Safety
Adaptive multi-fidelity optimization with fast learning rates
arXiv:2604.16239v1 Announce Type: cross Abstract: In multi-fidelity optimization, biased approximations of varying costs of the target function are available. This paper studies the problem of optimiz
arXiv:2604.16239v1 Announce Type: cross Abstract: In multi-fidelity optimization, biased approximations of varying costs of the target function are available. This paper studies the problem of optimizing a locally smooth function with a limited budget, where the learner has to make a tradeoff between the cost and the bias of these approximations. We first prove lower bounds for the simple regret under different assumptions on the fidelities, based on a cost-to-bias function. We then present the Kometo algorithm which achieves, with additional logarithmic factors, the same rates without any knowledge of the function smoothness and fidelity assumptions, and improves previously proven guarantees. We finally empirically show that our algorithm outperforms previous multi-fidelity optimization methods without the knowledge of problem-dependent parameters.
Related
- A Hessian-Free Actor-Critic Algorithm for Bi-Level Reinforcement Learning with Applications to LLM Fine-Tuning
- Estimating Continuous Treatment Effects with Two-Stage Kernel Ridge Regression
- A Two-Timescale Primal-Dual Framework for Reinforcement Learning via Online Dual Variable Guidance
- Restless Bandits with Individual Penalty Constraints: A New Near-Optimal Index Policy and How to Learn It
Source: arXiv cs.LG | 2026-04-20