arXiv AI
Aug 6
Efficient Online Lexicographic Generalized Low-Rank Matrix Bandits
arXiv:2608. 04324v1 Announce Type: cross Abstract: This paper studies generalized low-rank matrix bandits with multiple prioritized objectives.
Online Learning-to-Defer with Varying Experts
Related stories
arXiv Machine Learning
Jun 5
Adaptive Learning Rates with Surrogate Probability for Follow-the-Perturbed-Leader
arXiv:2606. 06043v1 Announce Type: cross Abstract: Follow-the-regularized-leader framework has shown effectiveness and flexibility in online learning problems, where the choice of learning rates are known to be crucial.
arXiv AI
Jun 16
Policy Regret for Embedding Model Routing: Contextual Bandits with Low-Rank Experts
arXiv:2606. 14929v1 Announce Type: cross Abstract: Modern recommendation systems increasingly rely on dynamically routing diverse queries to multiple embedding models.
arXiv Machine Learning
Aug 18
Online Convex Optimization with Dueling Feedback
arXiv:2608. 15050v1 Announce Type: new Abstract: We study online convex optimization with dueling (pairwise comparison) feedback, where the learner observes only a binary preference between two queried points.
arXiv Machine Learning
Aug 4
A Perturbation Approach to Unconstrained Linear Bandits
arXiv:2603. 28201v3 Announce Type: replace Abstract: We revisit the standard perturbation-based approach of Abernethy et al.
arXiv Machine Learning
Jul 14
Bandit PCA with Minimax Optimal Regret
arXiv:2607. 10936v1 Announce Type: new Abstract: We study the bandit-feedback version of online principal component analysis (Bandit PCA): in each round $t = 1,\dots,T$, the adversary selects a $d \times d$ symmetric gain matrix $G_t$ with spectrum in $[0,1]$ and rank at most $r$; the learner simultaneously selects a unit vector $w_t \in S^{d-1}$ and receives the reward $w_t^\top G_t w_t$.
arXiv AI
Sep 2
Bandits in Prod: Hyperparameter Optimization at Inference Time
The paper introduces Online Hyperparameter Optimization (OHPO), framing it as an infinitely many‑armed bandit problem over mixed and conditional search spaces. It proposes the IMABO framework, which couples any bandit policy with any oracle for proposing new configurations, and presents IMOSS—a restart‑free anytime policy with provable regret bounds. Experiments show that IMABO, combined with practical oracles such as TPE, an incumbent‑mutation oracle, and a pretrained tabular foundation model, outperforms random search across a range of settings from classical ML models to LLM‑based agents.
arXiv Machine Learning
Sep 10
Improved Dimension Dependence for Bandit Convex Optimization with Gradient Variations
The paper presents an improved analysis of non‑consecutive gradient variation in Bandit Convex Optimization (BCO) with two‑point feedback, leading to better dimension dependence for both convex and strongly convex functions compared to prior work. It also derives new problem‑dependent guarantees such as gradient‑variance and small‑loss regret bounds, extends the technique to one‑point bandit linear optimization over hyper‑rectangular domains, and establishes the first gradient‑variation dynamic and universal regret bounds for two‑point BCO.
arXiv Machine Learning
Sep 10
Online Learning with LLM Experts from Limited Feedback
arXiv:2609.05820v1 Announce Type: new Abstract: We study adaptive routing of prompts to large language model (LLM) experts to maximize response quality in an online setting with limited feedback. We...
arXiv Machine Learning
Jun 11
Capacity-Constrained Online Convex Optimization with Delayed Feedback
arXiv:2606. 11711v1 Announce Type: new Abstract: Online learning with delayed feedback typically assumes that the learner can track all pending rounds until their feedback arrives.
arXiv AI
Jun 30
Exploration and Online Transfer with Behavioral Foundation Models
arXiv:2606. 29980v1 Announce Type: new Abstract: Zero-shot Transfer in Reinforcement Learning (RL) aims to train an agent that can generate optimal policies for any reward function, without additional learning at transfer time, while training only on reward-free trajectories.
Hugging Face Trending Papers
Jul 21
The Price of Hidden Curvature: An $\widetildeΩ (d^{5/4} \sqrt{T})$ Lower Bound for Bandit Convex Optimization
We establish a $\widetildeΩ(d^{5/4}\sqrt T)$ lower bound on the minimax expected regret of stochastic bandit convex optimization of $1$-Lipschitz functions on the Euclidean ball. This presents the first nontrivial regret lower bound that grows faster than $d\sqrt{T}$ for this problem, establishing that stochastic bandit convex optimization is fundamentally harder than linear bandits.