English
Related papers

Related papers: Computing the Information Content of Trained Neura…

200 papers

Deep neural networks (DNNs) exhibit an exceptional capacity for generalization in practical applications. This work aims to capture the effect and benefits of depth for supervised learning via information-theoretic generalization bounds. We…

Machine Learning · Computer Science 2025-05-09 Haiyun He , Ziv Goldfeld

We examine a class of deep learning models with a tractable method to compute information-theoretic quantities. Our contributions are three-fold: (i) We show how entropies and mutual informations can be derived from heuristic statistical…

Machine Learning · Computer Science 2020-01-22 Marylou Gabrié , Andre Manoel , Clément Luneau , Jean Barbier , Nicolas Macris , Florent Krzakala , Lenka Zdeborová

This paper presents an empirical study on the weights of neural networks, where we interpret each model as a point in a high-dimensional space -- the neural weight space. To explore the complex structure of this space, we sample from a…

Computer Vision and Pattern Recognition · Computer Science 2020-02-14 Gabriel Eilertsen , Daniel Jönsson , Timo Ropinski , Jonas Unger , Anders Ynnerman

The generalization error of a learning algorithm refers to the discrepancy between the loss of a learning algorithm on training data and that on unseen testing data. Various information-theoretic bounds on the generalization error have been…

Information Theory · Computer Science 2025-06-24 Xuetong Wu , Jonathan H. Manton , Uwe Aickelin , Jingge Zhu

A central question in computational neuroscience is how structure determines function in neural networks. The emerging high-quality large-scale connectomic datasets raise the question of what general functional principles can be gleaned…

Neurons and Cognition · Quantitative Biology 2022-10-25 Weishun Zhong , Ben Sorscher , Daniel D Lee , Haim Sompolinsky

Deep neural networks have been successfully applied to a broad range of problems where overparametrization yields weight matrices which are partially random. A comparison of weight matrix singular vectors to the Porter-Thomas distribution…

Disordered Systems and Neural Networks · Physics 2024-01-22 Max Staats , Matthias Thamm , Bernd Rosenow

We present a unifying picture of PAC-Bayesian and mutual information-based upper bounds on the generalization error of randomized learning algorithms. As we show, Tong Zhang's information exponential inequality (IEI) gives a general recipe…

Machine Learning · Computer Science 2021-10-26 Pradeep Kr. Banerjee , Guido Montúfar

Memorization is worst-case generalization. Based on MacKay's information theoretic model of supervised machine learning, this article discusses how to practically estimate the maximum size of a neural network given a training data set.…

Neural and Evolutionary Computing · Computer Science 2018-10-05 Gerald Friedland , Alfredo Metere , Mario Krell

This article gives a new proof that fully connected neural networks with random weights and biases converge to Gaussian processes in the regime where the input dimension, output dimension, and depth are kept fixed, while the hidden layer…

Probability · Mathematics 2021-07-06 Boris Hanin

This paper follows up on a recent work of Neu et al. (2021) and presents some new information-theoretic upper bounds for the generalization error of machine learning models, such as neural networks, trained with SGD. We apply these bounds…

Machine Learning · Computer Science 2022-03-22 Ziqiao Wang , Yongyi Mao

Knowledge embedded in the weights of the artificial neural network can be used to improve the network structure, such as in network compression. However, the knowledge is set up by hand, which may not be very accurate, and relevant…

Neural and Evolutionary Computing · Computer Science 2021-10-13 Mengqiao Han , Xiabi Liu , Zhaoyang Hai , Xin Duan

Weight normalization (WeightNorm) is widely used in practice for the training of deep neural networks and modern deep learning libraries have built-in implementations of it. In this paper, we provide the first theoretical characterizations…

Machine Learning · Computer Science 2025-01-22 Pedro Cisneros-Velarde , Zhijie Chen , Sanmi Koyejo , Arindam Banerjee

We derive upper bounds on the generalization error of a learning algorithm in terms of the mutual information between its input and output. The bounds provide an information-theoretic understanding of generalization in learning problems,…

Machine Learning · Computer Science 2017-11-07 Aolin Xu , Maxim Raginsky

Despite the increasing prevalence of large language models (LLMs), we still have a limited understanding of how their representational spaces are structured. This limits our ability to interpret how and what they learn or relate them to…

Neural networks are nowadays highly successful despite strong hardness results. The existing hardness results focus on the network architecture, and assume that the network's weights are arbitrary. A natural approach to settle the…

Machine Learning · Computer Science 2020-10-15 Amit Daniely , Gal Vardi

We study the notion of a generalization bound being uniformly tight, meaning that the difference between the bound and the population loss is small for all learning algorithms and all population distributions. Numerous generalization bounds…

Machine Learning · Computer Science 2023-11-29 Michael Gastpar , Ido Nachum , Jonathan Shafer , Thomas Weinberger

Training a neural network is synonymous with learning the values of the weights. By contrast, we demonstrate that randomly weighted neural networks contain subnetworks which achieve impressive performance without ever training the weight…

Computer Vision and Pattern Recognition · Computer Science 2020-04-01 Vivek Ramanujan , Mitchell Wortsman , Aniruddha Kembhavi , Ali Farhadi , Mohammad Rastegari

This paper analyzes the convergence and generalization of training a one-hidden-layer neural network when the input features follow the Gaussian mixture model consisting of a finite number of Gaussian distributions. Assuming the labels are…

Machine Learning · Computer Science 2023-01-30 Hongkang Li , Shuai Zhang , Meng Wang

Intuitively, one would expect accuracy of a trained neural network's prediction on test samples to correlate with how densely the samples are surrounded by seen training samples in representation space. We find that a bound on empirical…

Machine Learning · Computer Science 2022-07-29 Xu Ji , Razvan Pascanu , Devon Hjelm , Balaji Lakshminarayanan , Andrea Vedaldi

We show experimentally that the accuracy of a trained neural network can be predicted surprisingly well by looking only at its weights, without evaluating it on input data. We motivate this task and introduce a formal setting for it. Even…

Machine Learning · Statistics 2021-04-12 Thomas Unterthiner , Daniel Keysers , Sylvain Gelly , Olivier Bousquet , Ilya Tolstikhin