Write a Blog >>
SPLASH 2019
Sun 20 - Fri 25 October 2019 Athens, Greece
Wed 23 Oct 2019 14:45 - 15:07 at Attica - Machine Learning Chair(s): Elisa Gonzalez Boix

As machine learning systems are increasingly used to make real world legal and financial decisions, it is of paramount importance that we develop algorithms to verify that these systems do not discriminate against minorities. We design a scalable algorithm for verifying fairness specifications. Our algorithm obtains strong correctness guarantees based on adaptive concentration inequalities; such inequalities enable our algorithm to adaptively take samples until it has enough data to make a decision. We implement our algorithm in a tool called VeriFair, and show that it scales to large machine learning models, including a deep recurrent neural network that is more than five orders of magnitude larger than the largest previously-verified neural network. While our technique only gives probabilistic guarantees due to the use of random samples, we show that we can choose the probability of error to be extremely small.

Wed 23 Oct
Times are displayed in time zone: Beirut change

14:00 - 15:30
Machine LearningOOPSLA at Attica
Chair(s): Elisa Gonzalez BoixVrije Universiteit Brussel, Belgium
14:00
22m
Talk
Duet: An Expressive Higher-Order Language and Linear Type System for Statically Enforcing Differential PrivacyACM SIGPLAN Distinguished Paper Award
OOPSLA
Joseph P. NearUniversity of Vermont, David DaraisUniversity of Vermont, Chike AbuahUniversity of Vermont, Tim StevensUniversity of Vermont, Pranav GaddamaduguUniversity of California, Berkeley, Lun WangUniversity of California, Berkeley, Neel SomaniUniversity of California, Berkeley, Mu ZhangUniversity of Utah, Nikhil SharmaUniversity of California, Berkeley, Alex ShanUniversity of California, Berkeley, Dawn SongUniversity of California, Berkeley
DOI
14:22
22m
Talk
Improving Bug Detection via Context-Based Code Representation Learning and Attention-Based Neural Networks
OOPSLA
Yi LiNew Jersey Institute of Technology, USA, Shaohua WangNew Jersey Institute of Technology, USA, Tien N. NguyenUniversity of Texas at Dallas, Son NguyenThe University of Texas at Dallas
DOI
14:45
22m
Talk
Probabilistic Verification of Fairness Properties via Concentration
OOPSLA
Osbert BastaniUniversity of Pennsylvania, Xin ZhangMassachusetts Institute of Technology, Armando Solar-LezamaMassachusetts Institute of Technology
DOI
15:07
22m
Talk
Generating Precise Error Specifications for C: A Zero Shot Learning Approach
OOPSLA
Baijun WuUniversity of Louisiana at Lafayette, John Peter CamporaUniversity of Louisiana at Lafayette, He YiUniversity of Louisiana at Lafayette, Alexander SchlechtUniversity of Louisiana at Lafayette, Sheng ChenUniversity of Louisiana at Lafayette
DOI