Projection-Free Bandit Convex Optimization
22ND INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS, VOL 89(2018)
摘要
In this paper, we propose the first computationally efficient projection-free algorithm for bandit convex optimization (BCO). We show that our algorithm achieves a sublinear regret of O(nT^4/5) (where T is the horizon and n is the dimension) for any bounded convex functions with uniformly bounded gradients. We also evaluate the performance of our algorithm against baselines on both synthetic and real data sets for quadratic programming, portfolio selection and matrix completion problems.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络