When applying aggregating strategies to Prediction with Expert Advice, the learning rate must be adaptively tuned. The natural choice of sqrt(complexity/current loss) renders the analysis of Weighted Majority derivatives quite complicated. In particular, for arbitrary weights there have been no results proven so far. The analysis of the alternative "Follow the Perturbed Leader" (FPL) algorithm from Kalai (2003} (based on Hannan's algorithm) is easier. We derive loss bounds for adaptive learning rate and both finite expert classes with uniform weights and countable expert classes with arbitrary weights. For the former setup, our loss bounds match the best known results so far, while for the latter our results are (to our knowledge) new.
We study the problem of online learning with non-convex losses, where the learner has access to an offline optimization oracle. We show that the classical Follow the Perturbed Leader (FTPL) algorithm achieves optimal regret rate of $O(T^{-1/2})$ in this setting. This improves upon the previous best-known regret rate of $O(T^{-1/3})$ for FTPL. We further show that an optimistic variant of FTPL achieves better regret bounds when the sequence of losses encountered by the learner is `predictable'.
Tsinghua University（清华大学）；University of Southern California（南加利福尼亚大学）
We consider regret minimization for Adversarial Markov Decision Processes (AMDPs), where the loss functions are changing over time and adversarially chosen, and the learner only observes the losses for the visited state-action pairs (i.e., bandit feedback). While there has been a surge of studies on this problem using Online-Mirror-Descent (OMD) methods, very little is known about the Follow-the-Perturbed-Leader (FTPL) methods, which are usually computationally more efficient and also easier to implement since it only requires solving an offline planning problem. Motivated by this, we take a c…
Game-theoretic models of learning are a powerful set of models that optimize multi-objective architectures. Among these models are zero-sum architectures that have inspired adversarial learning frameworks. An important shortcoming of these zeros-sum architectures is that gradient-based training leads to weak convergence and cyclic dynamics. We propose a novel follow the leader training algorithm for zeros-sum architectures that guarantees convergence to mixed Nash equilibrium without cyclic behaviors. It is a special type of follow the perturbed leader algorithm where perturbations are the res…
Tel Aviv University（特拉维夫大学）；Ben-Gurion University（本-古里安大学）；Google Research（谷歌研究院）
We revisit the fundamental problem of prediction with expert advice, in a setting where the environment is benign and generates losses stochastically, but the feedback observed by the learner is subject to a moderate adversarial corruption. We prove that a variant of the classical Multiplicative Weights algorithm with decreasing step sizes achieves constant regret in this setting and performs optimally in a wide range of environments, regardless of the magnitude of the injected corruption. Our results reveal a surprising disparity between the often comparable Follow the Regularized Leader (FTR…
We consider the problem of online learning and its application to solving minimax games. For the online learning problem, Follow the Perturbed Leader (FTPL) is a widely studied algorithm which enjoys the optimal $O(T^{1/2})$ worst-case regret guarantee for both convex and nonconvex losses. In this work, we show that when the sequence of loss functions is predictable, a simple modification of FTPL which incorporates optimism can achieve better regret guarantees, while retaining the optimal worst-case regret guarantee for unpredictable sequences. A key challenge in obtaining these tighter regret…
Adaptive Learning Rates with Surrogate Probability for Follow-the-Perturbed-Leader
Korea Institute of Science and Technology（韩国科学技术院）；Kyoto University（京都大学）；RIKEN AIP（理化学研究所AIP）；The University of Tokyo（东京大学）；University of Science and Technology（科学技术大学）
In an online decision problem, one makes decisions often with a pool of decision sequence called experts but without knowledge of the future. After each step, one pays a cost based on the decision and observed rate. One reasonal goal would be to perform as well as the best expert in the pool. The modern and well-known way to attain this goal is the algorithm of exponential weighting. However, recently, another algorithm called follow the perturbed leader is developed and achieved about the same performance. In our work, we first show the properties shared in common by the two algorithms which …
Università degli Studi di Milano（米兰大学）；Toulouse School of Economics（图卢兹经济学院）；CLC Space GmbH（CLC航天有限公司）；Politecnico di Milano（米兰理工大学）
In this paper, we present a real-world application of online learning with expert advice to the field of Space Operations, testing our theory on real-life data coming from the Copernicus Sentinel-6 satellite. We show that in Spacecraft Memory Dump Optimization, a lightweight Follow-The-Leader algorithm leads to an increase in performance of over $60\%$ when compared to traditional techniques.
