May 2023 arXiv papers — page 28

Corina Pasareanu, Ravi Mangal, Divya Gopinath, Huafeng Yu

Providing safety guarantees for autonomous systems is difficult as these systems operate in complex environments that require the use of learning-enabled components, such as deep neural networks (DNNs) for visual perception. DNNs are hard to analyze due to their size (they can have thousands or millions of parameters), lack of formal specifications (DNNs are

Shuhei Watanabe

Hyperparameter (HP) optimization of deep learning (DL) is essential for high performance. As DL often requires several hours to days for its training, HP optimization (HPO) of DL is often prohibitively expensive. This boosted the emergence of tabular or surrogate benchmarks, which enable querying the (predictive) performance of DL with a specific HP configur

Sizhen Bian, Alexander Rupp, Michele Magno

In recent years, working out in the gym has gotten increasingly more data-focused and many gym enthusiasts are recording their exercises to have a better overview of their historical gym activities and to make a better exercise plan for the future. As a side effect, this recording process has led to a lot of time spent painstakingly operating these apps by p

Sizhen Bian, Lukas Schulthess, Georg Rutishauser, Alfio Di Mauro

The interest in dynamic vision sensor (DVS)-powered unmanned aerial vehicles (UAV) is raising, especially due to the microsecond-level reaction time of the bio-inspired event sensor, which increases robustness and reduces latency of the perception tasks compared to a RGB camera. This work presents ColibriUAV, a UAV platform with both frame-based and event-ba

Cuong Tran, Ferdinando Fioretto

In domains with high stakes such as law, recruitment, and healthcare, learning models frequently rely on sensitive user data for inference, necessitating the complete set of features. This not only poses significant privacy risks for individuals but also demands substantial human effort from organizations to verify information accuracy. This paper asks wheth

Mircea Petrache, Shubhendu Trivedi

The explicit incorporation of task-specific inductive biases through symmetry has emerged as a general design precept in the development of high-performance machine learning models. For example, group equivariant neural networks have demonstrated impressive performance across various domains and applications such as protein and drug design. A prevalent intui

Thomas Polstra, Austyn Simpson, Kevin Tucker

We analyze adjunction and inversion of adjunction for the $F$-purity of divisor pairs in characteristic $p > 0$. In this vein, we give a complete answer for principal divisors under $\mathbb{Q}$-Gorenstein assumptions but without divisibility restrictions on the index. We also give a detailed analysis relating the $F$-purity of the pairs $(R,\Delta + D)$ and

Yan Ding, Xiaohan Zhang, Saeid Amiri, Nieqing Cao

Task planning systems have been developed to help robots use human knowledge (about actions) to complete long-horizon tasks. Most of them have been developed for "closed worlds" while assuming the robot is provided with complete world knowledge. However, the real world is generally open, and the robots frequently encounter unforeseen situations that can pote

Saurabh Sihag, Gonzalo Mateos, Corey McMillan, Alejandro Ribeiro

In computational neuroscience, there has been an increased interest in developing machine learning algorithms that leverage brain imaging data to provide estimates of "brain age" for an individual. Importantly, the discordance between brain age and chronological age (referred to as "brain age gap") can capture accelerated aging due to adverse health conditio

Sina Kazemian, Giovanni Fanchini

To understand the essential properties of Dirac crystals, such as their thermal conductivity, we require models that consider the interaction between Dirac electrons and dispersive acoustic phonons. The exceptionally high thermal conductivity in 2D Dirac crystals is attributed to near-ideal phonon quantum gases, while undesired limitations arise from electro

Liheng Ma, Chen Lin, Derek Lim, Adriana Romero-Soriano

Transformers for graph data are increasingly widely studied and successful in numerous learning tasks. Graph inductive biases are crucial for Graph Transformers, and previous works incorporate them using message-passing modules and/or positional encodings. However, Graph Transformers that use message-passing inherit known issues of message-passing, and diffe

Aliyah R. Hsu, Yeshwanth Cherapanamjeri, Briton Park, Tristan Naumann

Pre-trained transformers are often fine-tuned to aid clinical decision-making using limited clinical notes. Model interpretability is crucial, especially in high-stakes domains like medicine, to establish trust and ensure safety, which requires human engagement. We introduce SUFO, a systematic framework that enhances interpretability of fine-tuned transforme

José Cantarero, Jorge Gaspar-Lara

For a prime $p$, we show that uniqueness of factorization into irreducible $\Sigma_{p^2}$-invariant representations of $\mathbb{Z}/p \wr \mathbb{Z}/p$ holds if and only if $p=2$. We also show nonuniqueness of factorization for $\Sigma_8$-invariant representations of $D_8 \wr \mathbb{Z}/2$. The representation ring of $\Sigma_{p^2}$-invariant representations o

Louis Gass, Michele Stecconi

Let $f$ be a Gaussian random field on $\mathbb{R}^d$ and let $X$ be the number of critical points of $f$ contained in a compact subset. A long-standing conjecture is that, under mild regularity and non-degeneracy conditions on $f$, the random variable $X$ has finite moments. So far, this has been established only for moments of order lower than three. In thi

C. Vignat, M. Milgram

This manuscript introduces a general multisection identity expressed equivalently in terms of infinite double products and/or infinite double series, from which several new product or summation identities involving special functions including Gamma, hyperbolic trigonometric, polygamma, zeta and Jacobi theta functions, are derived. It is shown that a paramete

Stanley Gudder

Until recently, a quantum instrument was defined to be a completely positive operation-valued measure from the set of states on a Hilbert space to itself. In the last few years, this definition has been generalized to such measures between sets of states from different Hilbert spaces called the input and output Hilbert spaces. This article presents a theory

Boyao Li, Alexander J. Thomson, Houssam Nassif, Matthew M. Engelhard

Deep neural networks (DNNs) lack the precise semantics and definitive probabilistic interpretation of probabilistic graphical models (PGMs). In this paper, we propose an innovative solution by constructing infinite tree-structured PGMs that correspond exactly to neural networks. Our research reveals that DNNs, during forward propagation, indeed perform appro

Yuri Shtanov

We consider a simple scale-invariant action coupling the Higgs field to the metric scalar curvature $R$ and containing an $R^2$ term that exhibits spontaneous breaking of scale invariance and electroweak symmetry. The coefficient of the $R^2$ term in this case determines the self-coupling of the Higgs boson in the Einstein frame, and the scalaron becomes a d

Mher Safaryan, Alexandra Peste, Dan Alistarh

Knowledge distillation is a popular approach for enhancing the performance of ''student'' models, with lower representational capacity, by taking advantage of more powerful ''teacher'' models. Despite its apparent simplicity and widespread use, the underlying mechanics behind knowledge distillation (KD) are still not fully understood. In this work, we shed n

Maha Jarallah Althobaiti

Emotion recognition is a crucial task in Natural Language Processing (NLP) that enables machines to comprehend the feelings conveyed in the text. The applications of emotion recognition are diverse, including mental health diagnosis, student support, and the detection of online suspicious behavior. Despite the substantial amount of literature available on em

M. Mornev

Compared with algebraic varieties the local monodromy of Drinfeld modules appears to be hopelessly complex: The image of the wild inertia subgroup under Tate module representations is infinite save for the case of potential good reduction. Nonetheless we show that Tate modules of Drinfeld modules are ramified in a limited way: The image of a sufficiently dee

Aref Sayareh, Nader Zare, Omid Amini, Arad Firouzkouhi

The RoboCup competitions hold various leagues, and the Soccer Simulation 2D League is a major one among them. Soccer Simulation 2D (SS2D) match involves two teams, including 11 players and a coach, competing against each other. The players can only communicate with the Soccer Simulation Server during the game. This paper presents the latest research of the C

A. I. Ullah Tabassam

Machine Learning Operations (MLOps) is becoming a highly crucial part of businesses looking to capitalize on the benefits of AI and ML models. This research presents a detailed review of MLOps, its benefits, difficulties, evolutions, and important underlying technologies such as MLOps frameworks, Docker, GitHub actions, and Kubernetes. The MLOps workflow, wh

Stanley Cheung, Di Liang, Yuan Yuan, Yiwei Peng

We demonstrate, for the first time, non-volatile charge-trap flash memory (CTM) co-located with heterogeneous III-V/Si photonics. The wafer-bonded III-V/Si CTM cell facilitates non-volatile optical functionality for a variety of devices such as Mach-Zehnder Interferometers (MZIs), asymmetric MZI lattice filters, and ring resonator filters. The MZI CTM exhibi

J. Deride, A. Jofré, R. T. Rockafellar

The Walras approach to equilibrium focuses on the existence of market prices at which the total demands for goods are matched by the total supplies. Trading activities that might identify such prices by bringing agents together as potential buyers and sellers of a good are characteristically absent, however. Anyway, there is no money to pass from one to the

Erlang Surya, Lutz Warnke

We present a simple inductive proof of the Lagrange Inversion Formula.

