Hugging Face Trending Papers

Near-Optimal Regret for Oracle-Efficient Adversarial Contextual Bandits

Read the original on Hugging Face Trending Papers →

We study contextual bandits with $K$ actions, a class of $N$ policies, and i. i.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at Hugging Face Trending Papers.

arXiv Machine Learning
Sep 10

Mixing Makes Markovian Contexts Cheap for Linear Bandits

The paper extends the idea that contexts are cheap for linear bandits from i.i.d. settings to Markovian context processes. By assuming uniform geometric ergodicity, the authors construct a stationary surrogate action set and use a delayed‑update scheme to mitigate bias from nonstationary conditional context distributions. They provide a phased algorithm for unknown stationary distributions and achieve high‑probability regret bounds comparable to standard linear bandit oracles in fast‑mixing regimes, with empirical validation showing gains over LinUCB.

By Kaan Buyukkalayci, Osama Hanna, Christina Fragouli
Hugging Face Trending Papers
Jul 15

Optimal and Efficient Contextual Combinatorial Semi-bandits with General Function Approximation

We study the contextual combinatorial semi-bandit (CCSB) problem with general reward function approximation. At each round, the learner observes a context, selects a combinatorial action consisting of a subset of basic arms, and receives the reward of each selected arm; the goal is to maximize the cumulative reward over time.