November 2022 arXiv papers — page 27

Julian Hernandez, Clark Fitzgerald

This study combines photo metadata and computer vision to quantify where uncollected litter is present. Images from the Trash Annotations in Context (TACO) dataset were used to teach an algorithm to detect 10 categories of garbage. Although it worked well with smartphone photos, it struggled when trying to process images from vehicle mounted cameras. However

YuTeng Ye, Hang Zhou, Jiale Cai, Chenxing Gao

Occluded person re-identification (ReID) is a challenging problem due to contamination from occluders. Existing approaches address the issue with prior knowledge cues, such as human body key points and semantic segmentations, which easily fail in the presence of heavy occlusion and other humans as occluders. In this paper, we propose a feature pruning and co

Zachary Munro

An abelian group acting freely on a $\mathrm{CAT}(0)$ cube complex is free abelian.

Carissma McGee

The longest recognized stellar stream in the Milky Way Galaxy has an expanse of over more than half the north sky. There was a physical disturbance within the stream, 500 million years ago, which could have been the scar of a dark matter collision. Due to its proximity to the galactic center, the GD-1 stellar stream can act as an antenna for gravitational pe

Meihuizi Jia, Lei Shen, Xin Shen, Lejian Liao

Multimodal named entity recognition (MNER) is a critical step in information extraction, which aims to detect entity spans and classify them to corresponding entity types given a sentence-image pair. Existing methods either (1) obtain named entities with coarse-grained visual clues from attention mechanisms, or (2) first detect fine-grained visual regions wi

Ruofeng Wei, Bin Li, Hangjie Mo, Fangxun Zhong

Estimating precise metric depth and scene reconstruction from monocular endoscopy is a fundamental task for surgical navigation in robotic surgery. However, traditional stereo matching adopts binocular images to perceive the depth information, which is difficult to transfer to the soft robotics-based surgical systems due to the use of monocular endoscopy. In

Michael Chow, Pratyush Sarkar

Let $G$ be a connected center-free simple real algebraic group of rank one and $\Gamma < G$ be a Zariski dense torsion-free convex cocompact subgroup. We prove that the frame flow on $\Gamma \backslash G$, i.e., the right translation action of a one-parameter subgroup $\{a_t\}_{t \in \mathbb R} < G$ of semisimple elements, is exponentially mixing with respec

Kumar Abhishek, Deeksha Kamath

The advancements in deep learning-based methods for visual perception tasks have seen astounding growth in the last decade, with widespread adoption in a plethora of application areas from autonomous driving to clinical decision support systems. Despite their impressive performance, these deep learning-based models remain fairly opaque in their decision-maki

Kai Du, Ruoyang Liu, Yuxing Wang

Motivated by porous medium equations with randomly perturbed velocity field, this paper considers a class of nonlinear degenerate diffusion equations with nonlinear conservative noise in bounded domains. The existence, uniqueness and $L_{1}$-stability of non-negative entropy solutions under the homogeneous Dirichlet boundary condition are proved. The approac

Junyuan Shang, Shuohuan Wang, Yu Sun, Yanjun Yu

This paper describes our winning system on SemEval 2022 Task 7: Identifying Plausible Clarifications of Implicit and Underspecified Phrases in Instructional Texts. A replaced token detection pre-trained model is utilized with minorly different task-specific heads for SubTask-A: Multi-class Classification and SubTask-B: Ranking. Incorporating a pattern-aware

Licheng Zhang, Yuanqiu Huang

A graph is reducible if it is the lexicographic product of two smaller non-trivial graphs. It is well-known a 1-planar graph with $n ~(\ge3)$ vertices has at most $4n-8$ edges, and a graph $G$ with $n$ vertices is optimal if $G$ has exactly $4n-8$ edges. In this paper, we characterize the reducibility of optimal 1-planar graphs. This work is motivated by a p

Kourosh T. Baghaei, Amirreza Payandeh, Pooya Fayyazsanavi, Shahram Rahimi

Machine Learning algorithms have had a profound impact on the field of computer science over the past few decades. These algorithms performance is greatly influenced by the representations that are derived from the data in the learning process. The representations learned in a successful learning process should be concise, discrete, meaningful, and able to b

Zhenjun Zhao, Yu Zhai, Ben M. Chen, Peidong Liu

Local feature detection is a key ingredient of many image processing and computer vision applications, such as visual odometry and localization. Most existing algorithms focus on feature detection from a sharp image. They would thus have degraded performance once the image is blurred, which could happen easily under low-lighting conditions. To address this i

