arXiv · 2610.12851
Universal Bounds for Self-Normalized Kullback-Leibler Estimation
Abstract
This work studies an entropy-based estimator of Kullback-Leibler (KL) divergence constructed from normalized importance weights. We prove a universal finite-sample bound showing that its expectation can exceed the target-proposal KL divergence by at most $\log 2$ for any sample size. We then characterize the KL divergence between the distribution induced by importance-weighted resampling and the proposal, showing that it is upper bounded by both the expectation of the entropy-based estimator and the target-proposal KL divergence. Importantly, these bounds require neither bounded importance weights nor finite higher moments. We apply these results to test-time alignment of generative models via Soft Best-of-$N$ sampling, an importance-sampling-based scaling technique proposed by Verdun et al. (2025), and to relative entropy coding, obtaining finite-sample policy-divergence certificates and moment-free bounds on coding cost.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Buu Phan, Lester Mackey, David Alvarez-Melis. 2026-10-09. Universal Bounds for Self-Normalized Kullback-Leibler Estimation. https://searcharxiv.com/abs/2610.12851
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Searcharxiv by Indiciae: BibTeX · RIS.