Large Scale Multi-Task Bayesian Optimization with Large Language Models
In multi-task Bayesian optimization, the goal is to leverage experience from optimizing existing tasks to improve the efficiency of optimizing new ones. While approaches using multi-task Gaussian processes or deep kernel transfer exist, the performance improvement is marginal when scaling beyond a moderate number of tasks. We introduce a novel approach leveraging large language models (LLMs) to learn from, and improve upon, previous optimization trajectories, scaling to approximately 1500 distinct tasks. Specifically, we propose a feedback loop in which an LLM is fine-tuned on the high quality solutions to specific tasks found by Bayesian optimization (BO). This LLM is then used to generate initialization points for future BO searches for new tasks. The trajectories of these new searches provide additional training data for fine-tuning the LLM, completing the loop. We evaluate our method on two distinct domains: database query optimization and antimicrobial peptide design. Results demonstrate that our approach creates a positive feedback loop, where the LLM's generated initializations gradually improve, leading to better optimization performance. As this feedback loop continues, we find that the LLM is eventually able to generate solutions to new tasks in just a few shots that are better than the solutions produced by "from scratch" by Bayesian optimization while simultaneously requiring significantly fewer oracle calls.
Code (0)
등록된 구현이 없습니다.
Tasks
Bayesian OptimizationGaussian ProcessesSimilar Papers 제목 키워드 기반
Bayesian Screening: Multi-test Bayesian Optimization Applied to in silico Material Screening
We present new multi-test Bayesian optimization models and algorithms for use in large scale material screening applications. Our screening problems are designed around two tests, one expensive and one cheap. This paper …
Bayesian OptimizationBayesian Optimization with Robust Bayesian Neural Networks
Bayesian optimization is a prominent method for optimizing expensive to evaluate black-box functions that is prominently applied to tuning the hyperparameters of machine learning algorithms. Despite its successes, the pr…
Bayesian OptimizationDeep Reinforcement LearningHyperparameter OptimizationReinforcement Learning+1Latency-Aware Neural Architecture Search with Multi-Objective Bayesian Optimization
When tuning the architecture and hyperparameters of large machine learning models for on-device deployment, it is desirable to understand the optimal trade-offs between on-device latency and model accuracy. In this work,…
Bayesian OptimizationNatural Language UnderstandingNeural Architecture SearchVanilla Bayesian Optimization Performs Great in High Dimensions
High-dimensional problems have long been considered the Achilles' heel of Bayesian optimization algorithms. Spurred by the curse of dimensionality, a large collection of algorithms aim to make it more performant in this …
Bayesian OptimizationA Batched Scalable Multi-Objective Bayesian Optimization Algorithm
The surrogate-assisted optimization algorithm is a promising approach for solving expensive multi-objective optimization problems. However, most existing surrogate-assisted multi-objective optimization algorithms have th…
Bayesian Optimization