Yuqi Nie, Nam H. Nguyen, Phanwadee Sinthong, Jayant Kalagnanam

We propose an efficient design of Transformer-based models for multivariate time series forecasting and self-supervised representation learning. It is based on two key components: (i) segmentation of time series into subseries-level patches which are served as input tokens to Transformer; (ii) channel-independence where each channel contains a single univari

Gang Chen, Jiawei Chen, Fuli Feng, Sheng Zhou

As a promising solution for model compression, knowledge distillation (KD) has been applied in recommender systems (RS) to reduce inference latency. Traditional solutions first train a full teacher model from the training data, and then transfer its knowledge (\ie \textit{soft labels}) to supervise the learning of a compact student model. However, we find su

Liguo He, Gang Zhu

Let G be a Frobenius group with the Frobenius kernel K. Suppose that G contains a nontrival subgroup D \subseteq K such that the normalizer N_G(D) \not\subseteq K. When D is no 2-group, Flavell proved, without using character theory, that K is a subgroup of G. Based on this result, we further prove that K is a subgroup when D is a 2-group.

Mohammed Belkasmi

We introduce the notions of almost positively closed models and positive strong amalgamation property. We study the fundamental properties of these notions and develop some interactions between them.

Quanda Zhang, Hudi Wang

The future wireless communication system faces the bottleneck of the shortage of traditional spectrum resources and the explosive growth of the demand for wireless services. Millimeter-wave communication with spectral resources has become an effective choice for the next generation of wireless broadband cellular communication. However, the transmission path

Pascal Baseilhac, Rodrigo A. Pimenta

The $q$-Racah polynomials are expressed in terms of certain ratios of scalar products of Bethe states associated with Bethe equations of either homogeneous or inhomogeneous type. This result is obtained by combining the theory of Leonard pairs and the modified algebraic Bethe ansatz.

Ian J. Maquignaz

A novel approach to 3D surface imaging is proposed, allowing for the continuous sampling of 3D surfaces to extract localized perspective transformation coefficients from Fourier spectrum analysis of projected patterns. The mathematical relationship for Spatial-Fourier Transformation Pairs is derived, defining the transformation of spatial transformed planar

Tao Chen, Tianshu Liu

From the Navier-Stokes-Korteweg (NSK) equations, the exact relations between the fundamental surface physical quantities for two-phase viscous flow with diffuse interface are derived, including density gradient, shear stress, vorticity, pressure, enstrophy flux and surface curvature. These theoretical results provide a solid foundation of the boundary/interf

Yeojin Kim, Hyunju Lee

Identification of Alzheimer's Disease (AD)-related transcriptomic signatures from blood is important for early diagnosis of the disease. Deep learning techniques are potent classifiers for AD diagnosis, but most have been unable to identify biomarkers because of their lack of interpretability. To address these challenges, we propose a pathway information-bas

Thomas Schürmann, Ingo Hoffmann, Winfrid Görlich

Historically, Kennard was the first to choose the standard deviation as a quantitative measure of uncertainty, and neither he nor Heisenberg explicitly explained why this choice should be appropriate from the experimental physical point of view. If a particle is prepared by a single slit of spatial width $\Delta x$, it has been shown that a finite standard d

Yanwen Li, Siyang Gao, Zhongshun Shi

Ranking and selection (R&S) is a popular model for studying discrete-event dynamic systems. It aims to select the best design (the design with the largest mean performance) from a finite set, where the mean of each design is unknown and has to be learned by samples. Great research efforts have been devoted to this problem in the literature for developing pro

Yanwen Li, Siyang Gao

Ordinal optimization (OO) is a widely-studied technique for optimizing discrete-event dynamic systems (DEDS). It evaluates the performance of the system designs in a finite set by sampling and aims to correctly make ordinal comparison of the designs. A well-known method in OO is the optimal computing budget allocation (OCBA). It builds the optimality conditi

Katelyn Gao, Ozan Sener

Gaussian smoothing (GS) is a derivative-free optimization (DFO) algorithm that estimates the gradient of an objective using perturbations of the current parameters sampled from a standard normal distribution. We generalize it to sampling perturbations from a larger family of distributions. Based on an analysis of DFO for non-convex functions, we propose to c

