mlsanityData to 14 Oct 2026

Improving the evaluation of samplers on multi-modal targets

arXiv 2504.08916 ↗First posted 11 Apr 2025stat.ML cs.LGcited by 9

Not on the map. Why?

Abstract (arXiv)

Addressing multi-modality constitutes one of the major challenges of sampling. In this reflection paper, we advocate for a more systematic evaluation of samplers towards two sources of difficulty that are mode separation and dimension. For this, we propose a synthetic experimental setting that we illustrate on a selection of samplers, focusing on the challenging criterion of recovery of the mode relative importance. These evaluations are crucial to diagnose the potential of samplers to handle multi-modality and therefore to drive progress in the field.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 28 of its 52 references that are in the map. First posted on arXiv 11 Apr 2025.

Builds on

28 of 52 references.

References · 28

  1. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  2. 2015Variational Inference with Normalizing Flowscited by 2,170
  3. 2016Density estimation using Real NVPcited by 2,042
  4. 2023Stochastic Interpolants: A Unifying Framework for Flows and Diffusionscited by 939
  5. 2014Theoretical guarantees for approximate sampling from smooth and log-concave densitiescited by 208
  6. 2021Path Integral Sampler: a stochastic control approach for samplingcited by 181
  7. 2018Neural Importance Samplingcited by 155
  8. 2023Denoising Diffusion Samplerscited by 149
  9. 2022An optimal control perspective on diffusion-based generative modelingcited by 147
  10. 2016High-dimensional Bayesian inference via the Unadjusted Langevin Algorithmcited by 146
  11. 2018Log-concave sampling: Metropolis-Hastings algorithms are fastcited by 118
  12. 2023Improved sampling via learned diffusionscited by 104
16 more
  1. 2023normflows: A PyTorch Package for Normalizing Flowscited by 56
  2. 2024Beyond ELBOs: A Large-Scale Evaluation of Variational Methods for Samplingcited by 56
  3. 2024Sequential Controlled Langevin Diffusionscited by 48
  4. 2023Learning Interpolations between Boltzmann Densitiescited by 43
  5. 2023Reverse Diffusion Monte Carlocited by 41
  6. 2023Sampling, Diffusions, and Stochastic Localizationcited by 40
  7. 2018Coupling and Convergence for Hamiltonian Monte Carlocited by 36
  8. 2020Stacking for Non-mixing Bayesian Computations: The Curse and Blessing of Multimodal Posteriorscited by 29
  9. 2021Variational Refinement for Importance Sampling Using the Forward Kullback-Leibler Divergencecited by 29
  10. 2024Stochastic Localization via Iterative Posterior Samplingcited by 28
  11. 2023On Sampling with Approximate Transport Mapscited by 21
  12. 2024Zeroth-Order Sampling Methods for Non-Log-Concave Distributions: Alleviating Metastability by Denoising Diffusioncited by 19
  13. 2024Faster Sampling without Isoperimetry via Diffusion-based Monte Carlocited by 15
  14. 2024A theoretical perspective on mode collapse in variational inferencecited by 14
  15. 2024Learned Reference-based Diffusion Sampling for multi-modal distributionscited by 9
  16. 2013Fighting Sample Degeneracy and Impoverishment in Particle Filters: A Review of Intelligent Approachescited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 7.

9 papers.

  1. 2025Trust Region Constrained Measure Transport in Path Space for Stochastic Optimal Control and Inferencecited by 23
  2. 2026Bridge Matching Sampler: Scalable Sampling via Generalized Fixed-Point Diffusion Matchingcited by 10
  3. 2026Annealing in variational inference mitigates mode collapse: A theoretical study on Gaussian mixturescited by 4
  4. 2026Exact Global MCMC with Denoising Diffusioncited by 2
  5. 2026The critical slowing down in training diffusion modelscited by 1
  6. 2025Particle Monte Carlo methods for Lattice Field Theorycited by 0
  7. 2026Sampling from multi-modal distributions on Riemannian manifolds with training-free stochastic interpolantscited by 0
  8. 2026Entropic Mirror Monte Carlocited by 0
  9. 2026Total Variation Guarantees for Sampling with Stochastic Localizationcited by 0