11 papers
Beyond Marginal Validity: Finite-Sample Guarantees for Localized Conformal Prediction
Anton Conrad, Rustam Isaev, Denis Belomestny +2
Conformal prediction endows arbitrary black-box predictors with finite-sample, distribution-free marginal coverage, yet marginal validity can hide severe covariate-specific miscali…
Mathematical methods of reinforcement learning
Denis Belomestny, Alexander Gasnikov, Egor Gladin +5
Reinforcement learning (RL) is increasingly grounded in tools from probability, optimization, and operator theory. This survey organizes the mathematical structures that underpin t…
Your GFlowNet Secretly Learns an Optimal Transport Plan
Ian Maksimov, Nikita Morozov, Denis Belomestny +1
Generative Flow Networks (GFlowNets) are a framework for sampling structured objects via stochastic trajectories in a directed graph. In this work, we establish a theoretical conne…
Gaussian Approximation and Multiplier Bootstrap for Stochastic Gradient Descent
Marina Sheshukova, Sergey Samsonov, Denis Belomestny +4
In this paper, we establish the non-asymptotic validity of the multiplier bootstrap procedure for constructing the confidence sets using the Stochastic Gradient Descent (SGD) algor…
Proximal Point Nash Learning from Human Feedback
Daniil Tiapkin, Daniele Calandriello, Denis Belomestny +5
Traditional Reinforcement Learning from Human Feedback (RLHF) often relies on reward models, frequently assuming preference structures like the Bradley--Terry model, which may not…
Tight Bounds for Schrödinger Potential Estimation in Unpaired Data Translation
Nikita Puchkin, Denis Suchkov, Alexey Naumov +1
Modern methods of generative modelling and unpaired data translation based on Schrödinger bridges and stochastic optimal control theory aim to transform an initial density to a ta…