159 citations · 798 across the 116 of their papers we have counts for
5 papers · 1 filter
Program Synthesis using Conflict-Driven Learning
Yu Feng, Ruben Martins, Osbert Bastani +1
We propose a new conflict-driven program synthesis technique that is capable of learning from past mistakes. Given a spurious program that violates the desired specification, our s…
Eventually Sound Points-To Analysis with Missing Code
Osbert Bastani, Lazaro Clapp, Saswat Anand +2
Static analyses make the increasingly tenuous assumption that all source code is available for analysis; for example, large libraries often call into native code that cannot be ana…
Active Learning of Points-To Specifications
Osbert Bastani, Rahul Sharma, Alex Aiken +1
When analyzing programs, large libraries pose significant challenges to static points-to analysis. A popular solution is to have a human analyst provide points-to specifications th…
Interpretability via Model Extraction
Osbert Bastani, Carolyn Kim, Hamsa Bastani
The ability to interpret machine learning models has become increasingly important now that machine learning is used to inform consequential decisions. We propose an approach calle…
Interpreting Blackbox Models via Model Extraction
Osbert Bastani, Carolyn Kim, Hamsa Bastani
Interpretability has become incredibly important as machine learning is increasingly used to inform consequential decisions. We propose to construct global explanations of complex,…