Sukru Yaren Gelbal, Mustafa Ridvan Cantas, Bilin Aksun Guvenc, Levent Guvenc

Vulnerable Road User (VRU) safety has been an important issue throughout the years as corresponding fatality numbers in traffic have been increasing each year. With the developments in connected vehicle technology, there are new and easier ways of implementing Vehicle to Everything (V2X) communication which can be utilized to provide safety and early warning

Eric V. Strobl

Root causes of disease intuitively correspond to root vertices that increase the likelihood of a diagnosis. This description of a root cause nevertheless lacks the rigorous mathematical formulation needed for the development of computer algorithms designed to automatically detect root causes from data. Prior work defined patient-specific root causes of disea

Achim Zeileis, Roger Bivand, Dirk Eddelbuettel, Kurt Hornik

CRAN Task Views have been available on the Comprehensive R Archive Network since 2005. They provide guidance about which CRAN packages are relevant for tasks related to a certain topic, and can also facilitate automatic installation of all corresponding packages. Motivated by challenges from the growth of CRAN and the R community as a whole since 2005, all o

Ahmed Ghatasheh

We introduce a generalization of Cauchy's mean value theorem for regulated functions. Building on this, we extend both L'Hospital's rule and L'Hospital's monotone rule to quotients of regulated functions. We demonstrate that our extended L'Hospital's rule encompasses both the discrete case, known as the Stolz-Cesaro theorem, and the classical continuous case

F. Martin-Vergara, J. Cuevas-Maraver, P. E. Farrell, F. R. Villatoro

Deflation is an efficient numerical technique for identifying new branches of steady state solutions to nonlinear partial differential equations. Here, we demonstrate how to extend deflation to discover new periodic orbits in nonlinear dynamical lattices. We employ our extension to identify discrete breathers, which are generic exponentially localized, time-

Ben Chugg, Santiago Cortes-Gomez, Bryan Wilder, Aaditya Ramdas

We provide practical, efficient, and nonparametric methods for auditing the fairness of deployed classification and regression models. Whereas previous work relies on a fixed-sample size, our methods are sequential and allow for the continuous monitoring of incoming data, making them highly amenable to tracking the fairness of real-world systems. We also all

Shuyue Lan, Zhilu Wang, Ermin Wei, Amit K. Roy-Chowdhury

Multi-agent applications have recently gained significant popularity. In many computer vision tasks, a network of agents, such as a team of robots with cameras, could work collaboratively to perceive the environment for efficient and accurate situation awareness. However, these agents often have limited computation, communication, and storage resources. Thus

Abhisek Chakraborty

Advances in neuroscience have enabled researchers to measure the activities of large numbers of neurons simultaneously in behaving animals. We have access to the fluorescence of each of the neurons which provides a first-order approximation of the neural activity over time. Determining the exact spike of a neuron from this fluorescence trace constitutes an a

Donghao Ying, Yunkai Zhang, Yuhao Ding, Alec Koppel

We investigate safe multi-agent reinforcement learning, where agents seek to collectively maximize an aggregate sum of local objectives while satisfying their own safety constraints. The objective and constraints are described by {\it general utilities}, i.e., nonlinear functions of the long-term state-action occupancy measure, which encompass broader decisi

Mengzi Amy Guo, Donghao Ying, Javad Lavaei, Zuo-Jun Max Shen

This work is dedicated to the algorithm design in a competitive framework, with the primary goal of learning a stable equilibrium. We consider the dynamic price competition between two firms operating within an opaque marketplace, where each firm lacks information about its competitor. The demand follows the multinomial logit (MNL) choice model, which depend

Chenkun Zhou, Di Wang, Francisco Lagunas, Benjamin Atterberry

Two-dimensional (2D) transition-metal carbides and nitrides (MXenes) show impressive performance in applications, such as supercapacitors, batteries, electromagnetic interference shielding, or electrocatalysis. These materials combine the electronic and mechanical properties of 2D inorganic crystals with chemically modifiable surfaces, and surface-engineered

Liquan Wang, Nikita Dvornik, Rafael Dubeau, Mayank Mittal

When humans perform a task with an articulated object, they interact with the object only in a handful of ways, while the space of all possible interactions is nearly endless. This is because humans have prior knowledge about what interactions are likely to be successful, i.e., to open a new door we first try the handle. While learning such priors without su

Charles Lu, Yaodong Yu, Sai Praneeth Karimireddy, Michael I. Jordan

Conformal prediction is emerging as a popular paradigm for providing rigorous uncertainty quantification in machine learning since it can be easily applied as a post-processing step to already trained models. In this paper, we extend conformal prediction to the federated learning setting. The main challenge we face is data heterogeneity across the clients -

Zikai Xu, John W. Pierre

Forced oscillations threaten the reliability of widearea power systems, and different approaches to estimate forced oscillation have been explored over the past several years. Though these efforts provide powerful tools to estimate a forced oscillation's amplitude, frequency, and phase, a benchmark for estimation accuracy has not been available.

