We introduce a prior f

Wenkai Zheng, Li Xiang, Felipe de Quesada, Mathias Augustin

Interlayer excitons, or bound electron-hole pairs whose constituent quasiparticles are located in distinct stacked semiconducting layers, are being intensively studied in heterobilayers of two dimensional semiconductors. They owe their existence to an intrinsic type-II band alignment between both layers that convert these into p-n junctions. Here, we unveil

Qiqi Liu, Yuping Yan, Peter Ligeti, Yaochu Jin

Data-driven evolutionary algorithms usually aim to exploit the information behind a limited amount of data to perform optimization, which have proved to be successful in solving many complex real-world optimization problems. However, most data-driven evolutionary algorithms are centralized, causing privacy and security concerns. Existing federated Bayesian a

Maxim Senkov

A principal funds a multistage project and retains the right to cut the funding if it stagnates at some point. An agent wants to convince the principal to fund the project as long as possible, and can design the flow of information about the progress of the project in order to persuade the principal. If the project is sufficiently promising ex ante, then the

Lorenzo Ciardo, Stanislav Živný

We show that approximate graph colouring is not solved by any level of the affine integer programming (AIP) hierarchy. To establish the result, we translate the problem of exhibiting a graph fooling a level of the AIP hierarchy into the problem of constructing a highly symmetric crystal tensor. In order to prove the existence of crystals in arbitrary dimensi

Jasper van Doornmalen, Christopher Hojny, Roel Lambers, Frits C. R. Spieksma

Round robin tournaments are omnipresent in sport competitions and beyond. We propose two new integer programming formulations for scheduling a round robin tournament, one of which we call the matching formulation. We analytically compare their linear relaxations with the linear relaxation of a well-known traditional formulation. We find that the matching for

Hongkuan Shi, Zhiwei Wang, Ying Zhou, Dun Li

Semi-supervised learning via teacher-student network can train a model effectively on a few labeled samples. It enables a student model to distill knowledge from the teacher's predictions of extra unlabeled data. However, such knowledge flow is typically unidirectional, having the performance vulnerable to the quality of teacher model. In this paper, we seek

Zhihe Lu, Sen He, Da Li, Yi-Zhe Song

Generalized Few-shot Semantic Segmentation (GFSS) aims to segment each image pixel into either base classes with abundant training examples or novel classes with only a handful of (e.g., 1-5) training images per class. Compared to the widely studied Few-shot Semantic Segmentation FSS, which is limited to segmenting novel classes only, GFSS is much under-stud

Nejat Anbarci, Mehmet S. Ismail

Recently, Artificial Intelligence (AI) technology use has been rising in sports to reach decisions of various complexity. At a relatively low complexity level, for example, major tennis tournaments replaced human line judges with Hawk-Eye Live technology to reduce staff during the COVID-19 pandemic. AI is now ready to move beyond such mundane tasks, however.

Ruisheng Ran, Tianyu Gao, Bin Fang

Recently, Transformer is much popular and plays an important role in the fields of Machine Learning (ML), Natural Language Processing (NLP), and Computer Vision (CV), etc. In this paper, based on the Vision Transformer (ViT) model, a new dimensionality reduction (DR) model is proposed, named Transformer-DR. From data visualization, image reconstruction and f

Latifa Errami, El Houcine Bergou

In this work we study the problem of Byzantine-robust learning when data among clients is heterogeneous. We focus on poisoning attacks targeting the convergence of SGD. Although this problem has received great attention; the main Byzantine defenses rely on the IID assumption causing them to fail when data distribution is non-IID even with no attack. We propo

Nanchi Su, Fan Liu, Christos Masouros

In this paper, we investigate the sensing-aided physical layer security (PLS) towards Integrated Sensing and Communication (ISAC) systems. A well-known limitation of PLS is the need to have information about potential eavesdroppers (Eves). The sensing functionality of ISAC offers an enabling role here, by estimating the directions of potential Eves to inform

