5 citations · 21 across the 8 of their papers we have counts for
12 papers
Thompson Sampling for Unimodal Bandits
Long Yang, Zhao Li, Zehong Hu +4
In this paper, we propose a Thompson Sampling algorithm for \emph{unimodal} bandits, where the expected reward is unimodal over the partially ordered arms. To exploit the unimodal…
Optimize Neural Fictitious Self-Play in Regret Minimization Thinking
Yuxuan Chen, Li Zhang, Shijian Li +1
Optimization of deep learning algorithms to approach Nash Equilibrium remains a significant problem in imperfect information games, e.g. StarCraft and poker. Neural Fictitious Self…
Sync-Switch: Hybrid Parameter Synchronization for Distributed Deep Learning
Shijian Li, Oren Mangoubi, Lijie Xu +1
Stochastic Gradient Descent (SGD) has become the de facto way to train deep neural networks in distributed clusters. A critical factor in determining the training throughput and mo…
Characterizing and Modeling Distributed Training with Transient Cloud GPU Servers
Shijian Li, Robert J. Walls, Tian Guo
Cloud GPU servers have become the de facto way for deep learning practitioners to train complex models on large-scale datasets. However, it is challenging to determine the appropri…
Perseus: Characterizing Performance and Cost of Multi-Tenant Serving for CNN Models
Matthew LeMay, Shijian Li, Tian Guo
Deep learning models are increasingly used for end-user applications, supporting both novel features such as facial recognition, and traditional features, e.g. web search. To accom…
Inverse Reinforcement Learning with Multiple Ranked Experts
Pablo Samuel Castro, Shijian Li, Daqing Zhang
We consider the problem of learning to behave optimally in a Markov Decision Process when a reward function is not specified, but instead we have access to a set of demonstrators o…