168 citations · 249 across the 6 of their papers we have counts for
6 papers
Symbolic Discovery of Optimization Algorithms
Xiangning Chen, Chen Liang, Da Huang +9
We present a method to formulate algorithm discovery as program search, and apply it to discover optimization algorithms for deep neural network training. We leverage efficient sea…
Smart Build Targets Batching Service at Google
Kaiyuan Wang, Daniel Rall, Greg Tener +3
Google has a monolithic codebase with tens of millions build targets. Each build target specifies the information that is needed to build a software artifact or run tests. It is co…
A Study of the Learnability of Relational Properties: Model Counting Meets Machine Learning (MCML)
Muhammad Usman, Wenxi Wang, Kaiyuan Wang +3
This paper introduces the MCML approach for empirically studying the learnability of relational properties that can be expressed in the well-known software design language Alloy. A…
MoËT: Mixture of Expert Trees and its Application to Verifiable Reinforcement Learning
Marko Vasic, Andrija Petrovic, Kaiyuan Wang +3
Rapid advancements in deep learning have led to many recent breakthroughs. While deep learning models achieve superior performance, often statistically better than humans, their ad…
Symbolic Execution for Deep Neural Networks
Divya Gopinath, Kaiyuan Wang, Mengshi Zhang +2
Deep Neural Networks (DNN) are increasingly used in a variety of applications, many of them with substantial safety and security concerns. This paper introduces DeepCheck, a new ap…
Fault Localization for Declarative Models in Alloy
Kaiyuan Wang, Allison Sullivan, Darko Marinov +1
Fault localization is a popular research topic and many techniques have been proposed to locate faults in imperative code, e.g. C and Java. In this paper, we focus on the problem o…