Hengquan Guo, Qi Zhu, Xin Liu

This paper studies the problem of stochastic continuum-armed bandit with constraints (SCBwC), where we optimize a black-box reward function $f(x)$ subject to a black-box constraint function $g(x)\leq 0$ over a continuous space $\mathcal X$. We model reward and constraint functions via Gaussian processes (GPs) and propose a Rectified Pessimistic-Optimistic Le

Xiangrui Cai, Haidong Xu, Sihan Xu, Ying Zhang

The prompt-based learning paradigm has gained much research attention recently. It has achieved state-of-the-art performance on several NLP tasks, especially in the few-shot scenarios. While steering the downstream tasks, few works have been reported to investigate the security problems of the prompt-based models. In this paper, we conduct the first study on

Shunnosuke Okada, Yudai Inabu, Hirokuni Miyamoto, Kenta Suzuki

Reducing antibiotic usage in livestock animals has become an urgent issue worldwide to prevent antimicrobial resistance. Here, abuse of chlortetracycline (CTC), a versatile antibacterial agent, on the performance, blood components, fecal microbiota, and organic acid concentration in calves was investigated. Japanese Black calves were fed milk replacer contai

Andrew V. Sills

What follows is a lightly edited version of the author's unpublished master's essay, submitted in partial fulfillment of the requirements of the degree of Master of Arts at the Pennsylvania State University, dated June 1994, written under the supervision of Professor George E. Andrews. It was retyped by the author on November 23, 2022. Obvious typographical

Azim Ibragimov, Mauricio Pamplona Segundo

This work presents the first survey on fingerprint pore detection. The survey provides a general overview of the field and discusses methods, datasets, and evaluation protocols. We also present a baseline method inspired on the state-of-the-art that implements a customizable Fully Convolutional Network, whose hyperparameters were tuned to achieve optimal por

Wei Chen, Chen Li, Dan Chen, Xin Luo

Self-supervised pre-training has become the priory choice to establish reliable neural networks for automated recognition of massive biomedical microscopy images, which are routinely annotation-free, without semantics, and without guarantee of quality. Note that this paradigm is still at its infancy and limited by closely related open issues: 1) how to learn

Hongguang Sun, Chao Ma, Linyi Zhang, Jiahui Li

This letter proposes an analytical framework to evaluate the coverage performance of a cellular-connected unmanned aerial vehicle (UAV) network in which UAV user equipments (UAV-UEs) are equipped with directional antennas and move according to a three-dimensional (3D) mobility model. The ground base stations (GBSs) equipped with practical down-tilted antenna

Xianzhe Dai, Yukai Sun

In this note, we consider the positive mass theorem for Riemannian manifolds $(M^{n},g)$ asymptotic to $(\mathbb{R}^{k}\times X^{n-k}, g_{\mathbb{R}^{k}}+g_{X})$ for $k\geq 3$ by studying the corresponding compactification problem.

Heng Du, Tong Liu

We show all Laurent $F$-crystals over $p$-adic fields are overconvergent.

Vaishanth Ramaraj, Atharva Paralikar, Eung Joo Lee, Syed Muhammad Anwar

In this paper, we propose a modular navigation system that can be mounted on a regular powered wheelchair to assist disabled children and the elderly with autonomous mobility and shared-control features. The lack of independent mobility drastically affects an individual's mental and physical health making them feel less self-reliant, especially children with

Changyong Shu, JIajun Deng, Fisher Yu, Yifan Liu

Transformer-based methods have swept the benchmarks on 2D and 3D detection on images. Because tokenization before the attention mechanism drops the spatial information, positional encoding becomes critical for those methods. Recent works found that encodings based on samples of the 3D viewing rays can significantly improve the quality of multi-camera 3D obje

Yuhao Nie, Xiatong Li, Quentin Paletta, Max Aragon

Sky-image-based solar forecasting using deep learning has been recognized as a promising approach in reducing the uncertainty in solar power generation. However, one of the biggest challenges is the lack of massive and diversified sky image samples. In this study, we present a comprehensive survey of open-source ground-based sky image datasets for very short

Emile Anand, Charles Steinhardt, Martin Hansen

Civilizations have tried to make drinking water safe to consume for thousands of years. The process of determining water contaminants has evolved with the complexity of the contaminants due to pesticides and heavy metals. The routine procedure to determine water safety is to use targeted analysis which searches for specific substances from some known list; h

