English
Related papers

Related papers: Exponential Decay of Sensitivity in Graph-Structur…

200 papers

A wide array of graphical models can be parametrised to have atomic probabilities represented by monomial functions. Such monomial structure has proven very useful when studying robustness under the assumption of a multilinear model where…

Statistics Theory · Mathematics 2019-01-09 Manuele Leonelli

We investigate the vulnerabilities of consensus-based distributed optimization protocols to nodes that deviate from the prescribed update rule (e.g., due to failures or adversarial attacks). We first characterize certain fundamental…

Systems and Control · Computer Science 2016-06-30 Shreyas Sundaram , Bahman Gharesifard

Graph convolutional neural networks (GCNNs) are nonlinear processing tools to learn representations from network data. A key property of GCNNs is their stability to graph perturbations. Current analysis considers deterministic perturbations…

Machine Learning · Computer Science 2021-06-22 Zhan Gao , Elvin Isufi , Alejandro Ribeiro

Effective resistances are ubiquitous in graph algorithms and network analysis. In this work, we study sublinear time algorithms to approximate the effective resistance of an adjacent pair $s$ and $t$. We consider the classical adjacency…

Data Structures and Algorithms · Computer Science 2023-07-06 Dongrun Cai , Xue Chen , Pan Peng

Graph neural networks (GNNs) have become increasingly popular for classification tasks on graph-structured data. Yet, the interplay between graph topology and feature evolution in GNNs is not well understood. In this paper, we focus on…

Machine Learning · Computer Science 2023-10-27 Vignesh Kothapalli , Tom Tirer , Joan Bruna

Graph Neural Networks (GNNs) have emerged as highly successful tools for graph-related tasks. However, real-world problems involve very large graphs, and the compute resources needed to fit GNNs to those problems grow rapidly. Moreover, the…

Machine Learning · Computer Science 2021-11-11 Eitan Kosman , Joel Oren , Dotan Di Castro

This paper shows that the implicit bias of gradient descent on linearly separable data is exactly characterized by the optimal solution of a dual optimization problem given by a smoothed margin, even for general losses. This is in contrast…

Machine Learning · Computer Science 2020-11-13 Ziwei Ji , Matus Telgarsky

Termination analyses investigate the termination behavior of programs, intending to detect nontermination, which is known to cause a variety of program bugs (e.g. hanging programs, denial-of-service vulnerabilities). Beyond formal…

Software Engineering · Computer Science 2022-08-01 Yoav Alon , Cristina David

In this paper we study numerical approximations of the evolution problem for the nonlocal $p$-Laplacian with homogeneous Neumann boundary conditions. First, we derive a bound on the distance between two continuous-in-time trajectories…

Analysis of PDEs · Mathematics 2019-04-29 Hafiene Yosra , Jalal Fadili , Abderrahim Elmoataz

Modern Natural Language Processing (NLP) models are known to be sensitive to input perturbations and their performance can decrease when applied to real-world, noisy data. However, it is still unclear why models are less robust to some…

Computation and Language · Computer Science 2022-03-21 Yunxiang Zhang , Liangming Pan , Samson Tan , Min-Yen Kan

We study how neural networks trained by gradient descent extrapolate, i.e., what they learn outside the support of the training distribution. Previous works report mixed empirical results when extrapolating with neural networks: while…

Machine Learning · Computer Science 2021-03-04 Keyulu Xu , Mozhi Zhang , Jingling Li , Simon S. Du , Ken-ichi Kawarabayashi , Stefanie Jegelka

Message Passing Neural Networks (MPNNs) hold a key position in machine learning on graphs, but they struggle with unintended behaviors, such as over-smoothing and over-squashing, due to irregular data structures. The observation and…

Machine Learning · Computer Science 2025-08-26 Junhyun Lee , Veronika Thost , Bumsoo Kim , Jaewoo Kang , Tengfei Ma

A common theoretical approach to understanding neural networks is to take an infinite-width limit, at which point the outputs become Gaussian process (GP) distributed. This is known as a neural network Gaussian process (NNGP). However, the…

Machine Learning · Statistics 2025-06-26 Ben Anson , Edward Milsom , Laurence Aitchison

The accuracy of probability distributions inferred using machine-learning algorithms heavily depends on data availability and quality. In practical applications it is therefore fundamental to investigate the robustness of a statistical…

Machine Learning · Statistics 2018-10-01 Christiane Goergen , Manuele Leonelli

We consider the problem of learning a graph from a finite set of noisy graph signal observations, the goal of which is to find a smooth representation of the graph signal. Such a problem is motivated by the desire to infer relational…

Machine Learning · Computer Science 2023-02-08 Xiaolu Wang , Yuen-Man Pun , Anthony Man-Cho So

We consider a nonlinear parabolic equation with an exponential nonlinearity which is critical with respect to the growth of the nonlinearity and the regularity of the initial data. After showing the equivalence of the notions of weak and…

Analysis of PDEs · Mathematics 2017-12-01 Giulia Furioli , Tatsuki Kawakami , Bernhard Ruf , Elide Terraneo

Primal-dual methods for solving convex optimization problems with functional constraints often exhibit a distinct two-stage behavior. Initially, they converge towards a solution at a sublinear rate. Then, after a certain point, the method…

Optimization and Control · Mathematics 2026-02-12 Mateo Díaz , Pedro Izquierdo Lehmann , Haihao Lu , Jinwen Yang

While promising, graph reasoners based on Large Language Models (LLMs) lack built-in invariance to symmetries in graph representations. Operating on sequential graph serializations, LLMs can produce different outputs under node reindexing,…

Large Language Models (LLMs) have demonstrated remarkable performance across various natural language processing tasks. Recently, several LLMs-based pipelines have been developed to enhance learning on graphs with text attributes,…

Machine Learning · Computer Science 2024-07-30 Kai Guo , Zewen Liu , Zhikai Chen , Hongzhi Wen , Wei Jin , Jiliang Tang , Yi Chang

A quadratic approximation of neural network loss landscapes has been extensively used to study the optimization process of these networks. Though, it usually holds in a very small neighborhood of the minimum, it cannot explain many…

Machine Learning · Computer Science 2022-06-23 Chao Ma , Daniel Kunin , Lei Wu , Lexing Ying