paper-with-me

Papers

Continuously Tempered Diffusion Samplers

2025-08-30 · Ezra Erives, Bowen Jing, Peter Holderrieth, Tommi Jaakkola arxiv

Annealing-based neural samplers seek to amortize sampling from unnormalized distributions by training neural networks to transport a family of densities interpolating from source to target. A crucial design choice in the training phase of such samplers is the proposal distribution by which locations are generated at which to evaluate the loss. Previous work has obtained such a proposal distribution by combining a partially learned transport with annealed Langevin dynamics. However, isolated modes and other pathological properties of the annealing path imply that such proposals achieve insufficient exploration and thereby lower performance post training. To remedy this, we propose continuously tempered diffusion samplers, which leverage exploration techniques developed in the context of molecular dynamics to improve proposal distributions. Specifically, a family of distributions across different temperatures is introduced to lower energy barriers at higher temperatures and drive exploration at the lower temperature of interest. We empirically validate improved sampler performance driven by extended exploration. Code is available at https://github.com/eje24/ctds.

📄 PDF Abstract BibTeX arXiv:2509.00316

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

MetaDNS: Enhancing Exploration in Discrete Neural Samplers via Well-Tempered Metadynamics

2026-05-20 · Xiaochen Du, Juno Nam, Jaemoo Choi, Wei Guo 외 arxiv

Sampling from discrete distributions with multiple modes and energy barriers is fundamental to machine learning and computational physics. Recent discrete neural samplers like MDNS suffer from mode collapse and fail to s…

Tempered Guided Diffusion

2026-05-05 · Andreas Makris, Paul Fearnhead, Chris Nemeth arxiv

Training-free conditional diffusion provides a flexible alternative to task-specific conditional model training, but existing samplers often allocate computation inefficiently: independent guided trajectories can vary wi…

Continuously-Tempered PDMP Samplers

2022-05-19 · Matthew Sutton, Robert Salomone, Augustin Chevallier, Paul Fearnhead

New sampling algorithms based on simulating continuous-time stochastic processes called piece-wise deterministic Markov processes (PDMPs) have shown considerable promise. However, these methods can struggle to sample fro…

Amortized Simulation-Based Inference in Generalized Bayes via Neural Posterior Estimation

2026-01-29 · Shiyi Sun, Geoff K. Nicholls, Jeong Eun Lee arxiv

Generalized Bayesian Inference (GBI) tempers a loss with a temperature $β> 0$ to mitigate overconfidence and improve robustness under model misspecification, but existing GBI methods typically rely on costly MCMC or SDE-…

Bayesian Inference

Thermostat-assisted continuously-tempered Hamiltonian Monte Carlo for Bayesian learning

2017-11-30 · NeurIPS 2018 12 · Rui Luo, Jianhong Wang, Yaodong Yang, Zhanxing Zhu 외

We propose a new sampling method, the thermostat-assisted continuously-tempered Hamiltonian Monte Carlo, for Bayesian learning on large datasets and multimodal distributions. It simulates the Nos\'e-Hoover dynamics of a …