Stochastic Lifting is a novel technique that enhances the modeling of stochastic physical systems by introducing independent random labels to state transitions, allowing a single network to generate d…

This paper introduces mean field reinforcement learning through Markov decision processes in large-population stochastic control, developing the necessary framework for representative-agent learning,…

The paper proposes a novel Bayesian framework to learn the optimal decision strategy for the stochastic shortest path problem by directly constructing the posterior beliefs for the action-value functi…

This paper derives non-asymptotic bounds on the prediction risk for learning switched non-linear dynamical systems, providing the first guarantees from a single trajectory.

The paper analyzes the sample complexity of contextual bandits in the $s$-sparse setting, achieving optimal sample bounds for identifying an $\epsilon$-optimal policy.

The paper extends modular dynamic Bayesian networks (MDBNs) to model non-Markovian queues, providing the first causal metamodeling technique for such systems with significant speedup.

This paper introduces a stochastic differential equation approximation for linear Temporal Difference (TD) learning under Markovian noise, explaining the constant-stepsize error floor.

This paper introduces a framework for certifying the reliability of stochastic oracles and derives bounds on the minimum expected token cost for reliable oracle certification.

This paper provides non-asytotic sample complexity guarantees for the Navigate and Stop algorithm in online tabular Reinforcement Learning, identifying additional attributes that affect the overall sa…

The paper introduces PRAXIS, a novel algorithm that efficiently approximates the computation of 'Rashomon sets' for decision trees, significantly reducing memory and runtime complexity.

The paper challenges the conclusion that LLMs lack reasoning by demonstrating that reported performance drops on GSM-Symbolic are often statistically weak and partially attributable to dataset biases,…

This paper provides a mathematical framework for studying different policy learning problems and shows reductions between them.

This paper characterizes stabilizability of stochastic dynamic matching on hypergraphs using the arrival rates and incidence matrix, and proposes a stabilizing policy.

This paper introduces two novel mechanisms, reinforcement learning with metacognitive feedback (RLMF) and metacognitive data selection, to enhance language model metacognition and achieve faithful cal…

This paper introduces online assignment policies for stochastic matching on hypergraphs, which are maximally stable and allow for the derivation of necessary and sufficient stability criteria.

This paper theoretically justifies the strong performance of linear recurrent neural networks as memory units in partially observable reinforcement learning by constructing specific linear filters tha…

This paper analyzes the Bayesian fixed-budget best-arm identification problem with abstention, showing that it induces a phase transition from polynomial to exponential decay of error probability.