paper-with-me

Papers

On implicit regularization: Morse functions and applications to matrix factorization

2020-01-13 · Mohamed Ali Belabbas

In this paper, we revisit implicit regularization from the ground up using notions from dynamical systems and invariant subspaces of Morse functions. The key contributions are a new criterion for implicit regularization---a leading contender to explain the generalization power of deep models such as neural networks---and a general blueprint to study it. We apply these techniques to settle a conjecture on implicit regularization in matrix factorization.

📄 PDF Abstract BibTeX arXiv:2001.04264

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

How regularization affects the geometry of loss functions

2023-07-28 · Nathaniel Bottman, Y. Cooper, Antonio Lerario

What neural networks learn depends fundamentally on the geometry of the underlying loss function. We study how different regularizers affect the geometry of this function. One of the most basic geometric properties of a …

Morse sequences

2024-02-12 · Gilles Bertrand

We introduce the notion of a Morse sequence, which provides a simple and effective approach to discrete Morse theory. A Morse sequence is a sequence composed solely of two elementary operations, that is, expansions (the …

Statistical Inference using the Morse-Smale Complex

2015-06-29 · Yen-Chi Chen, Christopher R. Genovese, Larry Wasserman

The Morse-Smale complex of a function $f$ decomposes the sample space into cells where $f$ is increasing or decreasing. When applied to nonparametric density estimation and regression, it provides a way to represent, vis…

ClusteringDensity Estimationregression

Learning Stochastic Dynamical Systems as an Implicit Regularization with Graph Neural Networks

2023-07-12 · Jin Guo, Ting Gao, Yufu Lan, Peng Zhang 외

Stochastic Gumbel graph networks are proposed to learn high-dimensional time series, where the observed dimensions are often spatially correlated. To that end, the observed randomness and spatial-correlations are capture…

Time Series

Implicit Regularization in Deep Matrix Factorization

2019-05-31 · NeurIPS 2019 12 · Sanjeev Arora, Nadav Cohen, Wei Hu, Yuping Luo

Efforts to understand the generalization mystery in deep learning have led to the belief that gradient-based optimization induces a form of implicit regularization, a bias towards models of low "complexity." We study the…

Matrix Completion