Sampling from multimodal distributions with warm starts: Non-asymptotic bounds for the Reweighted Annealed Leap-Point Sampler
stat.ML, cs.LG, math.PR, math.ST, stat.CO, stat.TH
Submitted: 2025-12-19
Updated: 2026-10-12
Terminology
Sources
- Stochastic Interpolants: A Unifying Framework for Flows and Diffusions
- Weak Poincar'e Inequalities for Markov chains: theory and applications
- NETS: A Non-Equilibrium Transport Sampler
- Sampling and Identity-Testing Without Approximate Tensorization of Entropy
- Restricted Spectral Gap Decomposition for Simulated Tempering Targeting Mixture Distributions
- Simulated Tempering Langevin Monte Carlo II: An Improved Proof using Soft Markov Chain Decomposition
- Time-complexity of sampling from a multimodal distribution using sequential Monte Carlo
- Sampling Multimodal Distributions with the Vanilla Score: Benefits of Data-Based Initialization
- Convergence Bounds for Sequential Monte Carlo on Multimodal Distributions using Soft Decomposition
- Learning Interpolations between Boltzmann Densities
- Annealed Leap-Point Sampler for Multimodal Target Distributions
- Transport meets Variational Inference: Controlled Monte Carlo Diffusions
Related papers
- Behavior of prediction performance metrics with rare events
- Optimal Estimation of Generic Dynamics by Path-Dependent Neural Jump ODEs
- A Posterior-Dynamics Framework for Imaging Inverse Problems with Pretrained Diffusion Priors
- Efficient quadratic entropy with distance sketches
- Embedding-Bias in Conditional Independence Testing
- From Log-Odds to Shapley Values: An Explanatory Geometry for the Weighted Naive Bayes Classifier