Near-Optimal Regret for Oracle-Efficient Adversarial Contextual Bandits

We study contextual bandits with $K$ actions, a class of $N$ policies, and i.i.d.\ contexts from a distribution that the learner can sample. For any sequence of loss functions fixed before play, we give an oracle-efficient algorithm with expected regret $O(\sqrt{KT\log(2N)}\,\log(2KT))$ against the best policy in hindsight on the realized contexts. This improves the $T^{2/3}$ dependence on the horizon in prior oracle-efficient bounds and achieves the optimal regret rate in this setting up to logarithmic factors. Our algorithm perturbs policy scores using a Poisson sample of auxiliary contexts. At each sampled context, the perturbation assigned to an action is a Laplace noise draw multiplied by a scale specific to that context and action. We show that choosing these scales to minimize a convex objective determined by past observations yields the stated regret bound. We further approximate the minimizing scales by projected stochastic gradient descent using only an exact offline cost-sensitive optimization oracle that returns the optimum value. Since the table of scales can be large, the algorithm represents the SGD iterates implicitly by storing the random draws that determine each update and evaluates the scales only at queried contexts. Both the oracle complexity and the remaining resource bounds are polynomial in $T$, $K$, and $\log(2N)$.

Authors

Publication Details

Journal
arXiv (Cornell University)
Published
2026-11-12
DOI
https://doi.org/10.48550/arxiv.2611.17109
Primary Topic
Advanced Bandit Algorithms Research
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

Near-Optimal Regret for Oracle-Efficient Adversarial Contextual Bandits

Kiarash Banihashem, MohammadTaghi Hajiaghayi
arXiv (Cornell University)
Advanced Bandit Algorithms Research
preprint

Near-Optimal Regret for Oracle-Efficient Adversarial Contextual Bandits

Kiarash Banihashem, MohammadTaghi Hajiaghayi
preprint en

Abstract

We study contextual bandits with $K$ actions, a class of $N$ policies, and i.i.d.\ contexts from a distribution that the learner can sample. For any sequence of loss functions fixed before play, we give an oracle-efficient algorithm with expected regret $O(\sqrt{KT\log(2N)}\,\log(2KT))$ against the best policy in hindsight on the realized contexts. This improves the $T^{2/3}$ dependence on the horizon in prior oracle-efficient bounds and achieves the optimal regret rate in this setting up to logarithmic factors. Our algorithm perturbs policy scores using a Poisson sample of auxiliary contexts. At each sampled context, the perturbation assigned to an action is a Laplace noise draw multiplied by a scale specific to that context and action. We show that choosing these scales to minimize a convex objective determined by past observations yields the stated regret bound. We further approximate the minimizing scales by projected stochastic gradient descent using only an exact offline cost-sensitive optimization oracle that returns the optimum value. Since the table of scales can be large, the algorithm represents the SGD iterates implicitly by storing the random draws that determine each update and evaluates the scales only at queried contexts. Both the oracle complexity and the remaining resource bounds are polynomial in $T$, $K$, and $\log(2N)$.

arXiv (Cornell University)
Advanced Bandit Algorithms Research
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon