aiqbench analysis
This research advances Time-Varying Bayesian Optimization by removing the unrealistic constraint of constant sampling frequencies, addressing a critical bottleneck where Gaussian Process complexity scales cubically with dataset size. By deriving new regret bounds that account for variable observation rates, the authors introduce practical guidelines for managing stale data and dataset sizing in dynamic environments. The proposed BOLT algorithm demonstrates superior performance over current state-of-the-art methods on both synthetic benchmarks and real-world applications, offering a more robust framework for optimizing expensive black-box functions under non-stationary conditions.
Time-Varying Bayesian Optimization Without a Metronome
arXiv:2501.18963v4 Announce Type: replace-cross Abstract: Time-Varying Bayesian Optimization (TVBO) is the go-to framework for optimizing a time-varying, expensive, noisy black-box function $f$. However, most of the asymptotic guarantees offered by TVBO algorithms rely on the assumption that observations are acquired at a constant frequency. As the GP inference complexity scales with the cube of its dataset size, this assumption is unrealistic in the long run. In this paper, we relax this assumption and derive the first upper regret bound that explicitly accounts for changes in the observations sampling frequency. Based on this analysis, we formulate practical recommendations about dataset sizes and stale data policies of TVBO algorithms. We illustrate how an algorithm (BOLT) that follows these recommendations performs better than the state-of-the-art of TVBO through experiments on synthetic and real-world problems.
Abstract:Time-Varying Bayesian Optimization (TVBO) is the go-to framework for optimizing a time-varying, expensive, noisy black-box function $f$. However, most of the asymptotic guarantees offered by TVBO algorithms rely on the assumption that observations are acquired at a constant frequency. As the GP inference complexity scales with the cube of its dataset size, this assumption is unrealistic in the long run. In this paper, we relax this assumption and derive the first upper regret bound that explicitly accounts for changes in the observations sampling frequency. Based on this analysis, we formulate practical recommendations about dataset sizes and stale data policies of TVBO algorithms. We illustrate how an algorithm (BOLT) that follows these recommendations performs better than the state-of-the-art of TVBO through experiments on synthetic and real-world problems.
Machine Learning (stat.ML); Machine Learning (cs.LG)
arXiv:2501.18963 [stat.ML]
(or arXiv:2501.18963v4 [stat.ML] for this version)
https://doi.org/10.48550/arXiv.2501.18963 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 221 words
Related coverage
The Entangled Dimensions of Decision Theory
LessWrong · Jul 30, 2026
Why do models task game?
AI Alignment Forum · Aug 6, 2026
DIGing--SGLD: Decentralized and Scalable Langevin Sampling over Time--Varying Networks
arXiv · Aug 25, 2026
The Continual Constitutional Convention: How language models revise the documents that govern them
AI Alignment Forum · Oct 13, 2026