paper-with-me

Papers

Risk Bounds for Robust Deep Learning

2020-09-14 · Johannes Lederer

It has been observed that certain loss functions can render deep-learning pipelines robust against flaws in the data. In this paper, we support these empirical findings with statistical theory. We especially show that empirical-risk minimization with unbounded, Lipschitz-continuous loss functions, such as the least-absolute deviation loss, Huber loss, Cauchy loss, and Tukey's biweight loss, can provide efficient prediction under minimal assumptions on the data. More generally speaking, our paper provides theoretical evidence for the benefits of robust loss functions in deep learning.

📄 PDF Abstract BibTeX arXiv:2009.06202

Code (0)

등록된 구현이 없습니다.

Tasks

Deep Learning

Methods 이 논문이 사용한 방법론

Huber loss The Huber loss function describes the penalty incurred by an estimation procedure f. Huber (1964) defines the loss function piecewise by[1] L δ ( a ) = { 1 2 a 2 for | a |…

Similar Papers 제목 키워드 기반

Adversarial Risk Bounds via Function Transformation

2018-10-22 · Justin Khim, Po-Ling Loh

We derive bounds for a notion of adversarial risk, designed to characterize the robustness of linear and neural network classifiers to adversarial perturbations. Specifically, we introduce a new class of function transfo…

General Classification

Regret Bounds for Risk-sensitive Reinforcement Learning with Lipschitz Dynamic Risk Measures

2023-06-04 · Hao Liang, Zhi-Quan Luo

We study finite episodic Markov decision processes incorporating dynamic risk measures to capture risk sensitivity. To this end, we present two model-based algorithms applied to \emph{Lipschitz} dynamic risk measures, a …

reinforcement-learningSensitivity

A Wasserstein distance approach for concentration of empirical risk estimates

2019-02-27 · NeurIPS 2019 12 · Prashanth L. A., Sanjay P. Bhat

This paper presents a unified approach based on Wasserstein distance to derive concentration bounds for empirical estimates for two broad classes of risk measures defined in the paper. The classes of risk measures introd…

The Intrinsic Bounds on the Risk Premium of Markovian Pricing Kernels

2015-09-28

The risk premium is one of main concepts in mathematical finance. It is a measure of the trade-offs investors make between return and risk and is defined by the excess return relative to the risk-free interest rate that …

Bounds for randomly shared risk of heavy-tailed loss factors

2016-04-11

For a risk vector $V$, whose components are shared among agents by some random mechanism, we obtain asymptotic lower and upper bounds for the individual agents' exposure risk and the aggregated risk in the market. Risk i…