English
Related papers

Related papers: Critical feature learning in deep neural networks

200 papers

Kernel methods are ubiquitous tools in machine learning. However, there is often little reason for the common practice of selecting a kernel a priori. Even if a universal approximating kernel is selected, the quality of the finite sample…

Machine Learning · Statistics 2018-01-31 Junier Oliva , Avinava Dubey , Andrew G. Wilson , Barnabas Poczos , Jeff Schneider , Eric P. Xing

There has recently been much work on the "wide limit" of neural networks, where Bayesian neural networks (BNNs) are shown to converge to a Gaussian process (GP) as all hidden layers are sent to infinite width. However, these results do not…

Machine Learning · Statistics 2020-07-07 Devanshu Agrawal , Theodore Papamarkou , Jacob Hinkle

We present a new method to approximate posterior probabilities of Bayesian Network using Deep Neural Network. Experiment results on several public Bayesian Network datasets shows that Deep Neural Network is capable of learning joint…

Machine Learning · Computer Science 2018-01-12 Jie Jia , Honggang Zhou , Yunchun Li

In this article a novel approach for training deep neural networks using Bayesian techniques is presented. The Bayesian methodology allows for an easy evaluation of model uncertainty and additionally is robust to overfitting. These are…

Machine Learning · Computer Science 2019-04-03 Konstantin Posch , Jürgen Pilz

Deep Gaussian process models typically employ discrete hierarchies, but recent advancements in differential Gaussian processes (DiffGPs) have extended these models to infinite depths. However, existing DiffGP approaches often overlook the…

Machine Learning · Computer Science 2025-12-16 Jian Xu , Zhiqi Lin , Min Chen , Junmei Yang , Delu Zeng , John Paisley

In this short note, we reify the connection between work on the storage capacity problem in wide two-layer treelike neural networks and the rapidly-growing body of literature on kernel limits of wide neural networks. Concretely, we observe…

Disordered Systems and Neural Networks · Physics 2022-05-02 Jacob A. Zavatone-Veth , Cengiz Pehlevan

Recent progress in variational inference has paid much attention to the flexibility of variational posteriors. One promising direction is to use implicit distributions, i.e., distributions without tractable densities as the variational…

Machine Learning · Statistics 2018-02-26 Jiaxin Shi , Shengyang Sun , Jun Zhu

Neural networks (NN) have achieved state-of-the-art performance in various applications. Unfortunately in applications where training data is insufficient, they are often prone to overfitting. One effective way to alleviate this problem is…

Machine Learning · Computer Science 2016-11-03 Hao Wang , Xingjian Shi , Dit-Yan Yeung

Deep neural networks (DNNs) at convergence consistently represent the training data in the last layer via a highly symmetric geometric structure referred to as neural collapse. This empirical evidence has spurred a line of theoretical…

Machine Learning · Computer Science 2024-10-08 Arthur Jacot , Peter Súkeník , Zihan Wang , Marco Mondelli

Neural networks posses the crucial ability to generate meaningful representations of task-dependent features. Indeed, with appropriate scaling, supervised learning in neural networks can result in strong, task-dependent feature learning.…

Machine Learning · Computer Science 2025-05-13 Alexander van Meegen , Haim Sompolinsky

Feature learning (FL), where neural networks adapt their internal representations during training, remains poorly understood. Using methods from statistical physics, we derive a tractable, self-consistent mean-field (MF) theory for the…

Machine Learning · Computer Science 2025-10-20 Niclas Göring , Chris Mingard , Yoonsoo Nam , Ard Louis

Graph convolutional networks are a popular class of deep neural network algorithms which have shown success in a number of relational learning tasks. Despite their success, graph convolutional networks exhibit a number of peculiar features,…

Machine Learning · Computer Science 2022-08-22 Thomas Gebhart

When fine-tuning Deep Neural Networks (DNNs) to new data, DNNs are prone to overwriting network parameters required for task-specific functionality on previously learned tasks, resulting in a loss of performance on those tasks. We propose…

Machine Learning · Computer Science 2025-01-22 Christopher Angelini , Nidhal Bouaynaya

The dynamics of gradient-based training in neural networks often exhibit nontrivial structures; hence, understanding them remains a central challenge in theoretical machine learning. In particular, a concept of feature unlearning, in which…

Machine Learning · Computer Science 2026-02-10 Shota Imai , Sota Nishiyama , Masaaki Imaizumi

Generalization performance of classifiers in deep learning has recently become a subject of intense study. Deep models, typically over-parametrized, tend to fit the training data exactly. Despite this "overfitting", they perform well on…

Machine Learning · Statistics 2018-06-18 Mikhail Belkin , Siyuan Ma , Soumik Mandal

In this work, we aim to establish a Bayesian adaptive learning framework by focusing on estimating latent variables in deep neural network (DNN) models. Latent variables indeed encode both transferable distributional information and…

Audio and Speech Processing · Electrical Eng. & Systems 2024-01-26 Hu Hu , Sabato Marco Siniscalchi , Chin-Hui Lee

The advances in variational inference are providing promising paths in Bayesian estimation problems. These advances make variational phylogenetic inference an alternative approach to Markov Chain Monte Carlo methods for approximating the…

Populations and Evolution · Quantitative Biology 2023-09-12 Amine M. Remita , Golrokh Vitae , Abdoulaye Baniré Diallo

Neural networks in the lazy training regime converge to kernel machines. Can neural networks in the rich feature learning regime learn a kernel machine with a data-dependent kernel? We demonstrate that this can indeed happen due to a…

Machine Learning · Statistics 2022-02-07 Alexander Atanasov , Blake Bordelon , Cengiz Pehlevan

We undertake Bayesian learning of the high-dimensional functional relationship between a system parameter vector and an observable, that is in general tensor-valued. The ultimate aim is Bayesian inverse prediction of the system parameters,…

Methodology · Statistics 2018-04-17 Kangrui Wang , Dalia Chakrabarty

From the classical and influential works of Neal (1996), it is known that the infinite width scaling limit of a Bayesian neural network with one hidden layer is a Gaussian process, when the network weights have bounded prior variance.…

Machine Learning · Statistics 2024-06-06 Jorge Loría , Anindya Bhadra