曲率を考慮した期待自由エネルギーに基づくベイズ最適化の獲得関数
Curvature-aware Expected Free Energy as an Acquisition Function for Bayesian Optimization
ベイズ最適化において、学習と最適化を同時に行うための獲得関数として期待自由エネルギーを提案し、特定の条件下で既存の獲得関数と等価になることを示した。さらに、曲率を考慮した更新則を導入し、Van der Pol発振器のシステム同定問題で有効性を実証した。
詳しい要約
1. どんなもの?
2. 先行研究と比べてどこがすごい?
3. 技術・手法の肝は?
4. どうやって有効だと検証した?
5. 議論はある?
6. 次に読むべき論文は?
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Ajith Anil Meera, Wouter Kouw
分類: cs.LG, cs.RO, cs.SY, eess.SY
原文アブストラクト
We propose an Expected Free Energy-based acquisition function for Bayesian optimization to solve the joint learning and optimization problem, i.e., optimize and learn the underlying function simultaneously. We show that, under specific assumptions, Expected Free Energy reduces to Upper Confidence Bound, Lower Confidence Bound, and Expected Information Gain. We prove that Expected Free Energy has unbiased convergence guarantees for concave functions. Using the results from these derivations, we introduce a curvature-aware update law for Expected Free Energy and show its proof of concept using a system identification problem on a Van der Pol oscillator. Through rigorous simulation experiments, we show that our adaptive Expected Free Energy-based acquisition function outperforms state-of-the-art acquisition functions with the least final simple regret and error in learning the Gaussian process.
