paper-with-me

Papers

Exact Spectral Norm Regularization for Neural Networks

2022-06-27 · Anton Johansson, Claes Strannegård, Niklas Engsner, Petter Mostad

We pursue a line of research that seeks to regularize the spectral norm of the Jacobian of the input-output mapping for deep neural networks. While previous work rely on upper bounding techniques, we provide a scheme that targets the exact spectral norm. We showcase that our algorithm achieves an improved generalization performance compared to previous spectral regularization techniques while simultaneously maintaining a strong safeguard against natural and adversarial noise. Moreover, we further explore some previous reasoning concerning the strong adversarial protection that Jacobian regularization provides and show that it can be misleading.

📄 PDF Abstract BibTeX arXiv:2206.13581

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Spectrally-truncated kernel ridge regression and its free lunch

2019-06-14 · Arash A. Amini

Kernel ridge regression (KRR) is a well-known and popular nonparametric regression approach with many desirable properties, including minimax rate-optimality in estimating functions that belong to common reproducing kern…

regression

Spectral Norm Regularization for Improving the Generalizability of Deep Learning

2017-05-31 · Yuichi Yoshida, Takeru Miyato

We investigate the generalizability of deep learning based on the sensitivity to input perturbation. We hypothesize that the high sensitivity to the perturbation of data degrades the performance on it. To reduce the sens…

Deep LearningSensitivity

Spectral k-Support Norm Regularization

2014-12-01 · NeurIPS 2014 12 · Andrew M. McDonald, Massimiliano Pontil, Dimitris Stamos

The $k$-support norm has successfully been applied to sparse vector prediction problems. We observe that it belongs to a wider class of norms, which we call the box-norms. Within this framework we derive an efficient alg…

Matrix Completion

Adversarial Training Generalizes Data-dependent Spectral Norm Regularization

2019-09-25 · Kevin Roth, Yannic Kilcher, Thomas Hofmann

We establish a theoretical link between adversarial training and operator norm regularization for deep neural networks. Specifically, we present a data-dependent variant of spectral norm regularization and prove that it …

Sensitivity

Partial Recovery for Top-$k$ Ranking: Optimality of MLE and Sub-Optimality of Spectral Method

2020-06-30 · Pinhan Chen, Chao GAO, Anderson Y. Zhang

Given partially observed pairwise comparison data generated by the Bradley-Terry-Luce (BTL) model, we study the problem of top-$k$ ranking. That is, to optimally identify the set of top-$k$ players. We derive the minimax…