Exploring Local Norms in Exp-concave Statistical Learning
Not on the map. Why?
Abstract (arXiv)
We consider the problem of stochastic convex optimization with exp-concave losses using Empirical Risk Minimization in a convex class. Answering a question raised in several prior works, we provide a O( d / n + log( 1 / δ) / n ) excess risk bound valid for a wide class of bounded exp-concave losses, where d is the dimension of the convex reference set, n is the sample size, and δ is the confidence level. Our result is based on a unified geometric assumption on the gradient of losses and the notion of local norms.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 20 of its 51 references that are in the map. First posted on arXiv 21 Feb 2023.
Builds on
20 of 51 references.
References · 20
- 2013Non-strongly-convex smooth stochastic approximation with convergence rate O(1/n)cited by 110
- 2019Sharper bounds for uniformly stable algorithmscited by 91
- 2021Stability and Deviation Optimal Risk Bounds with Convergence Rate O(1/n)cited by 42
- 2018Logistic Regression: The Importance of Being Impropercited by 40
- 2015Learning with Square Loss: Localization through Offset Rademacher Complexitycited by 37
- 2014Logistic Regression: Tight Bounds for Stochastic and Online Optimizationcited by 30
- 2019An improper estimator with optimal excess risk in misspecified density estimation and logistic regressioncited by 24
- 2013Empirical entropy, minimax regret and minimax riskcited by 21
- 2021Distribution-Free Robust Linear Regressioncited by 19
- 2014The Sample Complexity of Learning Linear Predictors with the Squared Losscited by 16
- 2019Stochastic Approximation of Smooth and Strongly Convex Functions: Beyond the O(1/T) Convergence Ratecited by 14
- 2015Sequential Probability Assignment with Binary Alphabets and Large Classes of Expertscited by 11
8 more
- 2021An Even More Optimal Stochastic Optimization Algorithm: Minibatching and Interpolation Learningcited by 10
- 2020Suboptimality of Constrained Least Squares and Improvements via Non-Linear Predictorscited by 9
- 2022Exponential Tail Local Rademacher Complexity Risk Bounds Without the Bernstein Conditioncited by 9
- 2018Efficient online algorithms for fast-rate regret bounds under sparsitycited by 8
- 2021Localization, Convexity, and Star Aggregationcited by 7
- 2022A Regret-Variance Trade-Off in Online Learningcited by 7
- 2016Average Stability is Invariant to Data Preconditioning. Implications to Exp-concave Empirical Risk Minimizationcited by 6
- 2017A Simple Analysis for Exp-concave Empirical Minimization with Arbitrary Convex Regularizercited by 4
Built on by
Citing papers per year: 2023: 1; 2024: 0; 2025: 1.
2 papers.