Research map / Learning theory and algorithms / Sample complexity
Distribution Estimation under the Infinity Norm
Aryeh Kontorovich, Amichai Painsky
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 the proposed data-dependent bound instead of the benchmark bound | MLE infinity-norm confidence bound · 2000 US Census top-1000 surnames (n=10000, delta=0.05) | bound on infinity norm error: 0.0345 -> 0.0108 | Improved |
| use proposed Theorem bound instead of the other proposed bound at fixed delta | Zipf and uniform, A=100 · Zipf s=1.1 (A=100, delta=0.05) | bound tightness | Improved |
| use the decaying-confidence bound with delta=1/n^2 for large n | Zipf and uniform, A=100 · Zipf s=1.1 (A=100, delta=1/n^2) | bound tightness | Improved |
| use infinity norm as proxy for the k most frequent symbols | census and Hamilton word data · 2000 US Census top-1000 surnames (n=10000, delta=0.05) | CI agreement with oracle | Improved |
Closest papers by meaning
- Improved Distribution Estimation in $\ell_\infty$ (ICML 2026 · similarity 0.90)
- Learning discrete distributions with infinite support (NeurIPS 2020 · similarity 0.89)
- Instance-Optimality for Private KL Distribution Estimation (NeurIPS 2025 · similarity 0.86)
- PAC-Bayes-Chernoff bounds for unbounded losses (NeurIPS 2024 · similarity 0.85)
- Intrinsic-dimension empirical Bernstein inequalities for bounded self-adjoint operators (NeurIPS 2026 · similarity 0.85)
- A Unified View on Learning Unnormalized Distributions via Noise-Contrastive Estimation (ICML 2025 · similarity 0.85)
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.
