106 citations · 996 across the 72 of their papers we have counts for
12 papers · 1 filter
Minimax Regret for Stochastic Shortest Path with Adversarial Costs and Known Transition
Liyu Chen, Haipeng Luo, Chen-Yu Wei
We study the stochastic shortest path problem with adversarial costs and known transition, and show that the minimax regret is and $\widetilde{O}…
Comparator-adaptive Convex Bandits
Dirk van der Hoeven, Ashok Cutkosky, Haipeng Luo
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,…
Learning Infinite-horizon Average-reward MDPs with Linear Function Approximation
Chen-Yu Wei, Mehdi Jafarnia-Jahromi, Haipeng Luo +1
We develop several new algorithms for learning Markov Decision Processes in an infinite-horizon average-reward setting with linear function approximation. Using the optimism princi…
Open Problem: Model Selection for Contextual Bandits
Dylan J. Foster, Akshay Krishnamurthy, Haipeng Luo
In statistical learning, algorithms for model selection allow the learner to adapt to the complexity of the best hypothesis class in a sequence. We ask whether similar guarantees a…
Active Online Learning with Hidden Shifting Domains
Yining Chen, Haipeng Luo, Tengyu Ma +1
Online machine learning systems need to adapt to domain shifts. Meanwhile, acquiring label at every timestep is expensive. We propose a surprisingly simple algorithm that adaptivel…
Linear Last-iterate Convergence in Constrained Saddle-point Optimization
Chen-Yu Wei, Chung-Wei Lee, Mengxiao Zhang +1
Optimistic Gradient Descent Ascent (OGDA) and Optimistic Multiplicative Weights Update (OMWU) for saddle-point optimization have received growing attention due to their favorable l…
Bias no more: high-probability data-dependent regret bounds for adversarial bandits and MDPs
Chung-Wei Lee, Haipeng Luo, Chen-Yu Wei +1
We develop a new approach to obtaining high probability regret bounds for online learning with bandit feedback against an adaptive adversary. While existing approaches all require…
Simultaneously Learning Stochastic and Adversarial Episodic MDPs with Known Transition
Tiancheng Jin, Haipeng Luo
This work studies the problem of learning episodic Markov Decision Processes with known transition and bandit feedback. We develop the first algorithm with a ``best-of-both-worlds'…
A Model-free Learning Algorithm for Infinite-horizon Average-reward MDPs with Near-optimal Regret
Mehdi Jafarnia-Jahromi, Chen-Yu Wei, Rahul Jain +1
Recently, model-free reinforcement learning has attracted research attention due to its simplicity, memory and computation efficiency, and the flexibility to combine with function…
Adversarial Online Learning with Changing Action Sets: Efficient Algorithms with Approximate Regret Bounds
Ehsan Emamjomeh-Zadeh, Chen-Yu Wei, Haipeng Luo +1
We revisit the problem of online learning with sleeping experts/bandits: in each time step, only a subset of the actions are available for the algorithm to choose from (and learn a…
Taking a hint: How to leverage loss predictors in contextual bandits?
Chen-Yu Wei, Haipeng Luo, Alekh Agarwal
We initiate the study of learning in contextual bandits with the help of loss predictors. The main question we address is whether one can improve over the minimax regret $\mathcal{…
A Closer Look at Small-loss Bounds for Bandits with Graph Feedback
Chung-Wei Lee, Haipeng Luo, Mengxiao Zhang
We study small-loss bounds for adversarial multi-armed bandits with graph feedback, that is, adaptive regret bounds that depend on the loss of the best arm or related quantities, i…