The Hybrid Online Learning Problem, where features are drawn i.i.d. from an unknown distribution but labels are generated adversarially, is a well-motivated setting positioned between statistical and fully-adversarial online learning. Prior work has presented a dichotomy: algorithms that are statistically-optimal, but computationally intractable (Wu et al., 2023), and algorithms that are computationally-efficient (given an ERM oracle), but statistically-suboptimal (Wu et al., 2024).
This paper takes a significant step towards achieving statistical optimality and computational efficiency simultaneously in the Hybrid Learning setting. To do so, we consider a structured setting, where the Adversary is constrained to pick labels from an expressive, but fixed, class of functions $R$. Our main result is a new learning algorithm, which runs efficiently given an ERM oracle and obtains regret scaling with the Rademacher complexity of a class derived from the Learner's hypothesis class $H$ and the Adversary's label class $R$. As a key corollary, we give an oracle-efficient algorithm for computing equilibria in stochastic zero-sum games when action sets may be high-dimensional but the payoff function exhibits a type of low-dimensional structure. Technically, we develop a number of tools for the design and analysis of our learning algorithm, including a novel Frank-Wolfe reduction with "truncated entropy regularizer" and a new tail bound for sums of "hybrid" martingale difference sequences.
An Oracle for Guiding Large-Scale Model/Hybrid Parallel Training of Convolutional Neural Networks
Barcelona Supercomputing Center（巴塞罗那超级计算中心）；Universitat Politècnica de Catalunya（加泰罗尼亚理工大学）；National Institute of Advanced Industrial Science and Technology（日本产业技术综合研究所）；RIKEN-CCS（理化学研究所计算科学研究中心）
Goergen Institute for Data Science and Artificial Intelligence (GIDS-AI)（数据科学与人工智能研究所）；Department of Computer Science, University of Rochester（罗切斯特大学计算机科学系）；School of Aerospace Engineering, Georgia Institute of Technology（佐治亚理工学院航空航天工程学院）
Addressing practical challenges in Active Learning via a hybrid query strategy
Kansas State University（堪萨斯州立大学）；Indian Institute of Technology Gandhinagar（甘地纳格尔印度理工学院）；Viking Analytics（维京分析公司）；Luleå University of Technology（吕勒奥理工大学）；Indian Institute of Technology Madras（马德拉斯印度理工学院）
Online Markov Decision Processes with Non-oblivious Strategic Adversary
University of Southampton（南安普顿大学）；Huawei R&D UK（华为英国研发中心）；University of Warwick（华威大学）；University College London（伦敦大学学院）
我们研究了在线马尔可夫决策过程（OMDPs）中的一个新的设置，其中的损失函数是由一个非遗忘的战略对手谁遵循无外部遗憾算法选择。在这种情况下，我们首先证明了MDP-Expert，一个现有的算法，可以很好地与不经意的对手仍然可以应用和实现的政策遗憾界的$\mathcal{O}(\sqrt{T \log(L)}+τ^2\sqrt{ T \log(|A|)})$其中$L$是对手的纯策略集的大小和$|A|$表示代理的动作空间的大小。考虑到现实世界的游戏中，一个NE的支持大小是小的，我们进一步提出了一个新的算法：MDP-OOE在线Oracle专家（MDP-OOE），实现了$\mathcal{O}(\sqrt{T\log(L)}+τ^2\sqrt{ T k \log(k)})$的政策遗憾界，其中$k$只依赖于支持大小的NE。MDP-OOE在博弈论中利用了双预言的关键优势，因此可以解决具有过大动作空间的游戏。最后，为了更好地理解无遗憾方法的学习动态，在OMDPs中的无外部遗憾对手的相同设置下，我们引入了一种算法，该算法实现了NE的最后一轮收敛结果。据我们所知，这是第一个工作，导致OMDPs的最后一次迭代结果。