McGill University（麦吉尔大学）；ICREA；Pompeu Fabra University（庞培法布拉大学）；Budapest University of Technology and Economics（布达佩斯技术与经济大学）；Computer and Automation Research Institute of the Hungarian Academy of Sciences（匈牙利科学院计算机与自动化研究所）
Columbia University（哥伦比亚大学）；UC Berkeley（加州大学伯克利分校）；Google（谷歌）
We provide the first sub-linear space and sub-linear regret algorithm for online learning with expert advice (against an oblivious adversary), addressing an open question raised recently by Srinivas, Woodruff, Xu and Zhou (STOC 2022). We also demonstrate a separation between oblivious and (strong) adaptive adversaries by proving a linear memory lower bound of any sub-linear regret algorithm against an adaptive adversary. Our algorithm is based on a novel pool selection procedure that bypasses the traditional wisdom of leader selection for online learning, and a generic reduction that transform…
We propose a framework for ensuring safe behavior of a reinforcement learning agent when the reward function may be difficult to specify. In order to do this, we rely on the existence of demonstrations from expert policies, and we provide a theoretical framework for the agent to optimize in the space of rewards consistent with its existing knowledge. We propose two methods to solve the resulting optimization: an exact ellipsoid-based method and a method in the spirit of the "follow-the-perturbed-leader" algorithm. Our experiments demonstrate the behavior of our algorithm in both discrete and c…
Columbia University（哥伦比亚大学）；Cornell University（康奈尔大学）
We study a general online linear optimization problem(OLO). At each round, a subset of objects from a fixed universe of $n$ objects is chosen, and a linear cost associated with the chosen subset is incurred. To measure the performance of our algorithms, we use the notion of regret which is the difference between the total cost incurred over all iterations and the cost of the best fixed subset in hindsight. We consider Full Information and Bandit feedback for this problem. This problem is equivalent to OLO on the $\{0,1\}^n$ hypercube. The Exp2 algorithm and its bandit variant are commonly used…
An efficient algorithm for learning with semi-bandit feedback
Budapest University of Technology and Economics（布达佩斯技术与经济大学）；MTA SZTAKI Institute for Computer Science and Control（MTA SZTAKI计算机科学与控制研究所）；ETH Zürich（苏黎世联邦理工学院）
Recent work on follow the perturbed leader (FTPL) algorithms for the adversarial multi-armed bandit problem has highlighted the role of the hazard rate of the distribution generating the perturbations. Assuming that the hazard rate is bounded, it is possible to provide regret analyses for a variety of FTPL algorithms for the multi-armed bandit problem. This paper pushes the inquiry into regret bounds for FTPL algorithms beyond the bounded hazard rate condition. There are good reasons to do so: natural distributions such as the uniform and Gaussian violate the condition. We give regret bounds f…
We propose a sample-efficient alternative for importance weighting for situations where one only has sample access to the probability distribution that generates the observations. Our new method, called Geometric Resampling (GR), is described and analyzed in the context of online combinatorial optimization under semi-bandit feedback, where a learner sequentially selects its actions from a combinatorial decision set so as to minimize its cumulative loss. In particular, we show that the well-known Follow-the-Perturbed-Leader (FPL) prediction method coupled with Geometric Resampling yields the fi…
In this work we consider a variant of adversarial online learning where in each round one picks $B$ out of $N$ arms and incurs cost equal to the $\textit{minimum}$ of the costs of each arm chosen. We propose an algorithm called Follow the Perturbed Multiple Leaders (FPML) for this problem, which we show (by adapting the techniques of Kalai and Vempala [2005]) achieves expected regret $\mathcal{O}(T^{\frac{1}{B+1}}\ln(N)^{\frac{B}{B+1}})$ over time horizon $T$ relative to the $\textit{single}$ best arm in hindsight. This introduces a trade-off between the budget $B$ and the single-best-arm regr…
Delft University of Technology（代尔夫特理工大学）；Tata Institute of Fundamental Research（塔塔基础研究所）；Amazon（亚马逊）
We take a systematic look at the problem of storing whole files in a cache with limited capacity in the context of optimistic learning, where the caching policy has access to a prediction oracle (provided by, e.g., a Neural Network). The successive file requests are assumed to be generated by an adversary, and no assumption is made on the accuracy of the oracle. In this setting, we provide a universal lower bound for prediction-assisted online caching and proceed to design a suite of policies with a range of performance-complexity trade-offs. All proposed policies offer sublinear regret bounds…
Institute for Data Science & Analytics（数据科学与分析研究所）；Bocconi University（博科尼大学）；Toulouse School of Economics（图卢兹经济学院）；Artificial and Natural Intelligence Toulouse Institute（图卢兹人工智能与自然智能研究所）
We consider the problem of asynchronous online combinatorial optimization on a network of communicating agents. At each time step, some of the agents are stochastically activated, requested to make a prediction, and the system pays the corresponding loss. Then, neighbors of active agents receive semi-bandit feedback and exchange some succinct local information. The goal is to minimize the network regret, defined as the difference between the cumulative loss of the predictions of active agents and that of the best action in hindsight, selected from a combinatorial decision set. The main challen…
Group Distributionally Robust Optimization with Flexible Sample Queries
National Key Laboratory for Novel Software Technology, Nanjing University, China（国家新型软件技术重点实验室，南京大学，中国）；School of Artificial Intelligence, Nanjing University, China（人工智能学院，南京大学，中国）；John Hopcroft Center, Shanghai Jiao Tong University, China（约翰·霍普克罗夫特中心，上海交通大学，中国）；Thomas Lord Department of Computer Science, University of Southern California, USA（托马斯·劳德计算机科学系，美国南加州大学）