Radoslav Harman, Samuel Rosa

The problem of computing an exact experimental design that is optimal for the least-squares estimation of the parameters of a regression model is considered. We show that this problem can be solved via mixed-integer linear programming (MILP) for a wide class of optimality criteria, including the criteria of A-, I-, G- and MV-optimality. This approach improve

Sandeep Soni, Amanpreet Sihra, Elizabeth F. Evans, Matthew Wilkens

Tracking characters and locations throughout a story can help improve the understanding of its plot structure. Prior research has analyzed characters and locations from text independently without grounding characters to their locations in narrative time. Here, we address this gap by proposing a new spatial relationship categorization task. The objective of t

Zijie Li, Dule Shu, Amir Barati Farimani

Transformer has shown state-of-the-art performance on various applications and has recently emerged as a promising tool for surrogate modeling of partial differential equations (PDEs). Despite the introduction of linear-complexity attention, applying Transformer to problems with a large number of grid points can be numerically unstable and computationally ex

Noga Bar, Raja Giryes

The lottery ticket hypothesis (LTH) has increased attention to pruning neural networks at initialization. We study this problem in the linear setting. We show that finding a sparse mask at initialization is equivalent to the sketching problem introduced for efficient matrix multiplication. This gives us tools to analyze the LTH problem and gain insights into

Aniket Das, Dheeraj Nagaraj

Stein Variational Gradient Descent (SVGD) is a popular variational inference algorithm which simulates an interacting particle system to approximately sample from a target distribution, with impressive empirical performance across various domains. Theoretically, its population (i.e, infinite-particle) limit dynamics is well studied but the behavior of SVGD i

Abhisek Chakraborty, Anirban Bhattacharya, Debdeep Pati

The advent of ML-driven decision-making and policy formation has led to an increasing focus on algorithmic fairness. As clustering is one of the most commonly used unsupervised machine learning approaches, there has naturally been a proliferation of literature on {\em fair clustering}. A popular notion of fairness in clustering mandates the clusters to be {\

Huijun Wang, Oliver Sinnen

The scheduling of task graphs with communication delays has been extensively studied. Recently, new results for the common sub-case of fork-join shaped task graphs were published, including an EPTAS and polynomial algorithms for special cases. These new results modelled the target architecture to consist of homogeneous processors. However, forms of heterogen

Tung Le, Khai Nguyen, Shanlin Sun, Kun Han

Mesh deformation plays a pivotal role in many 3D vision tasks including dynamic simulations, rendering, and reconstruction. However, defining an efficient discrepancy between predicted and target meshes remains an open problem. A prevalent approach in current deep learning is the set-based approach which measures the discrepancy between two surfaces by compa

Matteo Zanfrognini, Alexandre Plaud, Ingrid Stenger, Frédéric Fossard

Despite its simple crystal structure, layered boron nitride features a surprisingly complex variety of phonon-assisted luminescence peaks. We present a combined experimental and theoretical study on ultraviolet-light emission in hexagonal and rhombohedral bulk boron nitride crystals. Emission spectra of high-quality samples are measured via cathodoluminescen

Jason Hoelscher-Obermaier, Julia Persson, Esben Kran, Ioannis Konstas

Recent model editing techniques promise to mitigate the problem of memorizing false or outdated associations during LLM training. However, we show that these techniques can introduce large unwanted side effects which are not detected by existing specificity benchmarks. We extend the existing CounterFact benchmark to include a dynamic component and dub our be

Burhani M. Burhani, Elena Fantino, Roberto Flores, Manuel Sanjurjo-Rivo

This study proposes a new automated strategy for designing and optimizing three-dimensional interplanetary low-thrust (LT) trajectories. The method formulates the design as a hybrid optimal control problem and solves it using a two-step approach. In Step 1, a three-dimensional model based on generalized logarithmic spirals is used with heuristics in combinat