Martín Soto Quintanilla

We introduce the stochastic Network-Iterated Prisoner's Dilemma (NIPD) model, a network of players playing the Prisoner's Dilemma with their neighbours, each with a memory-one strategy which they constantly and locally update to improve their success. This process is non-deterministic, and mirrors societal interactions in many relevant aspects. We use it to

Ming Hu, Peiheng Zhou, Zhihao Yue, Zhiwei Ling

As a promising distributed machine learning paradigm, Federated Learning (FL) has attracted increasing attention to deal with data silo problems without compromising user privacy. By adopting the classic one-to-multi training scheme (i.e., FedAvg), where the cloud server dispatches one single global model to multiple involved clients, conventional FL methods

Muhammad AL-Qurishi, Sarah AlQaseemi, Riad Soussi

The effectiveness of the BERT model on multiple linguistic tasks has been well documented. On the other hand, its potentials for narrow and specific domains such as Legal, have not been fully explored. In this paper, we examine how BERT can be used in the Arabic legal domain and try customizing this language model for several downstream tasks using several d

Ryuhei Kohno, Kyongmo An, Eric Clot, Vladimir V. Naletov

This review presents a comprehensive study of the spatial dispersion of propagating magnons electrically emitted in extended yttrium-iron garnet (YIG) films by the spin transfer effects across a YIG$\vert$Pt interface. Our goal is to provide a generic framework to describe the magnon transconductance inside magnetic films. We experimentally elucidate the rel

Trung Xuan Pham, Jin Woong Choi, Rusty John Lloyd Mina, Thanh Nguyen

Herein, we introduce "Look and Diagnose" (LAD), a hybrid deep learning-based system that aims to support doctors in the medical field in diagnosing effectively the Benign Paroxysmal Positional Vertigo (BPPV) disorder. Given the body postures of the patient in the Dix-Hallpike and lateral head turns test, the visual information of both eyes is captured and fe

Felix Klement, Henrich C. Pöhls, Stefan Katzenbeisser

Third-party dongles for cars, e.g. from insurance companies, can extract sensitive data and even send commands to the car via the standardized OBD-II interface. Due to the lack of message authentication mechanisms, this leads to major security vulnerabilities for example regarding the connection with malicious devices. Therefore, we apply a modular, protocol

Óscar Gil, Alberto Sanfeliu

The navigation of robots in dynamic urban environments, requires elaborated anticipative strategies for the robot to avoid collisions with dynamic objects, like bicycles or pedestrians, and to be human aware. We have developed and analyzed three anticipative strategies in motion planning taking into account the future motion of the mobile objects that can mo

Arsalan Jawaid, Jörg Seewig

Surface roughness plays a critical role and has effects in, e.g. fluid dynamics or contact mechanics. For example, to evaluate fluid behavior at different roughness properties, real-world or numerical experiments are performed. Numerical simulations of rough surfaces can speed up these studies because they can help collect more relevant information. However,

B. Taeri, M. R. Vedadi

We carry out a study of groups $G$ in which the index of any infinite subgroup is finite. We call them restricted-finite groups and characterize finitely generated not torsion restricted-finite groups. We show that every infinite restricted-finite abelian group is isomorphic to $\mathbb{Z}\times K$ or $\mathbb{Z}_{p^\infty}\times K$, where $K$ is a finite gr

Felix Petersen, Christian Borgelt, Hilde Kuehne, Oliver Deussen

Recently, research has increasingly focused on developing efficient neural network architectures. In this work, we explore logic gate networks for machine learning tasks by learning combinations of logic gates. These networks comprise logic gates such as "AND" and "XOR", which allow for very fast execution. The difficulty in learning logic gate networks is t

Daniel A. Berke, Michael T. Murphy, Chris Flynn, Fan Liu

Sun-like stars are a new probe of variations in the fine-structure constant, $\alpha$, via the solar twins approach: velocity separations of close pairs of absorption lines are compared between stars with very similar stellar parameters, i.e. effective temperature, metallicity and surface gravity within 100K, 0.1 dex and 0.2 dex of the Sun's values. Here we

