Research map / Learning theory and algorithms / Sample complexity
$\ell_1$-regression with Heavy-tailed Distributions
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use truncated minimization of the absolute loss instead of classical ERM | ℓ1-regression with heavy-tailed inputs and outputs · Heavy-tailed linear regression | high-probability excess risk: O(√(d/n)) | Helped |
| Use classical ERM when inputs are bounded | ℓ1-regression with heavy-tailed outputs · Bounded-input linear regression | high-probability excess risk: O(D/√n) | Helped |
Closest papers by meaning
- Non-Asymptotic and Non-Lipschitzian Bounds on Optimal Values in Stochastic Optimization Under Heavy Tails (ICML 2025 · similarity 0.84)
- On the Asymptotic Distribution of the Minimum Empirical Risk (ICML 2024 · similarity 0.84)
- Near-Optimal Streaming Heavy-Tailed Statistical Estimation with Clipped SGD (NeurIPS 2024 · similarity 0.83)
- Heavy-Tailed Linear Bandits: Huber Regression with One-Pass Update (ICML 2025 · similarity 0.83)
- Concentration Inequalities for General Functions of Heavy-Tailed Random Variables (ICML 2024 · similarity 0.83)
- On the Efficiency of ERM in Feature Learning (NeurIPS 2024 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.