Results show that surrogate-guided search can substantially reduce the evaluation cost of gradient-free post-training while producing stronger deployable single experts.
Abstract
Gradient-free post-training has emerged as a compelling alternative to gradient-based optimization for large language models (LLMs), but existing approaches remain costly. We ask whether structured search can identify a strong single expert under a modest evaluation budget. Motivated by evidence that useful weight updates lie in low-dimensional subspaces, we apply Bayesian optimization within a random linear embedding of weight space. Our method requires no backpropagation and uses a Gaussian process surrogate to guide candidate evaluations efficiently. Across several reasoning benchmarks with Qwen2.5-Instruct models from 0.5B to 3B parameters, Bayesian optimization using five times less candidate evaluations matches or exceeds RandOpt. These results show that surrogate-guided search can substantially reduce the evaluation cost of gradient-free post-training while producing stronger deployable single experts.
A unified framework, KENDO (Kernel ENsemble Disagreement-aware Operator), is proposed that integrates Ensemble Gaussian Processes (EGP) with disagreement-aware acquisition strategies and extends the approach to multi-objective optimization via random scalarization that preserves the single-optimizer conditioning struct...
Heng Zhang, Hao-Tian Xiang, Konstantinos D. Polyzos et al.· 1 citation
Finite-Library Input-Warped Bayesian Optimization (FLIWBO), which selects warps from a finite library of smooth input maps by any history-dependent rule, and adapts the input geometry to accelerate learning while retaining high-probability convergence guarantees under mild hypotheses, with an explicit library-size cost...
Edvin Ketabati Augustinsson, Robert A. Bridges· 0 citations
This work introduces agentic Bayesian optimization: a paradigm in which an LLM agent is the central decision maker in the BO loop while a Bayesian backend provides the uncertainty-aware optimization substrate, and demonstrates the practical value of agentic BO in dynamic settings.
Paul Brunzema, Louis C. Tiao, Nhat Le et al.· 1 citation
Many design tasks can be cast as black-box function optimization, enabling use of Bayesian optimization to find an ideal design with minimal number of trials. However, often we do not actually need the optimum but instead a sufficiently good solution is enough, for instance a material that is durable enough for its int...
Samuli Kinnunen, P. Mikkola, Antti Niskanen et al.· arXiv.org· 0 citations
It is found that while LLMs are competitive zero-shot batch optimizers for numerical test functions, their performance is brittle compared to classical non-LLM optimization approaches.
Frank Hu, Shriram Chennakesavalu, David Graff· 0 citations
A dual-objective surrogate-guided ensemble search is introduced: candidate architectures are represented as directed acyclic graphs, and two surrogate models are trained independently to estimate predictive accuracy and diversity potential and guide an NES framework that efficiently identifies architectures that are bo...
Alexandr Udeneev, Petr Babkin, O. Bakhteev· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