Zhaorong He, Zhongqiang Yang, Dongsheng Zhao

The study of weak domains and quasicontinuous domains leads to the consideration of two types generalizations of domains. In the current paper, we define the weak way-below relation between two nonempty subsets of a poset and quasiexact posets. We prove some connections among quasiexact posets, quasicontinuous domains and weak domains. Furthermore, we introd

Tu Anh-Nguyen, Joey Huchette

We present a technique for neural network verification using mixed-integer programming (MIP) formulations. We derive a \emph{strong formulation} for each neuron in a network using piecewise linear activation functions. Additionally, as in general, these formulations may require an exponential number of inequalities, we also derive a separation procedure that

Jiatong Zhang, Zengwei Yao, Fanglin Chen, Guangming Lu

Vision Transformers have achieved remarkable progresses, among which Swin Transformer has demonstrated the tremendous potential of Transformer for vision tasks. It surmounts the key challenge of high computational complexity by performing local self-attention within shifted windows. In this work we propose the Semantic-Aware Local-Global Vision Transformer (

Pierre-Antoine Bernard, Christino Tamon, Luc Vinet, Weichen Xie

We consider quantum state transfer on finite graphs which are attached to infinite paths. The finite graph represents an operational quantum system for performing useful quantum information tasks. In contrast, the infinite paths represent external infinite-dimensional systems which have limited (but nontrivial) interaction with the finite quantum system. We

Kaihong Wang, Donghyun Kim, Rogerio Feris, Kate Saenko

While transformers have greatly boosted performance in semantic segmentation, domain adaptive transformers are not yet well explored. We identify that the domain gap can cause discrepancies in self-attention. Due to this gap, the transformer attends to spurious regions or pixels, which deteriorates accuracy on the target domain. We propose to perform adaptat

Ping Xi

We prove non-trivial upper bounds for general bilinear forms with trace functions of bountiful sheaves, where the supports of two variables can be arbitrary subsets in $\mathbf{F}_p$ of suitable sizes. This essentially recovers the P\'olya-Vinogradov range, and also applies to symmetric powers of Kloosterman sums and Frobenius traces of elliptic curves. In t

Renhe Jiang, Zhaonan Wang, Jiawei Yong, Puneet Jeph

Traffic forecasting as a canonical task of multivariate time series forecasting has been a significant research topic in AI community. To address the spatio-temporal heterogeneity and non-stationarity implied in the traffic stream, in this study, we propose Spatio-Temporal Meta-Graph Learning as a novel Graph Structure Learning mechanism on spatio-temporal d

Sreyan Ghosh, Utkarsh Tyagi, Sonal Kumar, Manan Suri

Disfluency, though originating from human spoken utterances, is primarily studied as a uni-modal text-based Natural Language Processing (NLP) task. Based on early-fusion and self-attention-based multimodal interaction between text and acoustic modalities, in this paper, we propose a novel multimodal architecture for disfluency detection from individual utter

Jeff Z. HaoChen, Tengyu Ma

Understanding self-supervised learning is important but challenging. Previous theoretical works study the role of pretraining losses, and view neural networks as general black boxes. However, the recent work of Saunshi et al. argues that the model architecture -- a component largely ignored by previous works -- also has significant influences on the downstre

Ziang Niu, Abhinav Chakraborty, Oliver Dukes, Eugene Katsevich

Model-X approaches to testing conditional independence between a predictor and an outcome variable given a vector of covariates usually assume exact knowledge of the conditional distribution of the predictor given the covariates. Nevertheless, model-X methodologies are often deployed with this conditional distribution learned in sample. We investigate the co

Yixin Li, Wei Xiong, Lei Li, Zhuoming Zhou

CdTe is II-VI semiconductor material with excellent characteristics and has demonstrated promising potential for application in the photovoltaic field. The electronic properties of Cd43Te28 with microporous structures have been investigated based on density functional theory. The newly established binding-energy and bond-charge model have been used to conver

Jesús Sánchez-Guevara

In this article we present a detailed study of the existing constructions of colilimits in the category of symmetrical operations. In addition, some examples of operads obtained from colimits of other operads are presented.