Daniel A. Berke, Michael T. Murphy, Chris Flynn, Fan Liu

The rich absorption spectra of Sun-like stars are enticing probes for variations in the fine-structure constant, $\alpha$, which gauges the strength of electromagnetism. While individual line wavelengths are sensitive to $\alpha$, they are also sensitive to physical processes in the stellar atmospheres, which has precluded their use so far. Here we demonstra

Xixi Wu, Yun Xiong, Yao Zhang, Yizhu Jiao

Community detection refers to the task of discovering closely related subgraphs to understand the networks. However, traditional community detection algorithms fail to pinpoint a particular kind of community. This limits its applicability in real-world networks, e.g., distinguishing fraud groups from normal ones in transaction networks. Recently, semi-superv

Feihu Han, Sida Xing, Sui Yang Khoo

There introduce Particle Optimized Gradient Descent (POGD), an algorithm based on the gradient descent but integrates the particle swarm optimization (PSO) principle to achieve the iteration. From the experiments, this algorithm has adaptive learning ability. The experiments in this paper mainly focus on the training speed to reach the target value and the a

Andrea Venturi, Michele Colajanni, Marco Ramilli, Giorgio Valenziano Santangelo

Phishing kits are tools that dark side experts provide to the community of criminal phishers to facilitate the construction of malicious Web sites. As these kits evolve in sophistication, providers of Web-based services need to keep pace with continuous complexity. We present an original classification of a corpus of over 2000 recent phishing kits according

Max Rubinstein, Zach Branson, Edward H. Kennedy

We propose semi- and non-parametric methods to estimate conditional interventional effects in the setting of two discrete mediators whose causal ordering is unknown. Average interventional indirect effects have been shown to decompose an average treatment effect into a direct effect and interventional indirect effects that quantify effects of hypothetical in

Daniel S. Kosov

We present a theoretical approach to include dynamical aspects of molecular structural fluctuations, such as, for example, forming and breaking hydrogen bonds, isomerizations, and dynamical supramolecular structures, in nonequilibrium Green's functions electron transport calculations. Structural transitions are treated as a stochastic telegraph process, and

Christian Esposito, Olaf Hartig, Ross Horne, Chang Sun

The Solid specification aims to empower data subjects by giving them direct access control over their data across multiple applications. As governments are manifesting their interest in this framework for citizen empowerment and e-government services, security and privacy represent pivotal issues to be addressed. By analyzing the relevant legislation, notabl

Oliver Schön, Birgit van Huijgevoort, Sofie Haesaert, Sadegh Soudjani

This paper addresses the problem of computing controllers that are correct by design for safety-critical systems and can provably satisfy (complex) functional requirements. We develop new methods for models of systems subject to both stochastic and parametric uncertainties. We provide for the first time novel simulation relations for enabling correct-by-desi

Renzhe Xu, Xingxuan Zhang, Bo Li, Yafeng Zhang

Product ranking is the core problem for revenue-maximizing online retailers. To design proper product ranking algorithms, various consumer choice models are proposed to characterize the consumers' behaviors when they are provided with a list of products. However, existing works assume that each consumer purchases at most one product or will keep viewing the

Ranjiva M. Munasinghe

The integral $\int_{-\infty}^{\infty} e^{- x^2 - g x^4} dx $ is used as an introductory learning tool in the study of Quantum Field Theory and path integrals. Typically it is analysed via perturbation theory. Close form solutions have been quoted but it is not clear how they were derived. So I set about deriving the close form solution on my own and using th

Sheel Shah, Kushal Kejriwal

We look at the use of deterministic sensing matrices for compressed sensing and provide worst-case bounds on the classification accuracy of SVMs on compressively sensed data.

Klichchupong Dabsamut, Thanasee Thanasarnsurapong, Intuon Chatratin, Tosapol Maluangnont

The discovery of new and stable two-dimensional (2D) materials with exotic properties is essential for technological advancement. Inspired by the recently reported penta-PdPSe, we proposed penta-NiPS as a new member of the penta-2D materials based on first-principles calculations. The penta-NiPS monolayer is stable in two polymorphs including the alpha phase