Udaya Ghai, Arushi Gupta, Wenhan Xia, Karan Singh

We investigate robust model-free reinforcement learning algorithms designed for environments that may be dynamic or even adversarial. Traditional state-based policies often struggle to accommodate the challenges imposed by the presence of unmodeled disturbances in such settings. Moreover, optimizing linear state-based policies pose an obstacle for efficient

Roberto Flores, Mauro Pontani, Elena Fantino

The growth of the population of space debris in the geostationary ring and the resulting threat to active satellites require insight into the dynamics of uncontrolled objects in the region. A Monte Carlo simulation analyzed the sensitivity to initial conditions of the long-term evolution of geostationary spacecraft near an unstable point of the geopotential,

Dennis Bonatsos, Andriana Martinou, S. K. Peroulis, T. J. Mertzimekis

Systematics of B(E2) transition rates connecting the first excited 0+ state to the first excited 2+ state of the ground state band in even-even nuclei indicates that shape coexistence of the ground state band and the first excited K=0 band should be expected in nuclei lying within the stripes of nucleon numbers 7-8, 17-20, 34-40, 59-70, 96-112 predicted by t

Hasan Hejbari Zargar, Saha Hejbari Zargar, Raziye Mehri, Farzane Tajidini

Lung cancer is the leading reason behind cancer-related deaths within the world. Early detection of lung nodules is vital for increasing the survival rate of cancer patients. Traditionally, physicians should manually identify the world suspected of getting carcinoma. When developing these detection systems, the arbitrariness of lung nodules' shape, size, and

Raju Baral, Milinda Abeykoon, Branton J. Campbell, Benjamin A. Frandsen

We present a comprehensive x-ray scattering study of spontaneous magnetostriction in hexagonal MnTe, an antiferromagnetic semiconductor with a Neel temperature of $T_{\mathrm{N}} = 307$ K. We observe the largest spontaneous magnetovolume effect known for an antiferromagnet, reaching a volume contraction of $|\Delta V/V| > 7 \times 10^{-3}$. This can be justi

Elena Fantino, Burhani M. Burhani, Roberto Flores, Elisa Maria Alessi

We present a trajectory concept for a small mission to the four inner large satellites of Saturn. Leveraging the high efficiency of electric propulsion, the concept enables orbit insertion around each of the moons, for arbitrarily long close observation periods. The mission starts with a EVVES interplanetary segment, where a combination of multiple gravity a

Eliya Nachmani, Alon Levkovitch, Yifan Ding, Chulayuth Asawaroengchai

This paper presents Translatotron 3, a novel approach to unsupervised direct speech-to-speech translation from monolingual speech-text datasets by combining masked autoencoder, unsupervised embedding mapping, and back-translation. Experimental results in speech-to-speech translation tasks between Spanish and English show that Translatotron 3 outperforms a ba

A. Lee, H. -H. Kung, Xueyun Wang, S. -W. Cheong

We study surface states in the three-dimensional topological insulators Bi$_2$Te$_{3-x}$Se$_{x}$ (x = 0, 2, 3) by polarization resolved resonant Raman spectroscopy. By tracking the spectral intensity of the surface phonon modes with respect to the incident photon energy, we show that the surface phonons are qualitatively similar to their bulk counterparts. U

Rishabh Sharma, Smarajit Karmakar

Investigating the behavior of amorphous solids under various external loading conditions continues to be an intriguing area of research with significant practical implications. In this study, we demonstrate the utilization of self-motility as a means to anneal glasses and use that as a means to fine-tune the failure mode of the system under uniaxial tensile

Jeffrey Kuan

A previous paper of the author developed a general method for producing explicit central elements of quantized Lie algebras using Lusztig's inner product. This method had previously been applied for the type $C_2$, $D_3$ and $D_4$ Lie algebras. The current paper repeats the calculation for the type $B_2$ Lie algebra, which is actually isomorphic to the $C_2$

Guanghui Wang, Zihao Hu, Claudio Gentile, Vidya Muthukumar

First-order optimization methods tend to inherently favor certain solutions over others when minimizing an underdetermined training objective that has multiple global optima. This phenomenon, known as implicit bias, plays a critical role in understanding the generalization capabilities of optimization algorithms. Recent research has revealed that in separabl

Shashank Kanade

We show that the characters of $\mathfrak{sl}_r$ versions of the $(1,p)$ singlet and the $(1,p)$ triplet VOAs arise as limits of appropriately coloured $\mathfrak{sl}_r$ Jones invariants of certain torus links.

Yu Zhou, Sha Li, Manling Li, Xudong Lin

Online resources such as WikiHow compile a wide range of scripts for performing everyday tasks, which can assist models in learning to reason about procedures. However, the scripts are always presented in a linear manner, which does not reflect the flexibility displayed by people executing tasks in real life. For example, in the CrossTask Dataset, 64.5% of c

Todd Bichoupan

Given a nonempty finite multiset $S$ of positive integers, we wish to find a partially ordered set $P$ of minimal cardinality such that the multiset of cardinalities of all maximal chains in $P$ equals $S$. This paper establishes upper and lower bounds on the size of $P$: $\max(S) + \lceil \log_2 |S| \rceil <= |P| <= \max(S) + |S| - 1$, and both bounds are t

Hammad A. Ayyubi, Rahul Lokesh, Alireza Zareian, Bo Wu

Image-caption pretraining has been quite successfully used for downstream vision tasks like zero-shot image classification and object detection. However, image-caption pretraining is still a hard problem -- it requires multiple concepts (nouns) from captions to be aligned to several objects in images. To tackle this problem, we go to the roots -- the best le

Soheil Karimi Aghda, Dimitri Bogdanovski, Lukas Loefler, Heng Han Sua

Motivated by frequently reported deviations from stoichiometry in cubic transition metal nitride (TMNx) thin films, the effect of N-vacancy concentration on the elastic properties of cubic TiNx, ZrNx, VNx, NbNx, and MoNx (0.72<x<1.00) is systematically studied by density functional theory (DFT) calculations. The predictions are validated experimentally for V

Djemel Ziou

In this paper, we establish the links between the Lehmer and H\"older mean families and maximum weighted likelihood estimator. Considering the regular one-parameter exponential family of probability density functions, we show that the maximum weighted likelihood of the parameter is a generalized weighted mean family from which Lehmer and H\"older mean famili

Gabriel C. Grime, Marisa Roberto, Ricardo L. Viana, Yves Elskens

Nontwist area-preserving maps violate the twist condition along shearless invariant curves, which act as transport barriers in phase space. Recently, some plasma models have presented multiple shearless curves in phase space and these curves can break up independently. In this paper, we describe the different shearless curve breakup scenarios of the so-calle

Andrey Kurenkov, Michael Lingelbach, Tanmay Agarwal, Emily Jin

Embodied AI agents that search for objects in large environments such as households often need to make efficient decisions by predicting object locations based on partial information. We pose this as a new type of link prediction problem: link prediction on partially observable dynamic graphs. Our graph is a representation of a scene in which rooms and objec

Md. Simul Hasan Talukder, Rejwan Bin Sulaiman, Mohammad Raziuddin Chowdhury, Musarrat Saberin Nipun

Potatoes are the third-largest food crop globally, but their production frequently encounters difficulties because of aggressive pest infestations. The aim of this study is to investigate the various types and characteristics of these pests and propose an efficient PotatoPestNet AI-based automatic potato pest identification system. To accomplish this, we cur

Sriram Bhyravarapu, Swati Kumari, I. Vinod Reddy

For a positive integer $k$, a proper $k$-coloring of a graph $G$ is a mapping $f: V(G) \rightarrow \{1,2, \ldots, k\}$ such that $f(u) \neq f(v)$ for each edge $uv$ of $G$. The smallest integer $k$ for which there is a proper $k$-coloring of $G$ is called the chromatic number of $G$, denoted by $\chi(G)$. A locally identifying coloring (for short, lid-colori

Samuel Müller, Matthias Feurer, Noah Hollmann, Frank Hutter

In this paper, we use Prior-data Fitted Networks (PFNs) as a flexible surrogate for Bayesian Optimization (BO). PFNs are neural processes that are trained to approximate the posterior predictive distribution (PPD) through in-context learning on any prior distribution that can be efficiently sampled from. We describe how this flexibility can be exploited for

Adam Storek, Melanie Subbiah, Kathleen McKeown

A major issue with using deep learning models in sensitive applications is that they provide no explanation for their output. To address this problem, unsupervised selective rationalization produces rationales alongside predictions by chaining two jointly-trained components, a rationale generator and a predictor. Although this architecture guarantees that th

Lukas Köbbing, Arnulf Latz, Birger Horstmann

Silicon is a promising anode material for next-generation lithium-ion batteries. However, the volume change and the voltage hysteresis during lithiation and delithiation are two substantial drawbacks to their lifetime and performance. We investigate the reason for the voltage hysteresis in amorphous silicon nanoparticles covered by a solid-electrolyte interp

