End-to-End Meta-Bayesian Optimisation with Transformer Neural Processes
Maraval, Alexandre, Zimmer, Matthieu, Grosnit, Antoine, Ammar, Haitham Bou
–arXiv.org Artificial Intelligence
Meta-Bayesian optimisation (meta-BO) aims to improve the sample efficiency of Bayesian optimisation by leveraging data from related tasks. While previous methods successfully meta-learn either a surrogate model or an acquisition function independently, joint training of both components remains an open challenge. This paper proposes the first end-to-end differentiable meta-BO framework that generalises neural processes to learn acquisition functions via transformer architectures. We enable this end-to-end framework with reinforcement learning (RL) to tackle the lack of labelled acquisition data. Early on, we notice that training transformer-based neural processes from scratch with RL is challenging due to insufficient supervision, especially when rewards are sparse. We formalise this claim with a combinatorial analysis showing that the widely used notion of regret as a reward signal exhibits a logarithmic sparsity pattern in trajectory lengths. To tackle this problem, we augment the RL objective with an auxiliary task that guides part of the architecture to learn a valid probabilistic model as an inductive bias. We demonstrate that our method achieves state-of-the-art regret results against various baselines in experiments on standard hyperparameter optimisation tasks and also outperforms others in the real-world problems of mixed-integer programming tuning, antibody design, and logic synthesis for electronic design automation.
arXiv.org Artificial Intelligence
Dec-22-2023
- Country:
- Oceania > Australia
- New South Wales > Sydney (0.04)
- North America
- United States
- Nevada (0.04)
- Maryland > Baltimore (0.04)
- Texas > Travis County
- Austin (0.04)
- Massachusetts > Middlesex County
- Cambridge (0.04)
- Louisiana > Orleans Parish
- New Orleans (0.04)
- California > Los Angeles County
- Long Beach (0.14)
- Canada > British Columbia
- United States
- Europe
- Spain > Canary Islands (0.04)
- Austria (0.04)
- Sweden > Stockholm
- Stockholm (0.04)
- Germany
- Hesse > Darmstadt Region
- Darmstadt (0.04)
- Bavaria > Lower Franconia
- Würzburg (0.04)
- Hesse > Darmstadt Region
- France > Bourgogne-Franche-Comté
- Asia
- China (0.04)
- Middle East > Israel
- Haifa District > Haifa (0.04)
- Africa > Ethiopia
- Addis Ababa > Addis Ababa (0.04)
- Oceania > Australia
- Genre:
- Research Report (1.00)
- Industry:
- Technology: