Jun 20, 2019 · We present Placeto, a reinforcement learning (RL) approach to efficiently find device placements for distributed neural network training.

We present Placeto, a reinforcement learning (RL) approach to efficiently find de- vice placements for distributed neural network training.

We present Placeto, a reinforcement learning (RL) approach to efficiently find device placements for distributed neural network training.

Placeto is able to learn a generalizable placement policy for any given family of graphs, which can be used without any retraining to predict optimized ...

- It shows generalization to unseen graphs, but they are generated artificially by architecture search for a single learning task and dataset. How does the ...

This paper proposed a policy based approach to device placement. It starts with an i initialized placement and the policy learns to update the placement of ...

We present Placeto, a reinforcement learning (RL) approach to efficiently find device placements for distributed neural network training.

Jan 1, 2019 · "Placeto: Learning Generalizable Device Placement Algorithms for Distributed Machine Learning". Advances in Neural Information Processing ...

Jun 24, 2019 · Bibliographic details on Placeto: Learning Generalizable Device Placement Algorithms for Distributed Machine Learning.

We present Placeto, a reinforcement learning (RL) approach to efficiently find device placements for distributed neural network training. BIG-bench Machine ...