paper-with-me

Papers

Stochastic Rounding Implicitly Regularizes Tall-and-Thin Matrices

2024-03-18 · Gregory Dexter, Christos Boutsikas, Linkai Ma, Ilse C. F. Ipsen, Petros Drineas

Motivated by the popularity of stochastic rounding in the context of machine learning and the training of large-scale deep neural network models, we consider stochastic nearness rounding of real matrices $\mathbf{A}$ with many more rows than columns. We provide novel theoretical evidence, supported by extensive experimental evaluation that, with high probability, the smallest singular value of a stochastically rounded matrix is well bounded away from zero -- regardless of how close $\mathbf{A}$ is to being rank deficient and even if $\mathbf{A}$ is rank-deficient. In other words, stochastic rounding \textit{implicitly regularizes} tall and skinny matrices $\mathbf{A}$ so that the rounded version has full column rank. Our proofs leverage powerful results in random matrix theory, and the idea that stochastic rounding errors do not concentrate in low-dimensional column spaces.

📄 PDF Abstract BibTeX arXiv:2403.12278

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

SGD Implicitly Regularizes Generalization Error

2021-04-10 · Daniel A. Roberts

We derive a simple and model-independent formula for the change in the generalization gap due to a gradient descent update. We then compare the change in the test error for stochastic gradient descent to the change in te…

Stochastic Optimization

Stochastic Rounding Increases Small Singular Values

2026-05-29 · Linkai Ma, Tingzhou Yu, Petros Drineas arxiv

Over the past half-dozen years, stochastic rounding (SR) has regained significant attention as a quantization scheme for low-precision floating-point arithmetic, with applications spanning numerical analysis and modern m…

Implicit regularization in Heavy-ball momentum accelerated stochastic gradient descent

2023-02-02 · Avrajit Ghosh, He Lyu, Xitong Zhang, Rongrong Wang

It is well known that the finite step-size ($h$) in Gradient Descent (GD) implicitly regularizes solutions to flatter minima. A natural question to ask is "Does the momentum parameter $\beta$ play a role in implicit regu…

InRank: Incremental Low-Rank Learning

2023-06-20 · Jiawei Zhao, Yifei Zhang, Beidi Chen, Florian Schäfer 외

The theory of greedy low-rank learning (GLRL) aims to explain the impressive generalization capabilities of deep learning. It proves that stochastic gradient-based training implicitly regularizes neural networks towards …

Computational Efficiency

How Does Sharpness-Aware Minimization Minimize Sharpness?

2022-11-10 · Kaiyue Wen, Tengyu Ma, Zhiyuan Li

Sharpness-Aware Minimization (SAM) is a highly effective regularization technique for improving the generalization of deep neural networks for various settings. However, the underlying working of SAM remains elusive beca…