English
Related papers

Related papers: Average gradient outer product as a mechanism for …

200 papers

Neural collapse (NC) is a simple and symmetric phenomenon for deep neural networks (DNNs) at the terminal phase of training, where the last-layer features collapse to their class means and form a simplex equiangular tight frame aligning…

Machine Learning · Computer Science 2024-05-03 Sicong Wang , Kuo Gai , Shihua Zhang

In this paper, an algorithm for approximate evaluation of back-propagation in DNN training is considered, which we term Approximate Outer Product Gradient Descent with Memory (Mem-AOP-GD). The Mem-AOP-GD algorithm implements an…

Machine Learning · Computer Science 2021-10-19 Eduin E. Hernandez , Stefano Rini , Tolga M. Duman

Our understanding of learning dynamics of deep neural networks (DNNs) remains incomplete. Recent research has begun to uncover the mathematical principles underlying these networks, including the phenomenon of "Neural Collapse", where…

Machine Learning · Computer Science 2024-02-13 Bradley T. Baker , Barak A. Pearlmutter , Robyn Miller , Vince D. Calhoun , Sergey M. Plis

In this work, we investigate a particular implicit bias in gradient descent training, which we term "Feature Averaging," and argue that it is one of the principal factors contributing to the non-robustness of deep neural networks. We show…

Machine Learning · Computer Science 2025-03-04 Binghui Li , Zhixuan Pan , Kaifeng Lyu , Jian Li

Policy gradient (PG) methods in reinforcement learning frequently utilize deep neural networks (DNNs) to learn a shared backbone of feature representations used to compute likelihoods in an action selection layer. Numerous studies have been…

Out-of-distribution (OOD) detection and OOD generalization are widely studied in Deep Neural Networks (DNNs), yet their relationship remains poorly understood. We empirically show that the degree of Neural Collapse (NC) in a network layer…

Machine Learning · Computer Science 2025-09-23 Md Yousuf Harun , Jhair Gallardo , Christopher Kanan

In recent years neural networks have achieved impressive results on many technological and scientific tasks. Yet, the mechanism through which these models automatically select features, or patterns in data, for prediction remains unclear.…

Machine Learning · Computer Science 2023-05-11 Adityanarayanan Radhakrishnan , Daniel Beaglehole , Parthe Pandit , Mikhail Belkin

The recently discovered Neural collapse (NC) phenomenon states that the last-layer weights of Deep Neural Networks (DNN), converge to the so-called Equiangular Tight Frame (ETF) simplex, at the terminal phase of their training. This ETF…

Machine Learning · Computer Science 2024-03-01 Hafiz Tiomoko Ali , Umberto Michieli , Ji Joong Moon , Daehyun Kim , Mete Ozay

Understanding feature learning is an important open question in establishing a mathematical foundation for deep neural networks. The Neural Feature Ansatz (NFA) states that after training, the Gram matrix of the first-layer weights of a…

Machine Learning · Computer Science 2025-10-20 Edward Tansley , Estelle Massart , Coralia Cartis

We propose Deep Neural Coregionalization, a scalable framework for uncertainty-aware multivariate geostatistics. DNC models multivariate spatial effects through spatially varying latent factors and loadings, assigning deep Gaussian process…

Methodology · Statistics 2026-02-23 Yeseul Jeon , Aaron Scheffler , Rajarshi Guhaniyogi

A fundamental problem in machine learning is to understand how neural networks make accurate predictions, while seemingly bypassing the curse of dimensionality. A possible explanation is that common training algorithms for neural networks…

Machine Learning · Statistics 2024-01-10 Adityanarayanan Radhakrishnan , Mikhail Belkin , Dmitriy Drusvyatskiy

Neural Collapse (NC) is a geometric structure recently observed at the terminal phase of training deep neural networks, which states that last-layer feature vectors for the same class would "collapse" to a single point, while features of…

Machine Learning · Computer Science 2024-09-06 Leyan Pan , Xinyuan Cao

Deep neural networks have become the default choice for many of the machine learning tasks such as classification and regression. Dropout, a method commonly used to improve the convergence of deep neural networks, generates an ensemble of…

Machine Learning · Statistics 2019-04-11 Tal Kachman , Michal Moshkovitz , Michal Rosen-Zvi

Modern deep neural networks have achieved impressive performance on tasks from image classification to natural language processing. Surprisingly, these complex systems with massive amounts of parameters exhibit the same structural…

Machine Learning · Computer Science 2023-06-21 Hien Dang , Tho Tran , Stanley Osher , Hung Tran-The , Nhat Ho , Tan Nguyen

Deep classifier neural networks enter the terminal phase of training (TPT) when training error reaches zero and tend to exhibit intriguing Neural Collapse (NC) properties. Neural collapse essentially represents a state at which the…

Machine Learning · Computer Science 2023-04-12 Vignesh Kothapalli

Recently it has been observed that neural networks exhibit Neural Collapse (NC) during the final stage of training for the classification problem. We empirically show that multivariate regression, as employed in imitation learning and other…

Machine Learning · Computer Science 2025-09-30 George Andriopoulos , Zixuan Dong , Li Guo , Zifan Zhao , Keith Ross

Neural collapse (NC) -- the convergence of penultimate-layer features to a simplex equiangular tight frame -- is well understood at equilibrium, but the dynamics governing its onset remain poorly characterised. We identify a simple and…

Machine Learning · Computer Science 2026-04-02 Anamika Paul Rupa

This paper proposes a deep neural network (DNN)-driven framework to address the longstanding generalization challenge in adaptive filtering (AF). In contrast to traditional AF frameworks that emphasize explicit cost function design, the…

Machine Learning · Statistics 2025-08-07 Qizhen Wang , Gang Wang , Ying-Chang Liang

A recent study by De et al. (2022) has reported that large-scale representation learning through pre-training on a public dataset significantly enhances differentially private (DP) learning in downstream tasks, despite the high…

Machine Learning · Computer Science 2024-10-15 Chendi Wang , Yuqing Zhu , Weijie J. Su , Yu-Xiang Wang

Gradient Descent (GD) and its variants are the primary tool for enabling efficient training of recurrent dynamical systems such as Recurrent Neural Networks (RNNs), Neural ODEs and Gated Recurrent units (GRUs). The dynamics that are formed…

Machine Learning · Computer Science 2025-07-10 James Hazelden , Laura Driscoll , Eli Shlizerman , Eric Shea-Brown