paper-with-me

Papers

Implicit Regularization in Deep Learning May Not Be Explainable by Norms

2020-05-13 · NeurIPS 2020 12 · Noam Razin, Nadav Cohen

Mathematically characterizing the implicit regularization induced by gradient-based optimization is a longstanding pursuit in the theory of deep learning. A widespread hope is that a characterization based on minimization of norms may apply, and a standard test-bed for studying this prospect is matrix factorization (matrix completion via linear neural networks). It is an open question whether norms can explain the implicit regularization in matrix factorization. The current paper resolves this open question in the negative, by proving that there exist natural matrix factorization problems on which the implicit regularization drives all norms (and quasi-norms) towards infinity. Our results suggest that, rather than perceiving the implicit regularization via norms, a potentially more useful interpretation is minimization of rank. We demonstrate empirically that this interpretation extends to a certain class of non-linear neural networks, and hypothesize that it may be key to explaining generalization in deep learning.

📄 PDF Abstract BibTeX arXiv:2005.06398

Code (1)

noamrazin/imp_reg_dl_not_norms 공식 구현 pytorch

Tasks

Deep LearningMatrix CompletionOpen-Ended Question Answering

Similar Papers 제목 키워드 기반

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

Unpacking the Implicit Norm Dynamics of Sharpness-Aware Minimization in Tensorized Models

2025-08-14 · Tianxiao Cao, Kyohei Atarashi, Hisashi Kashima arxiv

Sharpness-Aware Minimization (SAM) has been proven to be an effective optimization technique for improving generalization in overparameterized models. While prior works have explored the implicit regularization of SAM in…

parameter-efficient fine-tuningModel Compression

Implicit Regularization Leads to Benign Overfitting for Sparse Linear Regression

2023-02-01 · Mo Zhou, Rong Ge

In deep learning, often the training process finds an interpolator (a solution with 0 training loss), but the test loss is still low. This phenomenon, known as benign overfitting, is a major mystery that received a lot o…

regression

Implicit Regularization Paths of Weighted Neural Representations

2024-08-28 · Jin-Hong Du, Pratik Patil

We study the implicit regularization effects induced by (observation) weighting of pretrained features. For weight and feature matrices of bounded operator norms that are infinitesimally free with respect to (normalized)…

On the Geometry of Regularization in Adversarial Training: High-Dimensional Asymptotics and Generalization Bounds

2024-10-21 · Matteo Vilucchio, Nikolaos Tsilivis, Bruno Loureiro, Julia Kempe

Regularization, whether explicit in terms of a penalty in the loss or implicit in the choice of algorithm, is a cornerstone of modern machine learning. Indeed, controlling the complexity of the model class is particularl…

Binary ClassificationGeneralization Bounds