papers

Publications (29)

cs.LG2020

Annealed Importance Sampling with q-Paths

Rob Brekelmans, Vaden Masrani, Thang Bui +4

Annealed importance sampling (AIS) is the gold standard for estimating partition functions or marginal likelihoods, corresponding to importance sampling over a path of distribution…

cs.GR2026

Local MAP Sampling for Diffusion Models

Shaorong Zhang, Rob Brekelmans, Greg Ver Steeg

Diffusion Posterior Sampling (DPS) provides a principled Bayesian approach to inverse problems by sampling from . While posterior sampling is valuable for capturing…

cs.LG2025

Feynman-Kac Correctors in Diffusion: Annealing, Guidance, and Product of Experts

Marta Skreta, Tara Akhound-Sadegh, Viktor Ohanesian +6

While score-based generative models are the model of choice across diverse domains, there are limited tools available for controlling inference-time behavior in a principled manner…

cs.LG2020

All in the Exponential Family: Bregman Duality in Thermodynamic Variational Inference

Rob Brekelmans, Vaden Masrani, Frank Wood +2

The recently proposed Thermodynamic Variational Objective (TVO) leverages thermodynamic integration to provide a family of variational inference objectives, which both tighten and…

cs.LG2021

q-Paths: Generalizing the Geometric Annealing Path using Power Means

Vaden Masrani, Rob Brekelmans, Thang Bui +4

Many common machine learning methods involve the geometric annealing path, a sequence of intermediate densities between two distributions of interest constructed using the geometri…

cs.LG2024

Generalized Flow Matching for Transition Dynamics Modeling

Haibo Wang, Yuxuan Qiu, Yanze Wang +2

Simulating transition dynamics between metastable states is a fundamental challenge in dynamical systems and stochastic processes with wide real-world applications in understanding…