paper-with-me

홈 › Papers

Characterization of the equivalence of robustification and regularization in linear and matrix regression

2014-11-22 · Dimitris Bertsimas, Martin S. Copenhaver

The notion of developing statistical methods in machine learning which are robust to adversarial perturbations in the underlying data has been the subject of increasing interest in recent years. A common feature of this work is that the adversarial robustification often corresponds exactly to regularization methods which appear as a loss function plus a penalty. In this paper we deepen and extend the understanding of the connection between robustification and regularization (as achieved by penalization) in regression problems. Specifically, (a) in the context of linear regression, we characterize precisely under which conditions on the model of uncertainty used and on the loss function penalties robustification and regularization are equivalent, and (b) we extend the characterization of robustification and regularization to matrix regression problems (matrix completion and Principal Component Analysis).

📄 PDF Abstract BibTeX arXiv:1411.6160

Code (0)

등록된 구현이 없습니다.

Tasks

Matrix Completionregression

Similar Papers 제목 키워드 기반

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 minimizatio…

Deep LearningMatrix CompletionOpen-Ended Question Answering

Implicit Regularization in Tensor Factorization

2021-02-19 · Noam Razin, Asaf Maman, Nadav Cohen

Recent efforts to unravel the mystery of implicit regularization in deep learning have led to a theoretical focus on matrix factorization -- matrix completion via linear neural network. As a step further towards practica…

Deep LearningMatrix Completion

Distributional Equivalence in Linear Non-Gaussian Latent-Variable Cyclic Causal Models: Characterization and Learning

2026-03-05 · Haoyue Dai, Immanuel Albrecht, Peter Spirtes, Kun Zhang arxiv

Causal discovery with latent variables is a fundamental task. Yet most existing methods rely on strong structural assumptions, such as enforcing specific indicator patterns for latents or restricting how they can interac…

An Analysis of Dropout for Matrix Factorization

2017-10-10 · Jacopo Cavazza, Connor Lane, Benjamin D. Haeffele, Vittorio Murino 외

Dropout is a simple yet effective algorithm for regularizing neural networks by randomly dropping out units through Bernoulli multiplicative noise, and for some restricted problem classes, such as linear or logistic regr…

The Unintended Consequences of Discount Regularization: Improving Regularization in Certainty Equivalence Reinforcement Learning

2023-06-20 · Sarah Rathnam, Sonali Parbhoo, Weiwei Pan, Susan A. Murphy 외

Discount regularization, using a shorter planning horizon when calculating the optimal policy, is a popular choice to restrict planning to a less complex set of policies when estimating an MDP from sparse or noisy data (…