activity
20112022
most citedA Berkeley View of Systems Challenges for AI

176 citations · 699 across the 41 of their papers we have counts for

collaborators
Showing 2019Show all

14 papers · 1 filter

cs.LG20197 cited

Domain-Aware Dynamic Networks

Tianyuan Zhang, Bichen Wu, Xin Wang +2

Deep neural networks with more parameters and FLOPs have higher capacity and generalize better to diverse domains. But to be deployed on edge devices, the model's complexity has to…

cs.LG2019

Checkmate: Breaking the Memory Wall with Optimal Tensor Rematerialization

Paras Jain, Ajay Jain, Aniruddha Nrusimha +5

We formalize the problem of trading-off DNN training time and memory requirements as the tensor rematerialization optimization problem, a generalization of prior checkpointing stra…

cs.LG2019

A View on Deep Reinforcement Learning in System Optimization

Ameer Haj-Ali, Nesreen K. Ahmed, Ted Willke +3

Many real-world systems problems require reasoning about the long term consequences of actions taken to configure and manage the system. These problems with delayed and often seque…

cs.CR2019

Helen: Maliciously Secure Coopetitive Learning for Linear Models

Wenting Zheng, Raluca Ada Popa, Joseph E. Gonzalez +1

Many organizations wish to collaboratively train machine learning models on their combined datasets for a common benefit (e.g., better medical research, or fraud detection). Howeve…

cs.LG2019

On-Policy Robot Imitation Learning from a Converging Supervisor

Ashwin Balakrishna, Brijen Thananjeyan, Jonathan Lee +4

Existing on-policy imitation learning algorithms, such as DAgger, assume access to a fixed supervisor. However, there are many settings where the supervisor may evolve during polic…

cs.LG2019

ANODEV2: A Coupled Neural ODE Evolution Framework

Tianjun Zhang, Zhewei Yao, Amir Gholami +4

It has been observed that residual networks can be viewed as the explicit Euler discretization of an Ordinary Differential Equation (ODE). This observation motivated the introducti…