English
Related papers

Related papers: Can Stability be Detrimental? Better Generalizatio…

200 papers

Recent work has highlighted a surprising alignment between gradients and the top eigenspace of the Hessian -- termed the Dominant subspace -- during neural network training. Concurrently, there has been growing interest in the distinct…

Machine Learning · Computer Science 2025-05-20 Daniyar Zakarin , Sidak Pal Singh

A leading hypothesis for the surprising generalization of neural networks is that the dynamics of gradient descent bias the model towards simple solutions, by searching through the solution space in an incremental order of complexity. We…

Machine Learning · Computer Science 2020-01-01 Daniel Gissin , Shai Shalev-Shwartz , Amit Daniely

The Hessian of a neural network captures parameter interactions through second-order derivatives of the loss. It is a fundamental object of study, closely tied to various problems in deep learning, including model design, optimization, and…

Machine Learning · Computer Science 2021-07-02 Sidak Pal Singh , Gregor Bachmann , Thomas Hofmann

The success of deep neural networks hinges on our ability to accurately and efficiently optimize high-dimensional, non-convex functions. In this paper, we empirically investigate the loss functions of state-of-the-art networks, and how…

Machine Learning · Computer Science 2017-12-11 Daniel Jiwoong Im , Michael Tao , Kristin Branson

Stochastic gradient descent is one of the most successful approaches for solving large-scale problems, especially in machine learning and statistics. At each iteration, it employs an unbiased estimator of the full gradient computed from one…

Numerical Analysis · Mathematics 2018-12-05 Bangti Jin , Xiliang Lu

A recent line of research has shown that gradient-based algorithms with random initialization can converge to the global minima of the training loss for over-parameterized (i.e., sufficiently wide) deep neural networks. However, the…

Machine Learning · Computer Science 2019-06-12 Difan Zou , Quanquan Gu

Neural networks (NNs) are central to modern machine learning and achieve state-of-the-art results in many applications. However, the relationship between loss geometry and generalization is still not well understood. The local geometry of…

Machine Learning · Computer Science 2026-04-15 Yuto Omae , Kazuki Sakai , Yohei Kakimoto , Makoto Sasaki , Yusuke Sakai , Hirotaka Takahashi

We theoretically characterize gradient descent dynamics in deep linear networks trained at large width from random initialization and on large quantities of random data. Our theory captures the ``wider is better" effect of…

Machine Learning · Computer Science 2025-06-17 Blake Bordelon , Cengiz Pehlevan

We identify and formalize a fundamental gradient descent phenomenon resulting in a learning proclivity in over-parameterized neural networks. Gradient Starvation arises when cross-entropy loss is minimized by capturing only a subset of…

Machine Learning · Computer Science 2021-11-25 Mohammad Pezeshki , Sékou-Oumar Kaba , Yoshua Bengio , Aaron Courville , Doina Precup , Guillaume Lajoie

We study the convergence of gradient flow for the training of deep neural networks. If Residual Neural Networks are a popular example of very deep architectures, their training constitutes a challenging optimization problem due notably to…

Machine Learning · Computer Science 2025-07-22 Raphaël Barboni , Gabriel Peyré , François-Xavier Vialard

Normalization layers (e.g., Batch Normalization, Layer Normalization) were introduced to help with optimization difficulties in very deep nets, but they clearly also help generalization, even in not-so-deep nets. Motivated by the long-held…

Machine Learning · Computer Science 2023-01-18 Kaifeng Lyu , Zhiyuan Li , Sanjeev Arora

Numerous theories of learning propose to prevent the gradient from exponential growth with depth or time, to stabilize and improve training. Typically, these analyses are conducted on feed-forward fully-connected neural networks or simple…

Machine Learning · Computer Science 2024-01-08 Luca Herranz-Celotti , Jean Rouat

Existing analyses of optimization in deep learning are either continuous, focusing on (variants of) gradient flow, or discrete, directly treating (variants of) gradient descent. Gradient flow is amenable to theoretical analysis, but is…

Machine Learning · Computer Science 2021-12-30 Omer Elkabetz , Nadav Cohen

The multiplicative structure of parameters and input data in the first layer of neural networks is explored to build connection between the landscape of the loss function with respect to parameters and the landscape of the model function…

Machine Learning · Computer Science 2021-11-30 Chao Ma , Lexing Ying

A probability model exhibits instability if small changes in a data outcome result in large, and often unanticipated, changes in probability. This instability is a property of the probability model, given by a distributional form and a…

Statistics Theory · Mathematics 2019-11-18 Andee Kaplan , Daniel Nordman , Stephen Vardeman

Inspired by convolutional neural networks on 1D and 2D data, graph convolutional neural networks (GCNNs) have been developed for various learning tasks on graph data, and have shown superior performance on real-world datasets. Despite their…

Machine Learning · Computer Science 2019-05-15 Saurabh Verma , Zhi-Li Zhang

Over the past few years, an extensively studied phenomenon in training deep networks is the implicit bias of gradient descent towards parsimonious solutions. In this work, we investigate this phenomenon by narrowing our focus to deep linear…

Machine Learning · Computer Science 2023-06-05 Can Yaras , Peng Wang , Wei Hu , Zhihui Zhu , Laura Balzano , Qing Qu

Meta-learning that uses implicit gradient have provided an exciting alternative to standard techniques which depend on the trajectory of the inner loop training. Implicit meta-learning (IML), however, require computing $2^{nd}$ order…

Machine Learning · Computer Science 2023-10-31 Fady Rezk

Gradient descent can be surprisingly good at optimizing deep neural networks without overfitting and without explicit regularization. We find that the discrete steps of gradient descent implicitly regularize models by penalizing gradient…

Machine Learning · Computer Science 2022-07-20 David G. T. Barrett , Benoit Dherin

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