activity
20172022
most cited"How do I fool you?": Manipulating User Trust via Misleading Black Box Explanations

27 citations · 126 across the 20 of their papers we have counts for

collaborators
Showing cs.LGShow all

14 papers · 1 filter

cs.LG20226 cited

Decision-Aware Learning for Optimizing Health Supply Chains

Tsai-Hsuan Chung, Vahid Rostami, Hamsa Bastani +1

We study the problem of allocating limited supply of medical resources in developing countries, in particular, Sierra Leone. We address this problem by combining machine learning (…

cs.LG2022

Bandits for Online Calibration: An Application to Content Moderation on Social Media Platforms

Vashist Avadhanula, Omar Abdul Baki, Hamsa Bastani +17

We describe the current content moderation strategy employed by Meta to remove policy-violating content from its platforms. Meta relies on both handcrafted and learned risk models…

cs.LG20221 cited

Regret Bounds for Risk-Sensitive Reinforcement Learning

O. Bastani, Y. J. Ma, E. Shen +1

In safety-critical applications of reinforcement learning such as healthcare and robotics, it is often desirable to optimize risk-sensitive objectives that account for tail outcome…

cs.LG2022

Understanding Robust Generalization in Learning Regular Languages

Soham Dan, Osbert Bastani, Dan Roth

A key feature of human intelligence is the ability to generalize beyond the training distribution, for instance, parsing longer sentences than seen in the past. Currently, deep neu…

cs.LG202115 cited

Conservative Offline Distributional Reinforcement Learning

Yecheng Jason Ma, Dinesh Jayaraman, Osbert Bastani

Many reinforcement learning (RL) problems in practice are offline, learning purely from observational data. A key challenge is how to ensure the learned policy is safe, which requi…

cs.LG20205 cited

Robust and Stable Black Box Explanations

Himabindu Lakkaraju, Nino Arsov, Osbert Bastani

As machine learning black boxes are increasingly being deployed in real-world applications, there has been a growing interest in developing post hoc explanations that summarize the…