# Adaptive multi-fidelity optimization with fast learning rates

arXiv: https://arxiv.org/abs/2604.16239 · HTML: https://mlsanity.com/paper/2604.16239/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 25 references that are in the map.
- First posted on arXiv 17 Apr 2026.

## Builds on (most cited first, 7 of 7)

- [Multi-fidelity Bayesian Optimisation with Continuous Approximations](https://mlsanity.com/paper/1703.06240/) (2017)
- [Multi-fidelity Gaussian Process Bandit Optimisation](https://mlsanity.com/paper/1603.06288/) (2016)
- [A simple parameter-free and adaptive approach to optimization under a minimal local smoothness assumption](https://mlsanity.com/paper/1810.00997/) (2018)
- [The Multi-fidelity Multi-armed Bandit](https://mlsanity.com/paper/1610.09726/) (2016)
- [Noisy Blackbox Optimization with Multi-Fidelity Queries: A Tree Search Approach](https://mlsanity.com/paper/1810.10482/) (2018)
- [Global Continuous Optimization with Error Bound and Fast Convergence](https://mlsanity.com/paper/1607.04817/) (2016)
- [A Strategy for Adaptive Sampling of Multi-fidelity Gaussian Process to Reduce Predictive Uncertainty](https://mlsanity.com/paper/1907.11739/) (2019)

## Built on by (most cited first, 1 of 1)

- [Two-Fidelity Best-Action Identification for Stochastic Minimax Tree](https://mlsanity.com/paper/2606.01708/) (2026)

## Abstract (arXiv)

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.