Aythami Bethencourt-de-León, So Takao

In this work, we demonstrate well-posedness and regularisation by noise results for a class of geometric transport equations that contains, among others, the linear transport and continuity equations. This class is known as linear advection of $k$-forms. In particular, we prove global existence and uniqueness of $L^p$-solutions to the stochastic equation, dr

Tiantian Fang, Ruoyu Sun, Alex Schwing

Generative adversarial nets (GANs) have been remarkably successful at learning to sample from distributions specified by a given dataset, particularly if the given dataset is reasonably large compared to its dimensionality. However, given limited data, classical GANs have struggled, and strategies like output-regularization, data-augmentation, use of pre-tra

Jesús Sánchez-Guevara

In this paper we introduce the concept of L-algebras, which can be seen as a generalization of the structure determined by the Eilenberg-Mac lane transformation and Alexander-Whitney diagonal in chain complexes. In this sense, our main result states that L-algebras are endowed with an E-infinity coalgebra struture, like the one determined by the Barrat-Eccle

Yichen Zhu, Michele Peruzzi, Cheng Li, David B. Dunson

In geostatistical problems with massive sample size, Gaussian processes can be approximated using sparse directed acyclic graphs to achieve scalable $O(n)$ computational complexity. In these models, data at each location are typically assumed conditionally dependent on a small set of parents which usually include a subset of the nearest neighbors. These meth

Jenny Huang, Raphaël Morsomme, David Dunson, Jason Xu

Throughout the course of an epidemic, the rate at which disease spreads varies with behavioral changes, the emergence of new disease variants, and the introduction of mitigation policies. Estimating such changes in transmission rates can help us better model and predict the dynamics of an epidemic, and provide insight into the efficacy of control and interve

Leo Digiosia

We compute the cylindrical contact homology of the links of the simple singularities. These manifolds are contactomorphic to $S^3/G$ for finite subgroups $G\subset\text{SU}(2)$. We perturb the degenerate contact form on $S^3/G$ with a Morse function, invariant under the corresponding $H\subset\text{SO}(3)$ action on $S^2$, to achieve nondegeneracy up to an a

Marcelo Epstein

Although it is often asserted that, in view of their reduced length, axially compressible beams have a higher buckling load than their inextensible counterpart, a detailed analysis demnstrates that this is not necessarily the case. The argument to arrive at this conclusion is made in terms of relatively straightforward concepts of elasticity and structural m

Jan P. Unsleber, Hongbin Liu, Leopold Talirz, Thomas Weymuth

Quantum chemical calculations on atomistic systems have evolved into a standard approach to study molecular matter. These calculations often involve a significant amount of manual input and expertise although most of this effort could be automated, which would alleviate the need for expertise in software and hardware accessibility. Here, we present the AutoR

Christina M. Rost, Daniel L. Schmuckler, Clifton Bumgardner, Md Shafkat Bin Hoque

As various property studies continue to emerge on high entropy and entropy-stabilized ceramics, we seek further understanding of property changes across the phase boundary between \enquote{high-entropy} and \enquote{entropy-stabilized}. The thermal and mechanical properties of bulk ceramic entropy stabilized oxide composition Mg$_{0.2}$Co$_{0.2}$Ni$_{0.2}$Cu

Hong-Quan Tran

We consider the Symmetric Simple Exclusion Process (SSEP) on the segment with two reservoirs of densities $p, q \in (0,1)$ at the two endpoints. We show that the system exhibits cutoff with a diffusive window, thus confirming a conjecture of Gantert, Nestoridi, and Schmid in \cite{Gantert2020}. In particular, our result covers the regime $p \neq q$, where th

Omar Hashash, Christina Chaccour, Walid Saad, Kei Sakaguchi

Accommodating digital twins (DTs) in the metaverse is essential to achieving digital reality. This need for integrating DTs into the metaverse while operating them at the network edge has increased the demand for a decentralized edge-enabled metaverse. Hence, to consolidate the fusion between real and digital entities, it is necessary to harmonize the intero

Khaywah Mohammad, Potdevin Audrey, Rvert François, Mahiou Rachid

Improving phosphor photoluminescence efficiency is a key parameter to boost the performances of many optical devices. In this work, colloidal silver nanocubes, homogeneously spread on a luminescent surface, have proved to help both injecting and extracting light in and out of the photoluminescent layer and hence contributed significantly to the enhancement o

Alexander J. Izzo

It is shown that there exists a compact planar set K such that the uniform algebra R(K) is nontrivial and strongly regular. This settles an issue raised by Donald Wilken 55 years ago. It is shown that the set K can be chosen such that, in addition, R(K) is not weakly amenable. It is also shown that there exists a uniform algebra that has bounded relative uni

