paper-with-me

Papers

A Kernel Perspective for Regularizing Deep Neural Networks

2018-09-30 · Alberto Bietti, Grégoire Mialon, Dexiong Chen, Julien Mairal

We propose a new point of view for regularizing deep neural networks by using the norm of a reproducing kernel Hilbert space (RKHS). Even though this norm cannot be computed, it admits upper and lower approximations leading to various practical strategies. Specifically, this perspective (i) provides a common umbrella for many existing regularization principles, including spectral norm and gradient penalties, or adversarial training, (ii) leads to new effective regularization penalties, and (iii) suggests hybrid strategies combining lower and upper bounds to get better approximations of the RKHS norm. We experimentally show this approach to be effective when learning on small datasets, or to obtain adversarially robust models.

📄 PDF Abstract BibTeX arXiv:1810.00363

Code (1)

albietz/kernel_reg 공식 구현 pytorch

Similar Papers 제목 키워드 기반

Self-supervised learning with rotation-invariant kernels

2022-07-28 · Léon Zheng, Gilles Puy, Elisa Riccietti, Patrick Pérez 외

We introduce a regularization loss based on kernel mean embeddings with rotation-invariant kernels on the hypersphere (also known as dot-product kernels) for self-supervised learning of image representations. Besides bei…

Self-Supervised Learning

Sound Field Estimation Using Deep Kernel Learning Regularized by the Wave Equation

2024-07-05 · David Sundström, Shoichi Koyama, Andreas Jakobsson

In this work, we introduce a spatio-temporal kernel for Gaussian process (GP) regression-based sound field estimation. Notably, GPs have the attractive property that the sound field is a linear function of the measuremen…

Learning Fair Canonical Polyadical Decompositions using a Kernel Independence Criterion

2021-04-27 · Kevin Kim, Alex Gittens

This work proposes to learn fair low-rank tensor decompositions by regularizing the Canonical Polyadic Decomposition factorization with the kernel Hilbert-Schmidt independence criterion (KHSIC). It is shown, theoreticall…

Fairness

KerJEPA: Kernel Discrepancies for Euclidean Self-Supervised Learning

2025-12-22 · Eric Zimmermann, Harley Wiltzer, Justin Szeto, David Alvarez-Melis 외 arxiv

Recent breakthroughs in self-supervised Joint-Embedding Predictive Architectures (JEPAs) have established that regularizing Euclidean representations toward isotropic Gaussian priors yields provable gains in training sta…

Self-Supervised Learning

Toward a better trade-off between performance and fairness with kernel-based distribution matching

2019-10-25 · Flavien Prost, Hai Qian, Qiuwen Chen, Ed H. Chi 외

As recent literature has demonstrated how classifiers often carry unintended biases toward some subgroups, deploying machine learned models to users demands careful consideration of the social consequences. How should we…

Fairness