Osbert Bastani

PAC Confidence Sets for Deep Neural Networks via Calibrated Prediction

2019 · arXiv (Cornell University)

We propose an algorithm combining calibrated prediction and generalization bounds from learning theory to construct confidence sets for deep neural networks with PAC guarantees---i.e., the confidence set for a given input contains the true label …

Program Synthesis Guided Reinforcement Learning

2021 · arXiv (Cornell University)

A key challenge for reinforcement learning is solving long-horizon planning and control problems. Recent work has proposed leveraging programs to help guide the learning algorithm in these settings. However, these approaches impose a high manual …

Counterfactual Explanations for Natural Language Interfaces

2022 · arXiv (Cornell University)

A key challenge facing natural language interfaces is enabling users to understand the capabilities of the underlying system. We propose a novel approach for generating explanations of a natural language interface based on semantic parsing. …

How Far I'll Go: Offline Goal-Conditioned Reinforcement Learning via $f$-Advantage Regression

2022 · arXiv (Cornell University)

Offline goal-conditioned reinforcement learning (GCRL) promises general-purpose skill learning in the form of reaching diverse goals from purely offline datasets. We propose $\textbf{Go}$al-conditioned $f$-$\textbf{A}$dvantage $\textbf{R}$egression (GoFAR), a novel regression-based offline GCRL algorithm derived from a …

Evidence Is All You Need: Ordering Imaging Studies via Language Model Alignment with the ACR Appropriateness Criteria

2024 · arXiv (Cornell University)

Diagnostic imaging studies are an increasingly important component of the workup and management of acutely presenting patients. However, ordering appropriate imaging studies according to evidence-based medical guidelines is a challenging task with a high degree …