Güray Hatipoğlu

This paper focuses on the utility of various data transformation techniques, which might be under the principal component analysis (PCA) category, on exoplanet research. The first section introduces the methodological background of PCA and related techniques. The second section reviews the studies which utilized these techniques in the exoplanet research fie

Matthew Nicoletti

We study the dimer model on special subgraphs of the square hexagon lattice called "tower graphs" of size $N$. Using integrable probability techniques, we confirm that as $N \rightarrow \infty$, the local statistics are translation invariant Gibbs measures, as conjectured by Kenyon-Okounkov-Sheffield. We also present a 2+1-dimensional discrete time growth pr

Xiaolei Zhang, Shiqi Xing, Wei Qi

In this paper, we first introduce and study the notions of strongly $\phi$-flat modules and strongly nonnil-injective modules. And then, we investigate the homology dimensions of modules and rings in terms of these two notions. Finally we give a new homological characterizations of $\phi$-Dedekind rings and $\phi$-\Prufer\ rings.

Dule Shu, Zijie Li, Amir Barati Farimani

Machine learning models are gaining increasing popularity in the domain of fluid dynamics for their potential to accelerate the production of high-fidelity computational fluid dynamics data. However, many recently proposed machine learning models for high-fidelity data reconstruction require low-fidelity data for model training. Such requirement restrains th

De-Zhang Li, Wei-Jie Huang, Yao Yao, Xiao-Bao Yang

Since the problem of the residual entropy of square ice was exactly solved, exact solutions for two-dimensional realistic ice models have been of interest. In this paper, we study the exact residual entropy of ice hexagonal monolayer in two cases. In the case that the external electric field along the z-axis exists, we map the hydrogen configurations into th

Zach Hunter

The "pancake problem" asks how many prefix reversals are sufficient to sort any permutation $\pi \in \mathcal{S}_k$ to the identity. We write $f(k)$ to denote this quantity. The best known bounds are that $\frac{15}{14}k -O(1) \le f(k)\le \frac{18}{11}k+O(1)$. The proof of the upper bound is computer-assisted, and considers thousands of cases. We consider $h

Lindsey J. Heagy, Douglas W. Oldenburg

Electromagnetic methods are increasingly being applied in settings with steel infrastructure. These include applications such as monitoring of CO2 sequestration or even assessing the integrity of a wellbore. In this paper, we examine the impacts of the magnetic permeability of a steel-cased well on electromagnetic responses in grounded source experiments. We

Petros Petsinis, Andreas Pavlogiannis, Panagiotis Karras

The Voter model is a well-studied stochastic process that models the invasion of a novel trait $A$ (e.g., a new opinion, social meme, genetic mutation, magnetic spin) in a network of individuals (agents, people, genes, particles) carrying an existing resident trait $B$. Individuals change traits by occasionally sampling the trait of a neighbor, while an inva

Aleksandr Berdnikov

We construct embeddings of simplicial complexes into a (surface of a) simplicial ball whose triangulation has bounded degrees and low volume. This construction can be used either to efficiently "simplify a complicated space" by realizing it as a part of a ball/sphere, or to "complexify" a sphere - to give it a specific metric that inherits desired properties

Volker Koch, Volodymyr Vovchenko

We study the equation of state of a mixture of (quasi-)free constituent quarks and nucleons with hard-core repulsion at zero temperature. Two opposite scenarios for the realization of the Pauli exclusion principle are considered: (i) a Fermi sea of quarks surrounded by a shell of baryons -- the quarkyonic matter, and (ii) a Fermi sea of nucleons surrounded b

Haitz Sáez de Ocáriz Borde, Anees Kazi, Federico Barbero, Pietro Liò

Graph Neural Networks usually rely on the assumption that the graph topology is available to the network as well as optimal for the downstream task. Latent graph inference allows models to dynamically learn the intrinsic graph structure of problems where the connectivity patterns of data may not be directly accessible. In this work, we generalize the discret

Charles Lovering, Jessica Zosa Forde, George Konidaris, Ellie Pavlick

AlphaZero, an approach to reinforcement learning that couples neural networks and Monte Carlo tree search (MCTS), has produced state-of-the-art strategies for traditional board games like chess, Go, shogi, and Hex. While researchers and game commentators have suggested that AlphaZero uses concepts that humans consider important, it is unclear how these conce

