English
Related papers

Related papers: Efficient Online-Bandit Strategies for Minimax Lea…

200 papers

Distributionally robust offline reinforcement learning (RL), which seeks robust policy training against environment perturbation by modeling dynamics uncertainty, calls for function approximations when facing large state-action spaces.…

Machine Learning · Computer Science 2025-11-03 Zhishuai Liu , Pan Xu

In this book, I introduce the basic concepts of Online Learning through the modern view of Online Convex Optimization. Here, online learning refers to the framework of regret minimization under worst-case assumptions. I present first-order…

Machine Learning · Computer Science 2026-04-28 Francesco Orabona

Many machine learning tasks, such as learning with invariance and policy evaluation in reinforcement learning, can be characterized as problems of learning from conditional distributions. In such problems, each sample $x$ itself is…

Machine Learning · Computer Science 2017-01-03 Bo Dai , Niao He , Yunpeng Pan , Byron Boots , Le Song

We consider the problem of designing minimax estimators for estimating the parameters of a probability distribution. Unlike classical approaches such as the MLE and minimum distance estimators, we consider an algorithmic approach for…

Machine Learning · Statistics 2020-06-23 Kartik Gupta , Arun Sai Suggala , Adarsh Prasad , Praneeth Netrapalli , Pradeep Ravikumar

A neural network-based approach for solving parametric convex optimization problems is presented, where the network estimates the optimal points given a batch of input parameters. The network is trained by penalizing violations of the…

Optimization and Control · Mathematics 2024-09-17 Carmine Delle Femine

A matroid is a notion of independence in combinatorial optimization which is closely related to computational efficiency. In particular, it is well known that the maximum of a constrained modular function can be found greedily if and only…

Machine Learning · Computer Science 2015-04-15 Branislav Kveton , Zheng Wen , Azin Ashkan , Hoda Eydgahi , Brian Eriksson

We consider dynamic pricing with many products under an evolving but low-dimensional demand model. Assuming the temporal variation in cross-elasticities exhibits low-rank structure based on fixed (latent) features of the products, we show…

Machine Learning · Computer Science 2019-09-12 Jonas Mueller , Vasilis Syrgkanis , Matt Taddy

We study computational and statistical consequences of problem geometry in stochastic and online optimization. By focusing on constraint set and gradient geometry, we characterize the problem families for which stochastic- and…

Optimization and Control · Mathematics 2025-07-17 Chen Cheng , Daniel Levy , John C. Duchi

We study online learning with bandit feedback (i.e. learner has access to only zeroth-order oracle) where cost/reward functions $\f_t$ admit a "pseudo-1d" structure, i.e. $\f_t(\w) = \loss_t(\pred_t(\w))$ where the output of $\pred_t$ is…

Machine Learning · Computer Science 2021-02-16 Aadirupa Saha , Nagarajan Natarajan , Praneeth Netrapalli , Prateek Jain

Leveraging offline data is an attractive way to accelerate online sequential decision-making. However, it is crucial to account for latent states in users or environments in the offline data, and latent bandits form a compelling model for…

Machine Learning · Computer Science 2025-09-03 Chinmaya Kausik , Kevin Tan , Ambuj Tewari

This paper considers the distributed bandit convex optimization problem with time-varying inequality constraints over a network of agents, where the goal is to minimize network regret and cumulative constraint violation. Existing…

Optimization and Control · Mathematics 2024-06-21 Kunpeng Zhang , Xinlei Yi , Guanghui Wen , Ming Cao , Karl H. Johansson , Tianyou Chai , Tao Yang

Contextual bandit algorithms have been recently studied under the federated learning setting to satisfy the demand of keeping data decentralized and pushing the learning of bandit models to the client side. But limited by the required…

Machine Learning · Computer Science 2022-10-14 Chuanhao Li , Hongning Wang

We study bandit convex optimization methods that adapt to the norm of the comparator, a topic that has only been studied before for its full-information counterpart. Specifically, we develop convex bandit algorithms with regret bounds that…

Machine Learning · Computer Science 2020-07-17 Dirk van der Hoeven , Ashok Cutkosky , Haipeng Luo

In this paper, we focus on the solution of online optimization problems that arise often in signal processing and machine learning, in which we have access to streaming sources of data. We discuss algorithms for online optimization based on…

Optimization and Control · Mathematics 2023-05-05 Nicola Bastianello , Ruggero Carli , Andrea Simonetto

In this paper we propose a model-based approach to the design of online optimization algorithms, with the goal of improving the tracking of the solution trajectory (trajectories) w.r.t. state-of-the-art methods. We focus first on quadratic…

Optimization and Control · Mathematics 2023-07-24 Nicola Bastianello , Ruggero Carli , Sandro Zampieri

Bandit problems with linear or concave reward have been extensively studied, but relatively few works have studied bandits with non-concave reward. This work considers a large family of bandit problems where the unknown underlying reward…

Machine Learning · Computer Science 2021-07-12 Baihe Huang , Kaixuan Huang , Sham M. Kakade , Jason D. Lee , Qi Lei , Runzhe Wang , Jiaqi Yang

We study online reinforcement learning in linear Markov decision processes with adversarial losses and bandit feedback, without prior knowledge on transitions or access to simulators. We introduce two algorithms that achieve improved regret…

Machine Learning · Computer Science 2023-10-19 Haolin Liu , Chen-Yu Wei , Julian Zimmert

The adversarial Bandit with Knapsack problem is a multi-armed bandits problem with budget constraints and adversarial rewards and costs. In each round, a learner selects an action to take and observes the reward and cost of the selected…

Machine Learning · Computer Science 2025-03-20 Mark Braverman , Jingyi Liu , Jieming Mao , Jon Schneider , Eric Xue

Motivated by applications in clinical trials and finance, we study the problem of online convex optimization (with bandit feedback) where the decision maker is risk-averse. We provide two algorithms to solve this problem. The first one is a…

Machine Learning · Computer Science 2018-10-02 Adrian Rivera Cardoso , Huan Xu

We consider the decision-making framework of online convex optimization with a very large number of experts. This setting is ubiquitous in contextual and reinforcement learning problems, where the size of the policy class renders…

Machine Learning · Computer Science 2021-02-19 Elad Hazan , Karan Singh