mlsanityData to 14 Oct 2026

A Second-Order Method for Stochastic Bandit Convex Optimisation

arXiv 2302.05371 ↗First posted 10 Feb 2023cs.LG math.OC stat.MLcited by 10

Not on the map. Why?

Abstract (arXiv)

We introduce a simple and efficient algorithm for unconstrained zeroth-order stochastic convex bandits and prove its regret is at most (1 + r/d)[d1.5 √n + d3] polylog(n, d, r) where n is the horizon, d the dimension and r is the radius of a known ball containing the minimiser of the loss.

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Builds on 8 of its 23 references that are in the map. First posted on arXiv 10 Feb 2023.

Builds on

8 of 23 references.

References · 8

  1. 2014Learning to Optimize via Information-Directed Samplingcited by 168
  2. 2016Kernel-based methods for bandit convex optimizationcited by 63
  3. 2018The Many Faces of Exponential Weights in Online Learningcited by 33
  4. 2020Improved Regret for Zeroth-Order Adversarial Bandit Convex Optimisationcited by 33
  5. 2016An optimal algorithm for bandit convex optimizationcited by 20
  6. 2016(Bandit) Convex Optimization with Biased Noisy Gradient Oraclescited by 12
  7. 2015Escaping the Local Minima via Simulated Annealing: Optimization of Approximately Convex Functionscited by 10
  8. 2022Adaptive Bandit Convex Optimization with Heterogeneous Curvaturecited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 6; 2025: 2; 2026: 2.

10 papers.