Mohammad Javad Sojdeh, Mehdi Letafati, Seyed Pooya Shariatpanahi, Babak Hossein Khalaj

In this paper, we consider multiple cache-enabled end-users connected to multiple transmitters through a linear network. We also prevent a totally passive eavesdropper, who sniffs the packets in the delivery phase, from obtaining any information about the original files in cache-aided networks. Three different secure centralized multi-transmitter coded cachi

Waverly Wei, Maya Petersen, Mark J van der Laan, Zeyu Zheng

In biomedical science, analyzing treatment effect heterogeneity plays an essential role in assisting personalized medicine. The main goals of analyzing treatment effect heterogeneity include estimating treatment effects in clinically relevant subgroups and predicting whether a patient subpopulation might benefit from a particular treatment. Conventional appr

Itai Arieli, Ivan Geffner, Moshe Tennenholtz

We study an information design problem with two informed senders and a receiver in which, in contrast to traditional Bayesian persuasion settings, senders do not have commitment power. In our setting, a trusted mediator/platform gathers data from the senders and recommends the receiver which action to play. We characterize the set of implementable action dis

Ethan Rathbun, Kaleel Mahmood, Sohaib Ahmad, Caiwen Ding

Recent advances in adversarial machine learning have shown that defenses considered to be robust are actually susceptible to adversarial attacks which are specifically customized to target their weaknesses. These defenses include Barrage of Random Transforms (BaRT), Friendly Adversarial Training (FAT), Trash is Treasure (TiT) and ensemble models made up of V

Samuel Hess, Gregory Ditzler

Few-shot learning is a rapidly evolving area of research in machine learning where the goal is to classify unlabeled data with only one or "a few" labeled exemplary samples. Neural networks are typically trained to minimize a distance metric between labeled exemplary samples and a query set. Early few-shot approaches use an episodic training process to sub-s

Britty Baby, Daksh Thapar, Mustafa Chasmai, Tamajit Banerjee

Minimally invasive surgeries and related applications demand surgical tool classification and segmentation at the instance level. Surgical tools are similar in appearance and are long, thin, and handled at an angle. The fine-tuning of state-of-the-art (SOTA) instance segmentation models trained on natural images for instrument segmentation has difficulty dis

Amin Azmoodeh, Ali Dehghantanha

According to the 2020 cyber threat defence report, 78% of Canadian organizations experienced at least one successful cyberattack in 2020. The consequences of such attacks vary from privacy compromises to immersing damage costs for individuals, companies, and countries. Specialists predict that the global loss from cybercrime will reach 10.5 trillion US dolla

Sébastien Lachapelle, Tristan Deleu, Divyat Mahajan, Ioannis Mitliagkas

Although disentangled representations are often said to be beneficial for downstream tasks, current empirical and theoretical understanding is limited. In this work, we provide evidence that disentangled representations coupled with sparse base-predictors improve generalization. In the context of multi-task learning, we prove a new identifiability result tha

Adam Topaz

This paper shows that algebraic (in)dependence is encoded in Milnor K-theory of fields. As an application, we show that the isomorphism type of a field is determined by its Milnor K-theory, up to purely inseparable extensions, in most situations.

Lily Chung, Erik D. Demaine, Dylan Hendrickson, Jayson Lynch

We prove essentially optimal fine-grained lower bounds on the gap between a data structure and a partially retroactive version of the same data structure. Precisely, assuming any one of three standard conjectures, we describe a problem that has a data structure where operations run in $O(T(n,m))$ time per operation, but any partially retroactive version of t

Jianzhe Gu, Lining Yao

Living creatures and machines interact with the world through their morphology and motions. Recent advances in creating bio-inspired morphing robots and machines have led to the study of variable geometry truss (VGT), structures that can approximate arbitrary geometries and has large degree of freedom to deform. However, they are limited to simple geometries

Jaydeep Rade, Soumik Sarkar, Anwesha Sarkar, Adarsh Krishnamurthy

Recent developments in deep learning-based methods demonstrated its potential to predict the 3D protein structures using inputs such as protein sequences, Cryo-Electron microscopy (Cryo-EM) images of proteins, etc. However, these methods struggle to predict the protein complexes (PC), structures with more than one protein. In this work, we explore the atomic

Ramen Ghosh, Jakub Marecek

We provide an overview of iterated function systems (IFS), where randomly chosen state-to-state maps are applied iteratively to a state. We aim to summarize the state of art and, where possible, identify fundamental challenges and opportunities for further research.

