Reinforced Genetic Algorithm Learning for Optimizing Computation Graphs

We present a deep reinforcement learning approach to minimizing the execution cost of neural network computation graphs in an optimizing compiler. Unlike earlier learning-based works that require training the optimizer on the same graph to be optimized, we propose a learning approach that trains an optimizer offline and then generalizes to previously unseen graphs without further training. This allows our approach to produce high-quality execution decisions on real-world TensorFlow graphs in seconds instead of hours. We consider two optimization tasks for computation graphs: minimizing running time and peak memory usage. In comparison to an extensive set of baselines, our approach achieves significant improvements over classical and other learning-based methods on these two tasks.

Authors

• Aditya Paliwal
• Felix Gimeno
• Vinod Nair
• Yujia Li 0001
• Miles Lubin
• Pushmeet Kohli
• Oriol Vinyals

Keywords

• reinforcement learning
• learning to optimize
• combinatorial optimization
• computation graphs
• model parallelism
• learning for systems