Bandit algorithms have been predominantly analyzed in the convex setting with function-value based stationary regret as the performance measure. In this paper, motivated by online reinforcement learning problems, we propose and analyze bandit algorithms for both general and structured nonconvex problems with nonstationary (or dynamic) regret as the performance measure, in both stochastic and non-stochastic settings. First, for general nonconvex functions, we consider nonstationary versions of first-order and second-order stationary solutions as a regret measure, motivated by similar performance measures for offline nonconvex optimization. In the case of second-order stationary solution based regret, we propose and analyze online and bandit versions of the cubic regularized Newton's method. The bandit version is based on estimating the Hessian matrices in the bandit setting, based on second-order Gaussian Stein's identity. Our nonstationary regret bounds in terms of second-order stationary solutions have interesting consequences for avoiding saddle points in the bandit setting. Next, for weakly quasi convex functions and monotone weakly submodular functions we consider nonstationary regret measures in terms of function-values; such structured classes of nonconvex functions enable one to consider regret measure defined in terms of function values, similar to convex functions. For this case of function-value, and first-order stationary solution based regret measures, we provide regret bounds in both the low- and high-dimensional settings, for some scenarios.
Bridging Adversarial and Nonstationary Multi-armed Bandit
Rotman School of Management, University of Toronto（多伦多大学罗特曼管理学院）；The Hong Kong University of Science and Technology（香港科技大学）；School of Data Science, The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳）数据科学学院）
Finite-time Analysis of Globally Nonstationary Multi-Armed Bandits
Stern School of Business（斯特恩商学院）；New York University（纽约大学）；Institute for Program Structures and Data Organization（程序结构与数据组织研究所）；Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院）；Kyoto University（京都大学）
We present and prove properties of a new offline policy evaluator for an exploration learning setting which is superior to previous evaluators. In particular, it simultaneously and correctly incorporates techniques from importance weighting, doubly robust evaluation, and nonstationary policy evaluation approaches. In addition, our approach allows generating longer histories by careful control of a bias-variance tradeoff, and further decreases variance by incorporating information about randomness of the target policy. Empirical evidence from synthetic and realworld exploration learning problem…
In this paper, we analyze the continuous armed bandit problems for nonconvex cost functions under certain smoothness and sublevel set assumptions. We first derive an upper bound on the expected cumulative regret of a simple bin splitting method. We then propose an adaptive bin splitting method, which can significantly improve the performance. Furthermore, a minimax lower bound is derived, which shows that our new adaptive method achieves locally minimax optimal expected cumulative regret.
We study the nonstationary stochastic Multi-Armed Bandit (MAB) problem in which the distribution of rewards associated with each arm are assumed to be time-varying and the total variation in the expected rewards is subject to a variation budget. The regret of a policy is defined by the difference in the expected cumulative rewards obtained using the policy and using an oracle that selects the arm with the maximum mean reward at each time. We characterize the performance of the proposed policies in terms of the worst-case regret, which is the supremum of the regret over the set of reward distri…
Power Constrained Nonstationary Bandits with Habituation and Recovery Dynamics
Department of Industrial and Systems Engineering, University of Wisconsin-Madison（工业与系统工程系，威斯康星大学麦迪逊分校）；College of Health Solutions, Arizona State University（健康解决方案学院，亚利桑那州立大学）
We considered a novel practical problem of online learning with episodically revealed rewards, motivated by several real-world applications, where the contexts are nonstationary over different episodes and the reward feedbacks are not always available to the decision making agents. For this online semi-supervised learning setting, we introduced Background Episodic Reward LinUCB (BerlinUCB), a solution that easily incorporates clustering as a self-supervision module to provide useful side information when rewards are not observed. Our experiments on a variety of datasets, both in stationary and…