Tyler Lutz, Sonja K. Richter, Andreas M. Menzel

Thin fluid or elastic films and membranes are found in nature and technology, for instance, as confinements of living cells or in loudspeakers. When applying a net force, resulting flows in an unbounded two-dimensional incompressible low-Reynolds-number fluid or displacements in a two-dimensional linearly elastic solid seem to diverge logarithmically with th

David Lafontaine, Euan A. Spence

We prove sharp bounds on certain impedance-to-impedance maps (and their compositions) for the Helmholtz equation with large wavenumber (i.e., at high-frequency) using semiclassical defect measures. The paper [GGGLS] (Gong-Gander-Graham-Lafontaine-Spence, 2022) recently showed that the behaviour of these impedance-to-impedance maps (and their compositions) di

Peng Zhang

Given vectors $\mathbb{v}_1, \ldots, \mathbb{v}_n \in \mathbb{R}^d$ with Euclidean norm at most $1$ and $\mathbb{x}_0 \in [-1,1]^n$, our goal is to sample a random signing $\mathbb{x} \in \{\pm 1\}^n$ with $\mathbb{E}[\mathbb{x}] = \mathbb{x}_0$ such that the operator norm of the covariance of the signed sum of the vectors $\sum_{i=1}^n \mathbb{x}(i) \mathbb

Saeed S. Jahromi, Roman Orus

Deep neural networks (NNs) encounter scalability limitations when confronted with a vast array of neurons, thereby constraining their achievable network depth. To address this challenge, we propose an integration of tensor networks (TN) into NN frameworks, combined with a variational DMRG-inspired training technique. This in turn, results in a scalable tenso

F. K. Dankar, M. K. Ibrahim

Data synthesis is a privacy enhancing technology aiming to produce realistic and timely data when real data is hard to obtain. Utility of synthetic data generators (SDGs) has been investigated through different utility metrics. These metrics have been found to generate conflicting conclusions making direct comparison of SDGs surprisingly difficult. Moreover,

Bowei Wu, Min Hyung Cho

A boundary integral equation method for the 3-D Helmholtz equation in multilayered media with many quasi-periodic layers is presented. Compared with conventional quasi-periodic Green's function method, the new method is robust at all scattering parameters. A periodizing scheme is used to decompose the solution into near- and far-field contributions. The near

Max Siebenborn, Boris Belousov, Junning Huang, Jan Peters

Decision Transformer (DT) is a recently proposed architecture for Reinforcement Learning that frames the decision-making process as an auto-regressive sequence modeling problem and uses a Transformer model to predict the next action in a sequence of states, actions, and rewards. In this paper, we analyze how crucial the Transformer model is in the complete D

Beichen Zhang, Huiqi Wang, Amani Alabri, Karol Bot

The accurate characterization of the severity of the wildfire event strongly contributes to the characterization of the fuel conditions in fire-prone areas, and provides valuable information for disaster response. The aim of this study is to develop an autonomous system built on top of high-resolution multispectral satellite imagery, with an advanced deep le

Shaoyu Huang, Kiumars Kaveh

A toric principal $G$-bundle is a principal $G$-bundle over a toric variety together with a torus action commuting with the $G$-action. In a recent paper, extending the Klyachko classification of toric vector bundles, Chris Manon and the second author give a classification of toric principal bundles using "piecewise linear maps" to the (extended) Tits buildi

Jennifer Grannen, Yilin Wu, Suneel Belkhale, Dorsa Sadigh

A robotic feeding system must be able to acquire a variety of foods. Prior bite acquisition works consider single-arm spoon scooping or fork skewering, which do not generalize to foods with complex geometries and deformabilities. For example, when acquiring a group of peas, skewering could smoosh the peas while scooping without a barrier could result in chas

Ted Lentsch, Zimin Xia, Holger Caesar, Julian F. P. Kooij

This work addresses cross-view camera pose estimation, i.e., determining the 3-Degrees-of-Freedom camera pose of a given ground-level image w.r.t. an aerial image of the local area. We propose SliceMatch, which consists of ground and aerial feature extractors, feature aggregators, and a pose predictor. The feature extractors extract dense features from the g