2026-09-19T20:49:05Zhttps://dspace.mit.edu/server/oai/request

oai:dspace.mit.edu:1721.1/1627282025-09-19T04:49:26Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023

Jaakkola, Tommi Erives, Ezra Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science 2025-09-18T14:29:21Z 2025-09-18T14:29:21Z 2025-05 2025-06-23T14:01:49.033Z https://hdl.handle.net/1721.1/162728 Sampling from distributions whose density is known up to a normalizing constant is an important problem with a wide range of applications including Bayesian posterior inference, statistical physics, and structural biology. 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 vector field 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. In this work we extend existing work and characterize new families of proposals based on controlled Langevin dynamics. In particular, 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 additionally explore proposals based on Langevin dynamics involving non-Newtonian kinetic energies. We empirically validate improved sampler performance driven by extended exploration. M.Eng. Massachusetts Institute of Technology In Copyright - Educational Use Permitted Copyright retained by author(s) https://rightsstatements.org/page/InC-EDU/1.0/ Towards Enhanced Proposals for PINN-Based Neural Sampler Training Thesis application/pdf Master Master of Engineering in Electrical Engineering and Computer Science Publication unknown unknown <Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="73c4c9ab-ae1b-4ba7-b683-027d050225cd"> <Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type> <Title>Towards Enhanced Proposals for PINN-Based Neural Sampler Training</Title> <PublishedIn> <Publication> </Publication> </PublishedIn> <PublicationDate>2025-05</PublicationDate> <Authors> <Author> <DisplayName>Erives, Ezra</DisplayName> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> </Authors> <Editors> </Editors> <Publishers> <Publisher> <DisplayName>Massachusetts Institute of Technology</DisplayName> <OrgUnit /> </Publisher> </Publishers> <License>https://rightsstatements.org/page/InC-EDU/1.0/</License> <Abstract>Sampling from distributions whose density is known up to a normalizing constant is an important problem with a wide range of applications including Bayesian posterior inference, statistical physics, and structural biology. 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 vector field 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. In this work we extend existing work and characterize new families of proposals based on controlled Langevin dynamics. In particular, 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 additionally explore proposals based on Langevin dynamics involving non-Newtonian kinetic energies. We empirically validate improved sampler performance driven by extended exploration.</Abstract> <Access xmlns="http://purl.org/coar/access_right" > </Access> </Publication>