← Back to all news
arXiv Machine Learning By Anthony Bardou, Patrick Thiran

Time-Varying Bayesian Optimization Without a Metronome

Read the original on arXiv Machine Learning →

Time‑Varying Bayesian Optimization (TVBO) is a framework for optimizing expensive, noisy black‑box functions that change over time. Existing TVBO algorithms assume observations are taken at a constant frequency, an assumption that becomes unrealistic as Gaussian‑process inference scales with the cube of dataset size. This paper relaxes that assumption, derives the first upper regret bound that incorporates variable sampling frequency, and uses the analysis to give practical guidance on dataset sizes and stale‑data policies. An algorithm (BOLT) that follows these recommendations outperforms the current state‑of‑the‑art TVBO methods on both synthetic and real‑world experiments.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
Aug 27

Gradient-based Sample Selection for Faster Bayesian Optimization

The paper introduces Gradient-based Sample Selection Bayesian Optimization (GSSBO), a method that builds the Gaussian process surrogate on a strategically chosen subset of samples rather than the full dataset. By using gradient information to eliminate redundant points while keeping diversity and representativeness, GSSBO achieves sublinear regret bounds and reduces the cubic computational cost of standard BO. Experiments on synthetic and real-world tasks show that this approach maintains comparable optimization performance while significantly cutting GP fitting time and resource usage.

By Qiyu Wei, Haowei Wang, Zirui Cao, Songhao Wang, Richard Allmendinger, Mauricio A \'Alvarez
More like this →