This paper studies a dynamic assortment problem on a two-sided service platform with incomplete information and heterogeneous customers, and develops a data-driven algorithm to learn parameters and op…

This paper shows that stochastic nonconvex optimization can be reduced to ordinary static regret minimization in online convex optimization, and establishes convergence rates for smooth and Lipschitz…

This paper introduces Repeated Policy Regret (RP-Regret), a novel game-theoretic metric for analyzing regret in repeated games with adaptive opponents, and proposes algorithms to minimize it.

The paper proposes a novel online learning algorithm that achieves an interval regret bound scaling with gradient variation, providing strong theoretical guarantees for non-stationary environments.

This paper derives the complete theory of covariance regret functional for decision making, providing insights on steepest-descent directions and boundary-optimal solutions.

The paper introduces MINTS, a minimalist Bayesian framework that simplifies sequential decision-making by placing priors only on the optimum location, allowing for the incorporation of structural cons…

The paper introduces 5WBENCH, a new benchmark for causal unlearning, and proposes MAAT, a novel three-phase framework that achieves high forgetting and high retention specifically on complex 'Why'-typ…

This paper shows that projected Adam with arbitrary moment decay parameters can have non-zero average regret in online optimization.

The paper theoretically explains that optimizing LLMs solely on outcomes leads to brittle reasoning (Reward-Induced Manifold Collapse) by favoring low-complexity shortcuts, and proposes process-based…

This paper proposes two strategies to improve feedback efficiency of reinforcement learning from human feedback (RLHF) in diffusion models.

The paper introduces BenchTrace, a novel benchmark designed to rigorously evaluate the self-evolution and reflection capabilities of LLM agents, revealing that current models struggle with accurate fa…

This paper introduces SAFE, a new framework for multi-agent reinforce learning with continuous action spaces using a counterfactual baseline conditioned on a self-evolving default action.

The paper introduces a truly benign Direct Preference Optimization (DPO) attack that can jailbreak large language models (LLMs) by fine-tuning them with minimal, harmless preference data, thereby supp…

The paper introduces an Item Response Theory (IRT)-based indicator that effectively identifies likely mislabeled items in existing LLM benchmarks, revealing systematic errors in labeling and model spe…

The paper introduces the Markov decision contest, a new framework for reinforcement learning using pairwise preferences, and proves that stationary Markov policies are optimal and solvable efficiently…

The paper proposes FOAM, an adaptive damping method that stabilizes the Shampoo optimization algorithm by dynamically controlling damping and eigendecomposition frequency, thereby reducing staleness-i…