Wed 23 Oct 2024 17:00 - 17:20 at IBR West - Performance Analysis and Optimisation 2 Chair(s): Matthew Flatt

Finding errors in machine learning applications requires a thorough exploration of their behavior over data. Existing approaches used by practitioners are often ad-hoc and lack the abstractions needed to scale this process. We present TorchQL, a programming framework to evaluate and improve the correctness of machine learning applications. TorchQL allows users to write queries to specify and check integrity constraints over machine learning models and datasets. It seamlessly integrates relational algebra with functional programming to allow for highly expressive queries using only eight intuitive operators. We evaluate TorchQL on diverse use-cases including finding critical temporal inconsistencies in objects detected across video frames in autonomous driving, finding data imputation errors in time-series medical records, finding data labeling errors in real-world images, and evaluating biases and constraining outputs of language models. Our experiments show that TorchQL enables up to 13x faster query executions than baselines like Pandas and MongoDB, and up to 40% shorter queries than native Python. We also conduct a user study and find that TorchQL is natural enough for developers familiar with Python to specify complex integrity constraints.

Wed 23 Oct

Displayed time zone: Pacific Time (US & Canada) change

16:00 - 17:40
Performance Analysis and Optimisation 2OOPSLA 2024 at IBR West
Chair(s): Matthew Flatt University of Utah
16:00
20m
Talk
Jmvx: Fast Multi-threaded Multi-Version eXecution and Record-Replay for Managed Languages
OOPSLA 2024
David Schwartz University of Illinois at Chicago, Ankith Kowshik University of Illinois Chicago, Luís Pina University of Illinois at Chicago
DOI
16:20
20m
Talk
libLISA: Instruction Discovery and Analysis on x86-64
OOPSLA 2024
Jos Craaijo Open Universiteit, Freek Verbeek Open Universiteit & Virginia Tech, Binoy Ravindran Virginia Tech
DOI
16:40
20m
Talk
Extending the C/C++ Memory Model with Inline Assembly
OOPSLA 2024
Paulo Emílio de Vilhena Imperial College London, Ori Lahav Tel Aviv University, Viktor Vafeiadis MPI-SWS, Azalea Raad Imperial College London
DOI
17:00
20m
Talk
TorchQL: A Programming Framework for Integrity Constraints in Machine Learning
OOPSLA 2024
Aaditya Naik University of Pennsylvania, Adam Stein University of Pennsylvania, Yinjun Wu University of Pennsylvania, Mayur Naik University of Pennsylvania, Eric Wong
DOI
17:20
20m
Talk
Verification of Neural Networks' Global RobustnessRemote
OOPSLA 2024
Anan Kabaha Technion, Israel Institute of Technology, Dana Drachsler Cohen Technion
DOI