arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2401.04812cs.AI
收藏

非凸优化的采样与定界方法

Sample-and-Bound for Non-Convex Optimization

University of California, San Diego(加利福尼亚大学圣迭戈分校)

Yaoguang Zhai, Zhizhen Qin, Sicun Gao

AI总结:

本文提出基于蒙特卡洛树搜索的非凸优化采样方法,用数值过近似替代访问次数作为不确定性度量,并结合一阶二阶信息采样估计,在高维基准上验证了其高效性。

摘要:

针对非凸函数全局优化的标准方法(如分支定界法)通过维护划分树来系统性地剪枝定义域,但树的规模会随维度数量呈指数增长。我们提出新的基于采样的非凸优化方法,将蒙特卡洛树搜索(MCTS)进行适配以提升效率。不同于置信上界中标准使用访问次数的方式,我们利用目标函数的数值过近似作为不确定性度量,同时考虑一阶和二阶信息的采样估计。我们方法中的蒙特卡洛树在生长过程中避免了通常的固定组合模式,并积极地聚焦于有前景的区域,同时仍能平衡探索与利用。我们在高维非凸优化基准上对所提算法进行了评估,并与竞争性基线方法进行了对比,分析了超参数的影响。

英文摘要:

Standard approaches for global optimization of non-convex functions, such as branch-and-bound, maintain partition trees to systematically prune the domain. The tree size grows exponentially in the number of dimensions. We propose new sampling-based methods for non-convex optimization that adapts Monte Carlo Tree Search (MCTS) to improve efficiency. Instead of the standard use of visitation count in Upper Confidence Bounds, we utilize numerical overapproximations of the objective as an uncertainty metric, and also take into account of sampled estimates of first-order and second-order information. The Monte Carlo tree in our approach avoids the usual fixed combinatorial patterns in growing the tree, and aggressively zooms into the promising regions, while still balancing exploration and exploitation. We evaluate the proposed algorithms on high-dimensional non-convex optimization benchmarks against competitive baselines and analyze the effects of the hyper parameters.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