8 papers
Improved denoising diffusion probabilistic models with efficient non-diagonal covariance modeling
Rui Xia, Ayan Das, Artem Artemev +3
The sampling process of Denoising Diffusion Probabilistic Models (DDPMs) can be accelerated by leveraging second-order information in the form of approximations to the denoising po…
Exploiting weight-space symmetries for approximating curvature
Artem Artemev, Rui Xia, Benjamin M. Boyd +4
Many machine learning techniques rely on approximating a loss function's curvature, but this is notoriously hard to do at the scale of modern deep networks. Surprisingly, no previo…
Reinforcement Learning Using known Invariances
Alexandru Cioba, Aya Kayal, Laura Toni +2
In many real-world reinforcement learning (RL) problems, the environment exhibits inherent symmetries that can be exploited to improve learning efficiency. This paper develops a th…
Cross-Tokenizer LLM Distillation through a Byte-Level Interface
Avyav Kumar Singh, Yen-Chen Wu, Alexandru Cioba +2
Cross-tokenizer distillation (CTD), the transfer of knowledge from a teacher to a student language model when the two use different tokenizers, remains a largely unsolved problem.…
Near-Optimal Sample Complexity in Reward-Free Kernel-Based Reinforcement Learning
Aya Kayal, Sattar Vakili, Laura Toni +1
Reinforcement Learning (RL) problems are being considered under increasingly more complex structures. While tabular and linear models have been thoroughly explored, the analytical…
Bayesian Optimization from Human Feedback: Near-Optimal Regret Bounds
Aya Kayal, Sattar Vakili, Laura Toni +2
Bayesian optimization (BO) with preference-based feedback has recently garnered significant attention due to its emerging applications. We refer to this problem as Bayesian Optimiz…