67 citations · 107 across the 8 of their papers we have counts for
9 papers
Fixed-Budget Best-Arm Identification with Heterogeneous Reward Variances
Anusha Lalitha, Kousha Kalantari, Yifei Ma +2
We study the problem of best-arm identification (BAI) in the fixed-budget setting with heterogeneous reward variances. We propose two variance-adaptive BAI algorithms for this sett…
Context Uncertainty in Contextual Bandits with Applications to Recommender Systems
Hao Wang, Yifei Ma, Hao Ding +1
Recurrent neural networks have proven effective in modeling sequential user feedbacks for recommender systems. However, they usually focus solely on item relevance and fail to effe…
Zero-Shot Recommender Systems
Hao Ding, Yifei Ma, Anoop Deoras +2
Performance of recommender systems (RS) relies heavily on the amount of training data available. This poses a chicken-and-egg problem for early-stage products, whose amount of data…
Towards Optimal Off-Policy Evaluation for Reinforcement Learning with Marginalized Importance Sampling
Tengyang Xie, Yifei Ma, Yu-Xiang Wang
Motivated by the many real-world applications of reinforcement learning (RL) that require safe-policy iterations, we consider the problem of off-policy evaluation (OPE) -- the prob…
Dynamic Mini-batch SGD for Elastic Distributed Training: Learning in the Limbo of Resources
Haibin Lin, Hang Zhang, Yifei Ma +4
With an increasing demand for training powers for deep learning algorithms and the rapid growth of computation resources in data centers, it is desirable to dynamically schedule di…
Imitation-Regularized Offline Learning
Yifei Ma, Yu-Xiang Wang, Balakrishnan +1
We study the problem of offline learning in automated decision systems under the contextual bandits model. We are given logged historical data consisting of contexts, (randomized)…