Author name cluster

Aditya Paliwal

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

2 papers

2 author rows

AAAI Conference 2020 Conference Paper

Graph Representations for Higher-Order Logic and Theorem Proving

Aditya Paliwal
Sarah Loos
Markus Rabe
Kshitij Bansal
Christian Szegedy

This paper presents the ﬁrst use of graph neural networks (GNNs) for higher-order proof search and demonstrates that GNNs can improve upon state-of-the-art results in this domain. Interactive, higher-order theorem provers allow for the formalization of most mathematical theories and have been shown to pose a signiﬁcant challenge for deep learning. Higher-order logic is highly expressive and, even though it is well-structured with a clearly deﬁned grammar and semantics, there still remains no well-established method to convert formulas into graph-based representations. In this paper, we consider several graphical representations of higher-order logic and evaluate them against the HOList benchmark for higher-order theorem proving.

PDF Details

ICLR Conference 2020 Conference Paper

Reinforced Genetic Algorithm Learning for Optimizing Computation Graphs

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

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.

Details