MARBLE: Multi-Armed Restless Bandits in Latent Markovian Environment
Department of Computer and Systems Sciences (DSV), Stockholm University（斯德哥尔摩大学计算机与系统科学系）；Inria Sophia Antipolis（法国国家信息与自动化研究所索菲亚·安蒂波利斯研究中心）；Smartprofile（Smartprofile公司）
IBM Thomas J. Watson Research Center（IBM托马斯·J·沃森研究中心）；Orange Labs（Orange实验室）
We consider a novel formulation of the multi-armed bandit model, which we call the contextual bandit with restricted context, where only a limited number of features can be accessed by the learner at every iteration. This novel formulation is motivated by different online problems arising in clinical trials, recommender systems and attention modeling. Herein, we adapt the standard multi-armed bandit algorithm known as Thompson Sampling to take advantage of our restricted context setting, and propose two novel algorithms, called the Thompson Sampling with Restricted Context(TSRC) and the Window…
Saddle-point optimization problems are an important class of optimization problems with applications to game theory, multi-agent reinforcement learning and machine learning. A majority of the rich literature available for saddle-point optimization has focused on the offline setting. In this paper, we study nonstationary versions of stochastic, smooth, strongly-convex and strongly-concave saddle-point optimization problem, in both online (or first-order) and multi-point bandit (or zeroth-order) settings. We first propose natural notions of regret for such nonstationary saddle-point optimization…
On the Peril of (Even a Little) Nonstationarity in Satisficing Regret Minimization
Department of Industrial & Systems Engineering, University of Wisconsin-Madison（威斯康星大学麦迪逊分校工业与系统工程系）；SC Johnson College of Business, Cornell University（康奈尔大学SC约翰逊商学院）
University of Alberta（阿尔伯塔大学）；Stanford University（斯坦福大学）；University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）
In this work, we consider the off-policy policy evaluation problem for contextual bandits and finite horizon reinforcement learning in the nonstationary setting. Reusing old data is critical for policy evaluation, but existing estimators that reuse old data introduce large bias such that we can not obtain a valid confidence interval. Inspired from a related field called survey sampling, we introduce a variant of the doubly robust (DR) estimator, called the regression-assisted DR estimator, that can incorporate the past data without introducing a large bias. The estimator unifies several existi…
Stochastic zeroth-order (SZO), or gradient-free, optimization allows to optimize arbitrary functions by relying only on function evaluations under parameter perturbations, however, the iteration complexity of SZO methods suffers a factor proportional to the dimensionality of the perturbed function. We show that in scenarios with natural sparsity patterns as in structured prediction applications, this factor can be reduced to the expected number of active features over input-output pairs. We give a general proof that applies sparse SZO optimization to Lipschitz-continuous, nonconvex, stochastic…
Dipartimento di Informatica Università degli Studi di Milano（米兰大学信息系）
Motivated by recommendation problems in music streaming platforms, we propose a nonstationary stochastic bandit model in which the expected reward of an arm depends on the number of rounds that have passed since the arm was last pulled. After proving that finding an optimal policy is NP-hard even when all model parameters are known, we introduce a class of ranking policies provably approximating, to within a constant factor, the expected reward of the optimal policy. We show an algorithm whose regret with respect to the best ranking policy is bounded by $\widetilde{\mathcal{O}}\big(\!\sqrt{kT}…
Adversarial bandit optimization for approximately linear functions
Joint Graduate School of Mathematics for Innovation, Kyushu University, Japan（创新数学联合研究生院，九州大学，日本）；Department of Informatics, Kyushu University, Japan（信息学系，九州大学，日本）；RIKEN AIP, Japan（日本理化学研究所AIP）
As two popular schools of machine learning, online learning and evolutionary computations have become two important driving forces behind real-world decision making engines for applications in biomedicine, economics, and engineering fields. Although there are prior work that utilizes bandits to improve evolutionary algorithms' optimization process, it remains a field of blank on how evolutionary approach can help improve the sequential decision making tasks of online learning agents such as the multi-armed bandits. In this work, we propose the Genetic Thompson Sampling, a bandit algorithm that…
