Sharp Optimal Algorithm for Derivative-Free Stochastic Convex Optimization in One Dimension

arXiv:2607.12938 · math.OC, stat.ML · Submitted 2026-07-14 · Read on arXiv

Alexandra Carpentier, Chloé Rouyer, Alexandre Tsybakov, Arya Akhavan

math.OC, stat.ML

Submitted: 2026-07-14

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Regret — 21× in this paper · explained in 4 episodes
• Data Assimilation — 2× in this paper · explained in 2 episodes
• European Research Council — 2× in this paper
• Accuracy — 1× in this paper · explained in 1 episode
• Computational Tractability — 1× in this paper · explained in 2 episodes
• Papers — 1× in this paper · explained in 3 episodes
• Query Complexity — 1× in this paper · explained in 2 episodes
• Regret Guarantees — 1× in this paper · explained in 2 episodes
• Zeroth-Order Optimization — 1× in this paper · explained in 2 episodes

Sources

• Online Newton Method for Bandit Convex Optimisation

Related papers

• Lions and Muons: Optimization via Stochastic Frank-Wolfe under Heavy-Tailed Noise
• Adam-HNAG: A Convergent Reformulation of Adam with Accelerated Rate
• Incremental Learning in Mirror Flows
• Beyond Aggregate Drift: Optimal Client-Specific Windows in Federated Learning
• Lower Bounds for Randomized Linear-Oracle Optimization over Strongly Convex Sets
• Second-Order Optimization with Asynchronous Curvature