English
Related papers

Related papers: Information Theoretic Lower Bounds for Feed-Forwar…

200 papers

We present an efficient coresets-based neural network compression algorithm that sparsifies the parameters of a trained fully-connected neural network in a manner that provably approximates the network's output. Our approach is based on an…

Machine Learning · Computer Science 2019-05-21 Cenk Baykal , Lucas Liebenwein , Igor Gilitschenski , Dan Feldman , Daniela Rus

Current approaches in approximate inference for Bayesian neural networks minimise the Kullback-Leibler divergence to approximate the true posterior over the weights. However, this approximation is without knowledge of the final application,…

Machine Learning · Statistics 2018-05-11 Adam D. Cobb , Stephen J. Roberts , Yarin Gal

We provide guarantees for learning latent variable models emphasizing on the overcomplete regime, where the dimensionality of the latent space can exceed the observed dimensionality. In particular, we consider multiview mixtures, spherical…

Machine Learning · Computer Science 2014-12-18 Animashree Anandkumar , Rong Ge , Majid Janzamin

Masking-based post-hoc explanation methods, such as KernelSHAP and LIME, estimate local feature importance by querying a black-box model under randomized perturbations. This paper formulates this procedure as communication over a query…

Artificial Intelligence · Computer Science 2026-04-21 Erciyes Karakaya , Ozgur Ercetin

In the postgenome era many efforts have been dedicated to systematically elucidate the complex web of interacting genes and proteins. These efforts include experimental and computational methods. Microarray technology offers an opportunity…

Molecular Networks · Quantitative Biology 2009-08-04 L. Diambra

Network weights can be reverse-engineered given enough informative samples of a network's input-output function. In a teacher-student setup, this translates into collecting a dataset of the teacher mapping -- querying the teacher -- and…

Artificial Intelligence · Computer Science 2025-11-26 Alexander Beiser , Flavio Martinelli , Wulfram Gerstner , Johanni Brea

Multi-layer feedforward networks have been used to approximate a wide range of nonlinear functions. An important and fundamental problem is to understand the learnability of a network model through its statistical risk, or the expected…

Machine Learning · Computer Science 2022-06-28 Gen Li , Jie Ding

We study information-theoretic phase transitions for the detectability of latent geometry in bipartite random geometric graphs RGGs with Gaussian d-dimensional latent vectors while only a subset of edges carries latent information…

Probability · Mathematics 2026-04-13 Andreas Göbel , Marcus Pappik , Leon Schiller

This paper studies the problem of recovering the hidden vertex correspondence between two correlated random graphs. We propose the partially correlated Erd\H{o}s-R\'enyi graphs model, wherein a pair of induced subgraphs with a certain…

Information Theory · Computer Science 2025-10-08 Dong Huang , Xianwen Song , Pengkun Yang

We describe a simple and general neural network weight compression approach, in which the network parameters (weights and biases) are represented in a "latent" space, amounting to a reparameterization. This space is equipped with a learned…

Machine Learning · Computer Science 2020-02-18 Deniz Oktay , Johannes Ballé , Saurabh Singh , Abhinav Shrivastava

In this paper, we consider the "foreach" sparse recovery problem with failure probability $p$. The goal of which is to design a distribution over $m \times N$ matrices $\Phi$ and a decoding algorithm $\algo$ such that for every…

Data Structures and Algorithms · Computer Science 2013-04-24 Anna C. Gilbert , Hung Q. Ngo , Ely Porat , Atri Rudra , Martin J. Strauss

We introduce a probability distribution, combined with an efficient sampling algorithm, for weights and biases of fully-connected neural networks. In a supervised learning context, no iterative optimization or gradient computations of…

Machine Learning · Computer Science 2023-11-14 Erik Lien Bolager , Iryna Burak , Chinmay Datar , Qing Sun , Felix Dietrich

The fundamental caching problem in networks asks to find an allocation of contents to a network of caches with the aim of maximizing the cache hit rate. Despite the problem's importance to a variety of research areas -- including not only…

Networking and Internet Architecture · Computer Science 2024-12-24 Robert Ganian , Fionn Mc Inerney , Dimitra Tsigkari

Deep neural networks generalize well despite being heavily overparameterized, in apparent contradiction with classical learning theory based on uniform convergence over fixed hypothesis spaces. Uniform bounds over the entire parameter space…

Machine Learning · Statistics 2026-05-15 Hubert Leroux , Jean Marcus , Julien Roger

Dependency networks (Heckerman et al., 2000) provide a flexible framework for modeling complex systems with many variables by combining independently learned local conditional distributions through pseudo-Gibbs sampling. Despite their…

Machine Learning · Computer Science 2026-04-02 Kazuya Takabatake , Shotaro Akaho

Supervised learning problems with side information in the form of a network arise frequently in applications in genomics, proteomics and neuroscience. For example, in genetic applications, the network side information can accurately capture…

Statistics Theory · Mathematics 2024-10-24 Sagnik Nandy , Subhabrata Sen

In this work, we consider the problem of recovering analysis-sparse signals from under-sampled measurements when some prior information about the support is available. We incorporate such information in the recovery stage by suitably tuning…

Information Theory · Computer Science 2019-01-30 Sajad Daei , Farzan Haddadi , Arash Amini

Deep Neural Networks (DNNs) are analyzed via the theoretical framework of the information bottleneck (IB) principle. We first show that any DNN can be quantified by the mutual information between the layers and the input and output…

Machine Learning · Computer Science 2015-03-10 Naftali Tishby , Noga Zaslavsky

In this paper, we study the data-dependent convergence and generalization behavior of gradient methods for neural networks with smooth activation. Our first result is a novel bound on the excess risk of deep networks trained by the logistic…

Machine Learning · Computer Science 2024-12-09 Hossein Taheri , Christos Thrampoulidis , Arya Mazumdar

We consider the problem of finding a two-layer neural network with sigmoid, rectified linear unit (ReLU), or binary step activation functions that "fits" a training data set as accurately as possible as quantified by the training error; and…

Machine Learning · Statistics 2022-04-06 David Gamarnik , Eren C. Kızıldağ , Ilias Zadik