Machine Learning

A new algorithm for multi-fidelity best-arm identification achieves asymptotically optimal cost complexity, offering significant improvements over existing methods.

Optimal Flow Matching (OFM) learns straight trajectories for generative modeling in a single step, eliminating iterative processes and improving efficiency.

Dope: Efficient algorithms optimize human preference elicitation for learning to rank, minimizing ranking loss and prediction error with absolute and ranking feedback models.

Tri-BBAI & Opt-BBAI achieve optimal asymptotic and near-optimal non-asymptotic sample & batch complexities in batched best arm identification.

Researchers developed QUIVER, an efficient algorithm for adaptive stochastic quantization, solving a previously intractable problem in machine learning.

This paper introduces a novel method for creating highly accurate and narrow prediction intervals even when data distribution shifts unexpectedly, significantly improving machine learning model reliab…

OptEx significantly speeds up first-order optimization by cleverly parallelizing iterations, enabling faster convergence for complex tasks.

Opponent Modeling with In-context Search (OMIS) leverages in-context learning and decision-time search for stable and effective opponent adaptation in multi-agent environments.

Opponent modeling based on subgoal inference (OMG) outperforms existing methods by inferring opponent subgoals, enabling better generalization to unseen opponents in multi-agent environments.

POWR: a novel RL algorithm using operator world models and policy mirror descent achieves global convergence with improved sample efficiency.

OPERA: A new algorithm intelligently blends multiple offline policy evaluation estimators for more accurate policy performance estimates.

This paper introduces open-book neural algorithmic reasoning, a novel framework that significantly enhances neural reasoning capabilities by allowing networks to access and utilize all training instan…

ORI: a novel online relational inference framework efficiently identifies hidden interaction graphs in evolving multi-agent systems using streaming data and real-time adaptation.

This paper introduces efficient approximate posterior sampling for contextual bandits using diffusion model priors, improving Thompson sampling’s performance and expressiveness.

Boost online learning algorithms with sublinear best-action queries to achieve optimal regret!

Online Label Shift adaptation with Online Feature Updates (OLS-OFU) significantly boosts online label shift adaptation by dynamically refining feature extractors using self-supervised learning, achiev…

This paper presents a novel two-level online control algorithm that learns to control continuous-time linear systems under adversarial disturbances, achieving sublinear regret.

Online learning algorithms can now leverage predictions about future data to achieve significantly lower regret, smoothly transitioning between worst-case and best-case performance based on prediction…

FedSD2C, a novel one-shot federated learning framework, tackles data heterogeneity and information loss by sharing synthetic distillates directly from local data, outperforming existing methods on com…

Truncated kernel methods consistently outperform standard methods by eliminating the saturation effect, offering faster learning rates and enhanced theoretical guarantees.