AI Paper Atlas

Research map / Learning theory and algorithms / Sample complexity

Improved Analysis of Score-based Generative Modeling: User-Friendly Bounds under Minimal Smoothness Assumptions

Hongrui Chen, Holden Lee, Jianfeng Lu

ICML 2023 · Learning theory and algorithms › Sample complexity · approach: Learning under log-concave distributions · 4 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
Use exponential integrator instead of Euler-Maruyama discretizationSGM sampler (trajectory-smooth setting) · KL(p0||q_T) bounderror bound termsImproved
Exponentially decreasing step size instead of uniform discretization (ablation)SGM with early stopping · discretization term Pi, dependence on 1/deltascaling of discretization errorImproved
Linear step size (quadratic discretization points) instead of exponentially decreasing step size (ablation)SGM with early stopping · discretization term Pi, dependence on 1/deltascaling of discretization errorMixed
Replace uniform Hessian bound with high-probability Hessian bound and change of measureSGM for general distributions with early stopping · steps for TV error vs prior bounded-support resultnumber of stepsImproved
Add truncation step to sampler outputSGM pure Wasserstein guarantee · W2 guarantee depending on tail decayWasserstein distanceImproved
Use reverse KL guarantee instead of TV guarantee for trajectory-smooth settingSGM analysis · trajectory-smoothguarantee strengthImproved

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