English
Related papers

Related papers: Sample-Adaptivity Tradeoff in On-Demand Sampling

200 papers

We study learning optimal policies from a logged dataset, i.e., offline RL, with function approximation. Despite the efforts devoted, existing algorithms with theoretic finite-sample guarantees typically assume exploratory data coverage or…

Machine Learning · Computer Science 2023-05-25 Chenjie Mao

We consider the adversarial online multi-task reinforcement learning setting, where in each of $K$ episodes the learner is given an unknown task taken from a finite set of $M$ unknown finite-horizon MDP models. The learner's objective is to…

Machine Learning · Computer Science 2023-01-12 Quan Nguyen , Nishant A. Mehta

Agnostic online learning is classically solved via a reduction to the realizable setting, utilizing Littlestone's Standard Optimal Algorithm (SOA) as a base learner. However, the SOA is computationally intractable to execute even for a…

Machine Learning · Computer Science 2026-05-11 Idan Attias , Steve Hanneke , Arvind Ramaswami

In this paper, we study oracle-efficient algorithms for beyond worst-case analysis of online learning. We focus on two settings. First, the smoothed analysis setting of [RST11,HRS22] where an adversary is constrained to generating samples…

Machine Learning · Computer Science 2022-11-23 Nika Haghtalab , Yanjun Han , Abhishek Shetty , Kunhe Yang

Recently, there has been significant work studying distribution testing under the Conditional Sampling model. In this model, a query specifies a subset $S$ of the domain, and the output received is a sample drawn from the distribution…

Data Structures and Algorithms · Computer Science 2020-11-05 Shyam Narayanan

One fundamental problem in decentralized multi-agent optimization is the trade-off between gradient/sampling complexity and communication complexity. We propose new algorithms whose gradient and sampling complexities are graph topology…

Optimization and Control · Mathematics 2021-01-14 Guanghui Lan , Yuyuan Ouyang , Yi Zhou

We study online multicalibration beyond the worst-case. We give a single, efficient algorithm which dynamically interpolates between benign and worst-case sequences by adaptively refining a dyadic grid of prediction values. Its error is…

Machine Learning · Computer Science 2026-05-22 Zhiming Huang , Jamie Morgenstern , Aaron Roth , Claire Jie Zhang

In this paper, we study the non-asymptotic and asymptotic performances of the optimal robust policy and value function of robust Markov Decision Processes(MDPs), where the optimal robust policy and value function are solved only from a…

Machine Learning · Statistics 2022-08-16 Wenhao Yang , Liangyu Zhang , Zhihua Zhang

We study the online learning problem of a bidder who participates in repeated auctions. With the goal of maximizing his T-period payoff, the bidder determines the optimal allocation of his budget among his bids for $K$ goods at each period.…

Computer Science and Game Theory · Computer Science 2017-11-20 Sevi Baltaoglu , Lang Tong , Qing Zhao

Adaptive sampling theory has shown that, with proper assumptions on the signal class, algorithms exist to reconstruct a signal in $\mathbb{R}^{d}$ with an optimal number of samples. We generalize this problem to the case of spatial signals,…

Machine Learning · Statistics 2017-02-20 John Lipor , Brandon Wong , Donald Scavia , Branko Kerkez , Laura Balzano

Round complexity is an extensively studied metric of distributed algorithms. In contrast, our knowledge of the \emph{message complexity} of distributed computing problems and its relationship (if any) with round complexity is still quite…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-05-01 Fabien Dufoulon , Shreyas Pai , Gopal Pandurangan , Sriram Pemmaraju , Peter Robinson

We investigate the sample complexity of networks with bounds on the magnitude of its weights. In particular, we consider the class \[ H=\left\{W_t\circ\rho\circ \ldots\circ\rho\circ W_{1} :W_1,\ldots,W_{t-1}\in M_{d, d}, W_t\in…

Machine Learning · Computer Science 2019-10-15 Amit Daniely , Elad Granot

We study the sample complexity of online reinforcement learning in the general \hzyrev{non-episodic} setting of nonlinear dynamical systems with continuous state and action spaces. Our analysis accommodates a large class of dynamical…

Machine Learning · Computer Science 2026-03-02 Michael Muehlebach , Zhiyu He , Michael I. Jordan

Motivated by limitations on the depth of near-term quantum devices, we study the depth-computation trade-off in the query model, where the depth corresponds to the number of adaptive query rounds and the computation per layer corresponds to…

Quantum Physics · Physics 2023-12-08 Uma Girish , Makrand Sinha , Avishay Tal , Kewen Wu

In this study, we derive Probably Approximately Correct (PAC) bounds on the asymptotic sample-complexity for RL within the infinite-horizon Markov Decision Process (MDP) setting that are sharper than those in existing literature. The…

Machine Learning · Computer Science 2025-07-17 Mohit Prashant , Arvind Easwaran

We investigate distribution testing with access to non-adaptive conditional samples. In the conditional sampling model, the algorithm is given the following access to a distribution: it submits a query set $S$ to an oracle, which returns a…

Data Structures and Algorithms · Computer Science 2018-11-06 Gautam Kamath , Christos Tzamos

Reinforcement learning with outcome-based feedback faces a fundamental challenge: when rewards are only observed at trajectory endpoints, how do we assign credit to the right actions? This paper provides the first comprehensive analysis of…

Machine Learning · Computer Science 2025-07-25 Fan Chen , Zeyu Jia , Alexander Rakhlin , Tengyang Xie

Asynchronous Q-learning aims to learn the optimal action-value function (or Q-function) of a Markov decision process (MDP), based on a single trajectory of Markovian samples induced by a behavior policy. Focusing on a $\gamma$-discounted…

Machine Learning · Computer Science 2022-09-13 Gen Li , Yuting Wei , Yuejie Chi , Yuantao Gu , Yuxin Chen

Offline reinforcement learning (RL) aims to find an optimal policy for Markov decision processes (MDPs) using a pre-collected dataset. In this work, we revisit the linear programming (LP) reformulation of Markov decision processes for…

Machine Learning · Computer Science 2024-12-11 Asuman Ozdaglar , Sarath Pattathil , Jiawei Zhang , Kaiqing Zhang

Large Language Models (LLMs) have become an indispensable part of natural language processing tasks. However, autoregressive sampling has become an efficiency bottleneck. Multi-Draft Speculative Decoding (MDSD) is a recent approach where,…

Computation and Language · Computer Science 2025-02-27 Zhengmian Hu , Tong Zheng , Vignesh Viswanathan , Ziyi Chen , Ryan A. Rossi , Yihan Wu , Dinesh Manocha , Heng Huang
‹ Prev 1 3 4 5 6 7 10 Next ›