University of Amsterdam（阿姆斯特丹大学）；Ahold Delhaize（皇家阿霍德德尔海兹集团）；Microsoft（微软）
Ranking system is the core part of modern retrieval and recommender systems, where the goal is to rank candidate items given user contexts. Optimizing ranking systems online means that the deployed system can serve user requests, e.g., queries in the web search, and optimize the ranking policy by learning from user interactions, e.g., clicks. Bandit is a general online learning framework and can be used in our optimization task. However, due to the unique features of ranking, there are several challenges in designing bandit algorithms for ranking system optimization. In this dissertation, we s…
GSC-QEMit: A Telemetry-Driven Hierarchical Forecast-and-Bandit Framework for Adaptive Quantum Error Mitigation
1 Department of Software Engineering, Rochester Institute of Technology, Rochester, USA Emails；2 Institute for Quantum \& Information Sciences, Syracuse University, Syracuse, USA Emails
A Markov Decision Process (MDP) is a popular model for reinforcement learning. However, its commonly used assumption of stationary dynamics and rewards is too stringent and fails to hold in adversarial, nonstationary, or multi-agent problems. We study an episodic setting where the parameters of an MDP can differ across episodes. We learn a reliable policy of this potentially adversarial MDP by developing an Adversarial Reinforcement Learning (ARL) algorithm that reduces our MDP to a sequence of \emph{adversarial} bandit problems. ARL achieves $O(\sqrt{SATH^3})$ regret, which is optimal with re…
Closed-Loop Bayesian Bandit Encoder with GRAND Receiver for a Bursty Interference Channel
Ming Hsieh Department of Electrical and Computer Engineering（明希学校电气与计算机工程系）；Viterbi School of Engineering, University of Southern California（维特比工程学院，南加州大学）
Universitat Pompeu Fabra（庞培法布拉大学）；Barcelona Graduate School of Economics（巴塞罗那经济研究生院）；Barcelona School of Management（巴塞罗那管理学院）
We consider a repeated newsvendor problem where the inventory manager has no prior information about the demand, and can access only censored/sales data. In analogy to multi-armed bandit problems, the manager needs to simultaneously "explore" and "exploit" with her inventory decisions, in order to minimize the cumulative cost. We make no probabilistic assumptions---importantly, independence or time stationarity---regarding the mechanism that creates the demand sequence. Our goal is to shed light on the hardness of the problem, and to develop policies that perform well with respect to the regre…
Online Learning on Hidden-Convex Losses via Algorithmic Equivalence: Optimal Regret, Geometric Barrier, and Bandit Feedback
Singapore University of Technology and Design（新加坡科技设计大学）；National Technical University of Athens（雅典国家技术大学）；National and Kapodistrian University of Athens（雅典国家与卡多斯大学）；University of California, Irvine（加州大学 Irvine 分校）；Archimedes, Athena Research Center, Greece（希腊阿提卡研究中心 Archimedes）；National University of Singapore, Centre for Quantum Technologies（新加坡国立大学 量子技术中心）
Nanjing University of Aeronautics and Astronautics（南京航空航天大学）；University of Pittsburgh（匹兹堡大学）
Proximal gradient method has been playing an important role to solve many machine learning tasks, especially for the nonsmooth problems. However, in some machine learning problems such as the bandit model and the black-box learning problem, proximal gradient method could fail because the explicit gradients of these problems are difficult or infeasible to obtain. The gradient-free (zeroth-order) method can address these problems because only the objective function values are required in the optimization. Recently, the first zeroth-order proximal stochastic algorithm was proposed to solve the no…
University of Pittsburgh（匹兹堡大学）；Nanjing University of Aeronautics and Astronautics（南京航空航天大学）；JD Finance America Corporation（京东金融美国公司）
Alternating direction method of multipliers (ADMM) is a popular optimization tool for the composite and constrained problems in machine learning. However, in many machine learning problems such as black-box attacks and bandit feedback, ADMM could fail because the explicit gradients of these problems are difficult or infeasible to obtain. Zeroth-order (gradient-free) methods can effectively solve these problems due to that the objective function values are only required in the optimization. Recently, though there exist a few zeroth-order ADMM methods, they build on the convexity of objective fu…
