Deep Symbolic Superoptimization Without Human Knowledge

International Conference on Learning Representations (ICLR)

Abstract

Deep symbolic superoptimization refers to the task of applying deep learning methods to simplify symbolic expressions. Existing approaches either perform supervised training on human-constructed datasets that define equivalent expression pairs, or apply reinforcement learning with human-defined equivalent transformation actions. In short, almost all existing methods rely on human knowledge to define equivalence, which suffers from large labeling cost and learning bias. We thus propose HISS, a reinforcement learning framework for symbolic superoptimization that keeps humans outside the loop. HISS introduces a treeLSTM encoder-decoder network with attention to ensure tractable learning. Our experiments show that HISS can discover more simplification rules than existing human-dependent methods, and can learn meaningful embeddings for symbolic expressions, which are indicative of equivalence. The code is available at: GitHub

Latest Publications