Pablo Lemos

On diffusion models for amortized inference: Benchmarking and improving stochastic control and sampling

We study the problem of training diffusion models to sample from a distribution with a given unnormalized density or energy function. We ben… (see more)chmark several diffusion-structured inference methods, including simulation-based variational approaches and off-policy methods (continuous generative flow networks). Our results shed light on the relative advantages of existing algorithms while bringing into question some claims from past work. We also propose a novel exploration strategy for off-policy methods, based on local search in the target space with the use of a replay buffer, and show that it improves the quality of samples on a variety of target distributions. Our code for the sampling methods and benchmarks studied is made public at https://github.com/GFNOrg/gfn-diffusion as a base for future work on diffusion models for amortized inference.

2024-01-01

NeurIPS (published)

Sequence-Augmented SE(3)-Flow Matching For Conditional Protein Generation.

James Vuckovic

Eric Laufer

Cheng-Hao Liu

Michael M. Bronstein

2024-01-01

Neural Information Processing Systems (published)

dblp.uni-trier.de

Improving Gradient-guided Nested Sampling for Posterior Inference

Will Handley

We present a performant, general-purpose gradient-guided nested sampling algorithm, …

2023-12-06

ArXiv (preprint)

Bayesian Imaging for Radio Interferometry with Score-Based Priors

No'e Dia

M. J. Yantovski-Barth

Alexandre Adam

Micah Bowles

A. Scaife

U. Montŕeal

Ciela Institute

Flatiron Institute

2023-11-29

ArXiv (preprint)

Learning an Effective Evolution Equation for Particle-Mesh Simulations Across Cosmologies

Nicolas Payot

Carolina Cuesta-lazaro

C. Modi

2023-11-29

ArXiv (preprint)

The search for the lost attractor

Mario Pasquato

Syphax Haddad

Pierfrancesco Di Cintio

Alexandre Adam

No'e Dia

Mircea Petrache

Ugo Niccolo Di Carlo

Alessandro A. Trani

2023-11-27

ArXiv (preprint)

Towards equilibrium molecular conformation generation with GFlowNets

Alexandra Volokhova

Michał Koziarski

Alex Hernandez-Garcia

Cheng-Hao Liu

Santiago Miret

Luca Thiede

Zichao Yan

Alan Aspuru-Guzik

Yoshua Bengio

Sampling diverse, thermodynamically feasible molecular conformations plays a crucial role in predicting properties of a molecule. In this pa… (see more)per we propose to use GFlowNet for sampling conformations of small molecules from the Boltzmann distribution, as determined by the molecule's energy. The proposed approach can be used in combination with energy estimation methods of different fidelity and discovers a diverse set of low-energy conformations for highly flexible drug-like molecules. We demonstrate that GFlowNet can reproduce molecular potential energy surfaces by sampling proportionally to the Boltzmann distribution.

2023-10-27

NeurIPS.cc/2023/Workshop/AI4Mat (poster)

Posterior Sampling of the Initial Conditions of the Universe from Non-linear Large Scale Structures using Score-Based Generative Models

Ronan Legin

Matthew Ho

Shirley Ho

Benjamin Wandelt

2023-10-13

Monthly Notices of the Royal Astronomical Society: Letters (published)

Sampling-Based Accuracy Testing of Posterior Estimators for General Inference

Adam Coogan

2023-07-03

Proceedings of the 40th International Conference on Machine Learning (published)

Sampling-Based Accuracy Testing of Posterior Estimators for General Inference

Adam Coogan

2023-04-24

ICML.cc/2023/Conference (poster)

A theory of continuous generative flow networks

Alex Hernandez-Garcia

Lena Nehale Ezzine

Yoshua Bengio

Nikolay Malkin

Generative flow networks (GFlowNets) are amortized variational inference algorithms that are trained to sample from unnormalized target dist… (see more)ributions over compositional objects. A key limitation of GFlowNets until this time has been that they are restricted to discrete spaces. We present a theory for generalized GFlowNets, which encompasses both existing discrete GFlowNets and ones with continuous or hybrid state spaces, and perform experiments with two goals in mind. First, we illustrate critical points of the theory and the importance of various assumptions. Second, we empirically demonstrate how observations about discrete GFlowNets transfer to the continuous case and show strong results compared to non-GFlowNet baselines on several previously studied tasks. This work greatly widens the perspectives for the application of GFlowNets in probabilistic inference and various modeling settings.

2023-01-30

ArXiv (preprint)