93 citations · 210 across the 6 of their papers we have counts for
4 papers · 1 filter
Integrated Model, Batch and Domain Parallelism in Training Neural Networks
Amir Gholami, Ariful Azad, Peter Jin +2
We propose a new integrated method of exploiting model, batch and domain parallelism for the training of deep neural networks (DNNs) on large distributed-memory computers using min…
Regret Minimization for Partially Observable Deep Reinforcement Learning
Peter Jin, Kurt Keutzer, Sergey Levine
Deep reinforcement learning algorithms that estimate state and state-action value functions have been shown to be effective in a variety of challenging domains, including learning…
How to scale distributed deep learning?
Peter H. Jin, Qiaochu Yuan, Forrest Iandola +1
Training time on large datasets for deep neural networks is the principal workflow bottleneck in a number of important applications of deep learning, such as object classification…
Convolutional Monte Carlo Rollouts in Go
Peter H. Jin, Kurt Keutzer
In this work, we present a MCTS-based Go-playing program which uses convolutional networks in all parts. Our method performs MCTS in batches, explores the Monte Carlo search tree u…