 MINDE: Mutual Information Neural Diffusion EstimationInternational Conference on Learning Representations (ICLR), 2023 |
 Interpretable Diffusion via Information DecompositionInternational Conference on Learning Representations (ICLR), 2023 |
 Provable benefits of annealing for estimating normalizing constants:
Importance Sampling, Noise-Contrastive Estimation, and beyondNeural Information Processing Systems (NeurIPS), 2023 |
 Mutual Information Regularized Offline Reinforcement LearningNeural Information Processing Systems (NeurIPS), 2022 |
 Variational Representations of Annealing Paths: Bregman Information
under Monotonic EmbeddingInformation Geometry (IG), 2022 |
 Score-Based Diffusion meets Annealed Importance SamplingNeural Information Processing Systems (NeurIPS), 2022 |
