This paper analyzes Best-of-$N$ preference data, deriving explicit reward targets for independent-reference variants and establishing design principles for choosing $N$ and the base distribution to op…

ShaplEIG introduces a Bayesian experimental design framework to efficiently and adaptively estimate Shapley values by minimizing the number of required costly function evaluations.

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 introduces and analyzes several novel data appraisal metrics, including the Vendi Score and matrix spectral functions, demonstrating that efficient optimization techniques make these metrics…

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 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 proposes FedSAP, a framework that stabilizes federated prototype learning by delaying global alignment and enforcing inter-class structure, significantly improving representation quality und…

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.

The paper proposes a unified, constrained optimization framework using KL divergence and likelihood constraints to achieve effective and principled unlearning in diffusion models.

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 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…

The paper proposes DiReCT, a novel framework that treats data selection during LLM annealing as a constrained optimization problem based on the spectral geometry of the loss landscape, achieving state…

The paper introduces trust functions to filter weak supervision labels, enabling near-lossless weak-to-strong generalization by selectively training a strong student using only the most reliable weak…

The paper proposes Locality-Aware Redundancy Pruning (LoRP), a training-free method that prunes LLM layers by exploiting localized inter-layer redundancy, leading to improved efficiency while maintain…

This paper analyzes the poor performance of Meta-learning for Training-data Selection (MTS) and proposes that increasing the batch size and incorporating informative features can significantly improve…

This paper introduces cost-aware Retrieval-Augmented Generation (RAG), demonstrating that fixed evidence selection is brittle and that adaptive, agentic controllers are necessary for effective knowled…

The paper proposes a novel geometric embedding hashing method to recover object correspondences (vector links) between two embedding clouds generated by different black-box encoders using only a small…