Frontiers in Probabilistic Inference:
Sampling Meets Learning 

The Frontiers in Probabilistic Inference: Sampling meets Learning (FPI) workshop at ICLR 2025 focuses on modern approaches to probabilistic inference to address the challenging and under-explored area of sampling from an unnormalized distribution. Sampling spans a wide range of difficult and timely problems from molecular dynamics simulation, and Bayesian posterior inference/inverse problems to sampling from generative models weighted by target density (e.g. finetuning, inference-time alignment). We hope to provide an inclusive and collaborative environment to discuss emerging ML methods for learning samplers and their applications to real-world problems. We aim to facilitate discussions around identifying some key challenges of learning-based approaches, compared to classical sampling approaches, along with techniques to overcome them.

We will center workshop discussions around the following topics/questions:

• Sampling methods and their connections to optimal transport and optimal control.

• Classical sampling approaches and how learning accelerates them.

• Connections between sampling methods and physics.

• Understanding sampling from theoretical perspectives. 

• Applications of sampling to natural sciences, Bayesian inference, LLM fine-tuning, and more.

Submissions:

• See the Call for Papers page for information about our submission tracks and instructions on how to submit a paper on OpenReview. 

• All accepted submissions will be invited to present a poster at the workshop (in person). We will invite some of the accepted submissions to give a spotlight talk at the workshop.