Pith. sign in

REVIEW 5 cited by

A short note on an inequality between KL and TV

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2202.07198 v2 pith:N6SQYSHA submitted 2022-02-15 math.PR math.STstat.TH

Clément L. Canonne This is my paper · ORCID
classification math.PRmath.STstat.TH
keywords inequalitydiscussnoteshortapparentlyapplicationsarguablybefore
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

The goal of this short note is to discuss the relation between Kullback--Leibler divergence and total variation distance, starting with the celebrated Pinsker's inequality relating the two, before switching to a simple, yet (arguably) more useful inequality, apparently not as well known, due to Bretagnolle and Huber. We also discuss applications of this bound for minimax testing lower bounds.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. The Sample Complexity of Lossless Data Compression

    cs.IT 2026-01 unverdicted novelty 8.0 of 10

    Sample complexity of lossless compression for memoryless sources is governed by Rényi entropy of order 1/2, with explicit non-asymptotic bounds and extensions to Markov and universal cases.

  2. Total Variation Distance Estimation in Autoregressive Models

    cs.LG 2026-07 accept novelty 7.0 of 10

    New query-optimal algorithms estimate the total variation distance between two autoregressive text distributions under sample, logit, and noisy-logit access.

  3. Stochastic Caching via Subset Entropy

    cs.DS 2026-07 accept novelty 7.0 of 10

    k-subset entropy H of an i.i.d. request distribution yields O(H) competitive ratio for Top-k and LFU and O(H^3) for LRU on stochastic caching.

  4. Best-of-N through the Smoothing Lens: KL Divergence and Regret Analysis

    stat.ML 2025-07 conditional novelty 6.0 of 10

    Smoothed Best-of-N has finite-sample KL and regret bounds under imperfect reward models, and tuning its temperature can make its regret bound beat hard Best-of-N in the overoptimization regime.

  5. On a structure preserving closure of Langevin dynamics

    cond-mat.stat-mech 2025-06 conditional novelty 6.0 of 10

    A closure method that turns overdamped Langevin dynamics into gradient-flow macroscopic models for arbitrary approximate densities, automatically satisfying the second law.

Pith tools