AI Paper Atlas

Research map / Learning theory and algorithms / Sample complexity

Quantum Algorithms for Sampling Log-Concave Distributions and Estimating Normalizing Constants

Andrew Childs, Tongyang Li, Jin-Peng Liu, Chunhao Wang, Ruizhe Zhang

NeurIPS 2022 · Learning theory and algorithms › Sample complexity · approach: Learning under log-concave distributions · 1 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
Replace gradient-oracle queries with quantum evaluation-oracle queries in ULD-RMMULD-RMM · Log-concave sampling (W2)query complexity: classical: \widetilde O\mathopen{}\mathclose\bgroup\originalleft(\kappa^{7/6}d^{1/6}\epsilon^{-1/3}+\kappa d^{1/3}\epsilImproved
Use quantum MALA instead of classical MALAMALA · Log-concave sampling (TV)query complexity: \widetilde O\mathopen{}\mathclose\bgroup\originalleft(\kappa d\aftergroup\egroup\originalright) -> \widetilde O\mathopenImproved
Use quantum MALA with a warm-start distributionMALA · Log-concave sampling (TV, warm start)query complexity: \widetilde O\mathopen{}\mathclose\bgroup\originalleft(\kappa d^{1/2}\aftergroup\egroup\originalright) -> \widetilde O\maImproved
Apply quantum mean estimation in multilevel ULD-RMM annealingMultilevel ULD-RMM · Normalizing constant estimationquery complexity: \widetilde O\mathopen{}\mathclose\bgroup\originalleft(\kappa^{7/6}d^{7/6}\epsilon^{-2}+\kappa d^{4/3}\epsilon^{-2}\afterImproved
Apply quantum mean estimation in multilevel ULD annealingMultilevel ULD · Normalizing constant estimationquery complexity: \widetilde O\mathopen{}\mathclose\bgroup\originalleft(\kappa^2d^{3/2}\epsilon^{-2}\aftergroup\egroup\originalright) -> \Improved
Combine quantum MALA with quantum annealing and non-destructive mean estimationMALA · Normalizing constant estimationquery complexity: \widetilde O\mathopen{}\mathclose\bgroup\originalleft(\kappa d^2\epsilon^{-2}\max\{1,\frac{\kappa}{d}\}\aftergroup\egrouImproved

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