activity
20182021
most citedInterpreting Neural Network Judgments via Minimal, Stable, and Symbolic Corrections

36 citations · 44 across the 5 of their papers we have counts for

collaborators

5 papers

cs.RO2021★ 2 cited

Safe Human-Interactive Control via Shielding

Jeevana Priya Inala, Yecheng Jason Ma, Osbert Bastani +2

Ensuring safety for human-interactive robotics is important due to the potential for human injury. The key challenge is defining safety in a way that accounts for the complex range…

cs.PL2019★ 2 cited

Synthesizing Queries via Interactive Sketching

Osbert Bastani, Xin Zhang, Armando Solar-Lezama

We propose a novel approach to program synthesis, focusing on synthesizing database queries. At a high level, our proposed algorithm takes as input a sketch with soft constraints e…

cs.PL2019★ 3 cited

The Random Conditional Distribution for Higher-Order Probabilistic Inference

Zenna Tavares, Xin Zhang, Edgar Minaysan +3

The need to condition distributional properties such as expectation, variance, and entropy arises in algorithmic fairness, model simplification, robustness and many other areas. At…

cs.AI2018★ 1 cited

Probabilistic Verification of Fairness Properties via Concentration

Osbert Bastani, Xin Zhang, Armando Solar-Lezama

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 sy…

cs.LG2018★ 36 cited

Interpreting Neural Network Judgments via Minimal, Stable, and Symbolic Corrections

Xin Zhang, Armando Solar-Lezama, Rishabh Singh

We present a new algorithm to generate minimal, stable, and symbolic corrections to an input that will cause a neural network with ReLU activations to change its output. We argue t…