Tue 25 Jun 2019 14:20 - 14:40 at 224AB - Reasoning and Optimizing ML Models Chair(s): Martin Maas

Most traditional software systems are not built with the artificial intelligence support (AI) in mind. Among them, some may require human interventions to operate, e.g., the manual specification of the parameters in the data processing programs, or otherwise, would behave poorly. We propose a novel framework called Autonomizer to autonomize these systems by installing the AI into the traditional programs. Autonomizeris general so it can be applied to many real-world applications. We provide the primitives and the run-time support, where the primitives abstract common tasks of autonomization and the runtime support realizes them transparently. With the support of Autonomizer, the users can gain the AI support with little engineering efforts. Like many other AI applications, the challenge lies in the feature selection, which we address by proposing multiple automated strategies based on the program analysis. Our experiment results on nine real-world applications show that the autonomization only requires adding a few lines to the source code.Besides, for the data-processing programs, Autonomizer improves the output quality by 161% on average over the default settings. For the interactive programs such as game/driving,Autonomizer achieves higher success rate with lower training time than existing autonomized programs.

Tue 25 Jun

Displayed time zone: Tijuana, Baja California change

14:00 - 15:30
Reasoning and Optimizing ML ModelsPLDI Research Papers at 224AB
Chair(s): Martin Maas Google
14:00
20m
Talk
An Inductive Synthesis Framework for Verifiable Reinforcement Learning
PLDI Research Papers
He Zhu Rutgers University, USA, Zikang Xiong Purdue University, Stephen Magill , Suresh Jagannathan Purdue University
Media Attached
14:20
20m
Talk
Programming Support for Autonomizing Software
PLDI Research Papers
Wen-Chuan Lee Purdue University, Peng Liu Purdue University, Yingqi Liu Purdue University, USA, Shiqing Ma Purdue University, USA, Xiangyu Zhang Purdue University
14:40
20m
Talk
Wootz: A Compiler-Based Framework for Fast CNN Pruning via Composability
PLDI Research Papers
Hui Guan North Carolina State University, Xipeng Shen North Carolina State University, Seung-Hwan Lim Oak Ridge National Laboratory, USA
Media Attached File Attached
15:00
20m
Talk
Optimization and Abstraction: A Synergistic Approach for Analyzing Neural Network Robustness
PLDI Research Papers
Greg Anderson University of Texas at Austin, USA, Shankara Pailoor University of Texas at Austin, USA, Işıl Dillig UT Austin, Swarat Chaudhuri Rice University
Media Attached