Kernel-based Methods for Bandit Convex Optimization

Sébastien Bubeck · Yin Tat Lee · Ronen Eldan

107 citations0/0 files storedACM Symposium on Theory of Computing (STOC)

No readable copy stored yet — this record is metadata only.

No open-access location is known for this record yet.

Literature note Cite in a project Citation map

Advanced Bandit Algorithms Research Stochastic Gradient Optimization Techniques Optimization and Search Problems

Abstract

We consider the adversarial convex bandit problem and we build the first poly(T)-time algorithm with poly(n) √T-regret for this problem. To do so we introduce three new ideas in the derivative-free optimization

Paper brief

Loading…

Cite this work

Citation unavailable for this work.

BibTeX RIS CSL-JSON

No public copy is stored for this record, so only the metadata is cited.

Citations in this library

Citation map →

Stored only when both papers are in the corpus — 107 citations exist upstream.

References

2012Regret Analysis of Stochastic and Nonstochastic Multi-armed Bandit Problems 2012Regret Analysis of Stochastic and Nonstochastic Multi-armed Bandit Problems 2004Online convex optimization in the bandit setting: gradient descent without a gradient 2004Nearly Tight Bounds for the Continuum-Armed Bandit Problem 2010Optimal Algorithms for Online Convex Optimization with Multi-Point Bandit Feedback.2007The Price of Bandit Information for Online Optimization

Cited by

2021Distributed Online Optimization With Long-Term Constraints 2021Experimenting in Equilibrium 2020Distributed Online Linear Regressions 2019Adversarial Bandits with Knapsacks 2018Dynamic Joint Assortment and Pricing Optimization With Demand Learning 2020Robust Dynamic Pricing with Demand Learning in the Presence of Outlier Customers

Explore the map →

Papers that cite the same references — the relational fallback while embeddings are still backfilling.

Imported from OpenAlex (CC0) — nothing here is generated.