AI Paper Atlas

Research map / Learning theory and algorithms / Sample complexity

Optimal Robust Learning of Discrete Distributions from Batches

Ayush Jain, Alon Orlitsky

ICML 2020 · Learning theory and algorithms › Sample complexity · approach: Distributed estimation under communication limits · 2 citations (OpenAlex)

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 changedWhereMeasuredEffect
Increase alphabet size while holding n=1000 and β=0.4, with m=k/(0.4)^2Robust Distribution Estimator · Synthetic data, varying alphabet size kL1 lossNo clear effect
Increase batch size while keeping total sample count constantRobust Distribution Estimator · Synthetic data, varying batch size nL1 lossImproved
Increase adversarial fraction βRobust Distribution Estimator · Synthetic data, varying adversarial noise levelL1 lossHurt
Increase the number of batchesRobust Distribution Estimator · Synthetic data, varying number of batchesL1 lossMixed
Use the naive empirical estimator over all batches instead of robust batch filteringSynthetic distribution learning · Synthetic data, varying alphabet size kL1 lossHurt
Use adversarial batches drawn from a distribution far from the targetRobust Distribution Estimator · Synthetic data, adversarial distribution distanceL1 lossImproved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy