تقرير
Stochastic Bandits with ReLU Neural Networks
العنوان: | Stochastic Bandits with ReLU Neural Networks |
---|---|
المؤلفون: | Xu, Kan, Bastani, Hamsa, Goel, Surbhi, Bastani, Osbert |
سنة النشر: | 2024 |
المجموعة: | Computer Science Statistics |
مصطلحات موضوعية: | Computer Science - Machine Learning, Computer Science - Data Structures and Algorithms, Statistics - Machine Learning |
الوصف: | We study the stochastic bandit problem with ReLU neural network structure. We show that a $\tilde{O}(\sqrt{T})$ regret guarantee is achievable by considering bandits with one-layer ReLU neural networks; to the best of our knowledge, our work is the first to achieve such a guarantee. In this specific setting, we propose an OFU-ReLU algorithm that can achieve this upper bound. The algorithm first explores randomly until it reaches a linear regime, and then implements a UCB-type linear bandit algorithm to balance exploration and exploitation. Our key insight is that we can exploit the piecewise linear structure of ReLU activations and convert the problem into a linear bandit in a transformed feature space, once we learn the parameters of ReLU relatively accurately during the exploration stage. To remove dependence on model parameters, we design an OFU-ReLU+ algorithm based on a batching strategy, which can provide the same theoretical guarantee. |
نوع الوثيقة: | Working Paper |
URL الوصول: | http://arxiv.org/abs/2405.07331 |
رقم الأكسشن: | edsarx.2405.07331 |
قاعدة البيانات: | arXiv |
الوصف غير متاح. |