Steven Dale Cutkosky, Parangama Sarkar

We extend the epsilon multiplicity of ideals defined by Ulrich and Validashti to epsilon multiplicity of filtrations, and show that under mild assumptions this multiplicity exists as a limit. We show that in rather general rings, the epsilon multiplicity of a Q-divisorial filtration is positive if and only if the analytic spread of the filtration is maximal

Thanh-Tung Nguyen, Viktor Schlegel, Abhinav Kashyap, Stefan Winkler

Clinical notes in healthcare facilities are tagged with the International Classification of Diseases (ICD) code; a list of classification codes for medical diagnoses and procedures. ICD coding is a challenging multilabel text classification problem due to noisy clinical document inputs and long-tailed label distribution. Recent automated ICD coding efforts i

Senwei Liang, Aditya N. Singh, Yuanran Zhu, David T. Limmer

We propose a reinforcement learning based method to identify important configurations that connect reactant and product states along chemical reaction paths. By shooting multiple trajectories from these configurations, we can generate an ensemble of configurations that concentrate on the transition path ensemble. This configuration ensemble can be effectivel

Qingqing Cao, Bhargavi Paranjape, Hannaneh Hajishirzi

Large-scale vision language (VL) models use Transformers to perform cross-modal interactions between the input text and image. These cross-modal interactions are computationally expensive and memory-intensive due to the quadratic complexity of processing the input image and text. We present PuMer: a token reduction framework that uses text-informed Pruning a

Yebowen Hu, Tim Ganter, Hanieh Deilamsalehy, Franck Dernoncourt

As the number of recorded meetings increases, it becomes increasingly important to utilize summarization technology to create useful summaries of these recordings. However, there is a crucial lack of annotated meeting corpora for developing this technology, as it can be hard to collect meetings, especially when the topics discussed are confidential. Furtherm

Nils Palumbo, Yang Guo, Xi Wu, Jiefeng Chen

Both transduction and rejection have emerged as important techniques for defending against adversarial perturbations. A recent work by Goldwasser et al. showed that rejection combined with transduction can give provable guarantees (for certain problems) that cannot be achieved otherwise. Nevertheless, under recent strong adversarial attacks, their work was s

Valentin N. Hartmann, Marc Toussaint

We propose an approach to find low-makespan solutions to multi-robot multi-task planning problems in environments where robots block each other from completing tasks simultaneously. We introduce a formulation of the problem that allows for an approach based on greedy descent with random restarts for generation of the task assignment and task sequence. We the

Rustem Takhanov

Valued constraint satisfaction problems with ordered variables (VCSPO) are a special case of Valued CSPs in which variables are totally ordered and soft constraints are imposed on tuples of variables that do not violate the order. We study a restriction of VCSPO, in which soft constraints are imposed on a segment of adjacent variables and a constraint langua

J. Abouie, M. H. Zarei

Enhancing robustness of topological orders against perturbations is one of the main goals in topological quantum computing. Since the kinetic of excitations is in conflict with the robustness of topological orders, any mechanism that reduces the mobility of excitations will be in favor of robustness. A strategy in this direction is adding frustration to topo

Xiangman Li, Miao He, Jianbing Ni

Network slicing in 3GPP 5G system architecture has introduced significant improvements in the flexibility and efficiency of mobile communication. However, this new functionality poses challenges in maintaining the privacy of mobile users, especially in multi-hop environments. In this paper, we propose a secure and privacy-preserving network slicing protocol

Jaydip Sen, Aditya Jaiswal, Anshuman Pathak, Atish Kumar Majee

This paper presents a comparative analysis of the performances of three portfolio optimization approaches. Three approaches of portfolio optimization that are considered in this work are the mean-variance portfolio (MVP), hierarchical risk parity (HRP) portfolio, and reinforcement learning-based portfolio. The portfolios are trained and tested over several s

Hailin Li, Raghavendra Ramachandra

The vulnerabilities of fingerprint authentication systems have raised security concerns when adapting them to highly secure access-control applications. Therefore, Fingerprint Presentation Attack Detection (FPAD) methods are essential for ensuring reliable fingerprint authentication. Owing to the lack of generation capacity of traditional handcrafted based a

Jianxiang Zhao, Xiangman Li, Jianbing Ni

We present a novel privacy-preserving model aggregation for asynchronous federated learning, named PPA-AFL that removes the restriction of synchronous aggregation of local model updates in federated learning, while enabling the protection of the local model updates against the server. In PPA-AFL, clients can proactive decide when to engage in the training pr

