82 citations · 546 across the 65 of their papers we have counts for
6 papers · 1 filter
Accelerated and instance-optimal policy evaluation with linear function approximation
Tianjiao Li, Guanghui Lan, Ashwin Pananjady
We study the problem of policy evaluation with linear function approximation and present efficient and practical algorithms that come with strong optimality guarantees. We begin by…
Frequency-aware SGD for Efficient Embedding Learning with Provable Benefits
Yan Li, Dhruv Choudhary, Xiaohan Wei +4
Embedding learning has found widespread applications in recommendation systems and natural language modeling, among other domains. To learn quality embeddings efficiently, adaptive…
Mirror-prox sliding methods for solving a class of monotone variational inequalities
Guanghui Lan, Yuyuan Ouyang
In this paper we propose new algorithms for solving a class of structured monotone variational inequality (VI) problems over compact feasible sets. By identifying the gradient comp…
Faster Algorithm and Sharper Analysis for Constrained Markov Decision Process
Tianjiao Li, Ziwei Guan, Shaofeng Zou +3
The problem of constrained Markov decision process (CMDP) is investigated, where an agent aims to maximize the expected accumulated discounted reward subject to multiple constraint…
Policy Mirror Descent for Reinforcement Learning: Linear Convergence, New Sampling Complexity, and Generalized Problem Classes
Guanghui Lan
We present new policy mirror descent (PMD) methods for solving reinforcement learning (RL) problems with either strongly convex or general convex regularizers. By exploring the str…
Graph topology invariant gradient and sampling complexity for decentralized and stochastic optimization
Guanghui Lan, Yuyuan Ouyang, Yi Zhou
One fundamental problem in decentralized multi-agent optimization is the trade-off between gradient/sampling complexity and communication complexity. We propose new algorithms whos…