English
Related papers

Related papers: Eigenvalue Decay Implies Polynomial-Time Learnabil…

200 papers

For fixed training data and network parameters in the other layers the L1 loss of a ReLU neural network as a function of the first layer's parameters is a piece-wise affine function. We use the Deep ReLU Simplex algorithm to iteratively…

Machine Learning · Statistics 2021-05-07 Peter Hinz

We develop a corrective mechanism for neural network approximation: the total available non-linear units are divided into multiple groups and the first group approximates the function under consideration, the second group approximates the…

Machine Learning · Computer Science 2020-06-23 Guy Bresler , Dheeraj Nagaraj

In this paper we develop a complete analytical framework based on Random Matrix Theory for the performance evaluation of Eigenvalue-based Detection. While, up to now, analysis was limited to false-alarm probability, we have obtained an…

Information Theory · Computer Science 2009-09-23 Federico Penna , Roberto Garello

We study the decentralized online regularized linear regression algorithm over random time-varying graphs. At each time step, every node runs an online estimation algorithm consisting of an innovation term processing its own new…

Machine Learning · Computer Science 2025-10-02 Xiwei Zhang , Tao Li , Xiaozheng Fu

It is well-known that modern neural networks are vulnerable to adversarial examples. To mitigate this problem, a series of robust learning algorithms have been proposed. However, although the robust training error can be near zero via some…

Machine Learning · Computer Science 2022-10-17 Binghui Li , Jikai Jin , Han Zhong , John E. Hopcroft , Liwei Wang

Besides the complexity in time or in number of messages, a common approach for analyzing distributed algorithms is to look at the assumptions they make on the underlying network. We investigate this question from the perspective of network…

Distributed, Parallel, and Cluster Computing · Computer Science 2014-05-02 Arnaud Casteigts , Serge Chaumette , Afonso Ferreira

Graph Neural Networks (GNNs) have achieved remarkable success across diverse tasks on graph-structured data, primarily through the use of learned weights in message passing layers. In this paper, we demonstrate that random weights can be…

Machine Learning · Computer Science 2025-02-04 Thu Bui , Carola-Bibiane Schönlieb , Bruno Ribeiro , Beatrice Bevilacqua , Moshe Eliasof

Arguably the most fundamental question in the theory of generative adversarial networks (GANs) is to understand to what extent GANs can actually learn the underlying distribution. Theoretical and empirical evidence suggests local optimality…

Machine Learning · Computer Science 2022-01-19 Sitan Chen , Jerry Li , Yuanzhi Li , Raghu Meka

Recurrent neural networks (RNN) as used in machine learning are commonly formulated in discrete time, i.e. as recursive maps. This brings a lot of advantages for training models on data, e.g. for the purpose of time series prediction or…

Dynamical Systems · Mathematics 2020-07-02 Zahra Monfared , Daniel Durstewitz

The goal of this paper is to characterize function distributions that deep learning can or cannot learn in poly-time. A universality result is proved for SGD-based deep learning and a non-universality result is proved for GD-based deep…

Machine Learning · Computer Science 2020-01-10 Emmanuel Abbe , Colin Sandon

Recent experiments in neuroscience reveal that task-relevant variables are often encoded in approximately orthogonal subspaces of neural population activity. These disentangled, or abstract, representations have been observed in multiple…

Neurons and Cognition · Quantitative Biology 2026-03-16 Bin Wang , W. Jeffrey Johnston , Stefano Fusi

The last decade has seen the parallel emergence in computational neuroscience and machine learning of neural network structures which spread the input signal randomly to a higher dimensional space; perform a nonlinear activation; and then…

Neural and Evolutionary Computing · Computer Science 2013-06-11 Jonathan Tapson , Andre van Schaik

Neural networks have been used successfully in a variety of fields, which has led to a great deal of interest in developing a theoretical understanding of how they store the information needed to perform a particular task. We study the…

Disordered Systems and Neural Networks · Physics 2022-11-16 Matthias Thamm , Max Staats , Bernd Rosenow

Deep neural networks (DNNs) have demonstrated dominating performance in many fields; since AlexNet, networks used in practice are going wider and deeper. On the theoretical side, a long line of works has been focusing on training neural…

Machine Learning · Computer Science 2019-06-18 Zeyuan Allen-Zhu , Yuanzhi Li , Zhao Song

A particular direction of recent advance about stochastic deep-learning algorithms has been about uncovering a rather mysterious heavy-tailed nature of the stationary distribution of these algorithms, even when the data distribution is not…

Machine Learning · Computer Science 2022-04-28 Sayar Karmakar , Anirbit Mukherjee

Verifying the input-output relationships of a neural network so as to achieve some desired performance specification is a difficult, yet important, problem due to the growing ubiquity of neural nets in many engineering applications. We use…

Machine Learning · Computer Science 2022-12-06 Joshua Pilipovsky , Vignesh Sivaramakrishnan , Meeko M. K. Oishi , Panagiotis Tsiotras

We present a PTAS for learning random constant-depth networks. We show that for any fixed $\epsilon>0$ and depth $i$, there is a poly-time algorithm that for any distribution on $\sqrt{d} \cdot \mathbb{S}^{d-1}$ learns random Xavier…

Machine Learning · Computer Science 2023-10-26 Amit Daniely , Nathan Srebro , Gal Vardi

We study the training of deep neural networks by gradient descent where floating-point arithmetic is used to compute the gradients. In this framework and under realistic assumptions, we demonstrate that it is highly unlikely to find ReLU…

Machine Learning · Computer Science 2023-11-16 Clemens Karner , Vladimir Kazeev , Philipp Christian Petersen

In this paper we show that neural ODE analogs of recurrent (ODE-RNN) and Long Short-Term Memory (ODE-LSTM) networks can be algorithmically embeddeded into the class of polynomial systems. This embedding preserves input-output behavior and…

Optimization and Control · Mathematics 2023-10-27 Martin Gonzalez , Thibault Defourneau , Hatem Hajri , Mihaly Petreczky

The choice of activation function fundamentally shapes the representational capacity and parameter efficiency of deep neural networks, yet most widely used activations lack rigorous theoretical guarantees on these properties. We provide a…

Machine Learning · Computer Science 2026-05-14 Ibrahim Albool , Malak Gamal El-Din , Salma Elmalaki , Yasser Shoukry