Vikrant Rangnekar, Uddeshya Upadhyay, Zeynep Akata, Biplab Banerjee

Dense regression is a widely used approach in computer vision for tasks such as image super-resolution, enhancement, depth estimation, etc. However, the high cost of annotation and labeling makes it challenging to achieve accurate results. We propose incorporating active learning into dense regression models to address this problem. Active learning allows mo

Vishnu Murali, Ashutosh Trivedi, Majid Zamani

A barrier certificate, defined over the states of a dynamical system, is a real-valued function whose zero level set characterizes an inductively verifiable state invariant separating reachable states from unsafe ones. When combined with powerful decision procedures such as sum-of-squares programming (SOS) or satisfiability-modulo-theory solvers (SMT) barrie

Alperen Tercan, Ahana Ghosh, Hasan Ferit Eniser, Maria Christakis

Block-based visual programming environments play an increasingly important role in introducing computing concepts to K-12 students. In recent years, they have also gained popularity in neuro-symbolic AI, serving as a benchmark to evaluate general problem-solving and logical reasoning skills. The open-ended and conceptual nature of these visual programming ta

Iaroslav Kriuchkov, Timo Kuosmanen

Recent advances in operations research and machine learning have revived interest in solving complex real-world, large-size traffic control problems. With the increasing availability of road sensor data, deterministic parametric models have proved inadequate in describing the variability of real-world data, especially in congested area of the density-flow di

Jordan Berthoumieu

This paper deals with the existence of travelling wave solutions for a general one-dimensional nonlinear Schr\"odinger equation. We construct these solutions by minimizing the energy under the constraint of fixed momentum. We also prove that the family of minimizers is stable. Our method is based on recent articles about the orbital stability for the classic

Xuetao Lu, J. Jack Lee

Bayesian hierarchical model (BHM) has been widely used in synthesizing information across subgroups. Identifying heterogeneity in the data and determining proper strength of borrow have long been central goals pursued by researchers. Because these two goals are interconnected, we must consider them together. This joint consideration presents two fundamental

Shyam S. Kamath, Nithya Muraleedharan

A set $D$ of vertices in a graph $G=(V,E)$ is a degree restricted dominating set for $G$ if each vertex $v_i$ in $D$ is dominating atmost $g(d_i)$ vertices of $V-D$, where $g$ is a function restricting the degree value $d_i$ with respect to the given function value $k_i$ for a natural valued function $f$ from the vertex set of the graph. We define three diff

Sergei D. Odintsov, V. K. Oikonomou, German S. Sharov

We study a power-law $F(R)$ gravity with an early dark energy term, that can describe both the early-time and the late-time acceleration of the Universe. We confront this scenario with recent observational data including the Pantheon Type Ia supernovae, measurements of the Hubble parameter $H(z)$ (Cosmic Chronometers), data from Baryon Acoustic Oscillations

Wontaek Kim, Gyouil Jeong, Juseung Oh, Jihun Kim

The efficient optical second-harmonic generation (SHG) of two-dimensional (2D) crystals, coupled with their atomic thickness that circumvents the phase-match problem, has garnered considerable attention. While various 2D heterostructures have shown promising applications in photodetectors, switching electronics, and photovoltaics, the modulation of nonlinear

Eli Temanson, Jessica Baker, Sean Kuvin, Ken Hanselman

The $\mathrm{^{25}Al(p,\gamma)^{26}Si}$ reaction is part of a reaction network with impact on the observed galactic $^{26}$Al abundance. A new determination of the proton strength of the lowest $\ell=0$ proton-resonance in $^{26}$Si is required to more precisely calculate the thermal reaction rate. To this end, the $\mathrm{^{25}Al(d,n)^{26}Si}$ proton-trans

Hongyi Pan, Xin Zhu, Salih Atici, Ahmet Enis Cetin

In this paper, we propose a novel Hadamard Transform (HT)-based neural network layer for hybrid quantum-classical computing. It implements the regular convolutional layers in the Hadamard transform domain. The idea is based on the HT convolution theorem which states that the dyadic convolution between two vectors is equivalent to the element-wise multiplicat

Loring W. Tu

Under Poincar\'e duality, a smooth map of compact oriented manifolds induces a pushforward map in cohomology, called the "Gysin map." It plays an important role in enumerative geometry. Using the equivariant localization formula, the author gave in 2017 a general formula for the Gysin map of a fiber bundle with equivariantly formal fibers. Equivariantly form