Skip to content

Author

Esmeralda S. Whitammer

5 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Amortizing intractable inference in diffusion models for vision, language, and control

Amortized sampling of the posterior over data is studied, and the asymptotic correctness of a data-free learning objective, relative trajectory balance, is proved for training a diffusion model that samples from this posterior, a problem that existing methods solve only approximately or in restricted cases.

S. Venkatraman, Moksh Jain, Luca Scimeca et al. · 75 citations · ⚡5

Improved off-policy training of diffusion samplers

This work benchmarks several diffusion-structured inference methods, including simulation-based variational approaches and off-policy methods (continuous generative flow networks), and proposes a novel exploration strategy for off-policy methods, based on local search in the target space with the use of a replay buffer.

Marcin Sendera, Minsu Kim, Sarthak Mittal et al. · 52 citations · ⚡7

Joint Bayesian Inference of Graphical Structure and Parameters with a Single Generative Flow Network

This paper proposes a method to approximate the joint posterior over not only the structure of a Bayesian Network, but also the parameters of its conditional probability distributions, using a single GFlowNet whose sampling policy follows a two-phase process.

T. Deleu, Mizu Nishikawa-Toomey, Jithendaraa Subramanian et al. · 65 citations · ⚡4

Let the Flows Tell: Solving Graph Combinatorial Optimization Problems with GFlowNets

This paper designs Markov decision processes (MDPs) for different combinatorial problems and proposes to train conditional GFlowNets to sample from the solution space and demonstrates that GFlowNet policies can efficiently find high-quality solutions.

Dinghuai Zhang, H. Dai, Esmeralda S. Whitammer et al. · 59 citations · ⚡8

Likelihood hacking in probabilistic program synthesis

This work formalises LH in a core probabilistic programming language (PPL) and gives sufficient syntactic conditions for its prevention, proving that a safe language fragment satisfying these conditions cannot produce likelihood-hacking programs.

Jacek Karwowski, Y. Kaddar, Zihuiwen Ye et al. · 2 citations