James Koppel — accepted AI-conference papers

2021

A Language for Counterfactual Generative Models

Zenna Tavares, James Koppel, Xin Zhang, Ria Das, Armando Solar-Lezama

ICML 2021spotlight

We present Omega, a probabilistic programming language with support for counterfactual inference. Counterfactual inference means to observe some fact in the present, and infer what would have happened had some past intervention been taken, e.g. “given that medication was not effective at dose x, wha…

Cited by 26 Source ↗PDF ↗code ↗Scholar ↗

2021

A large-scale benchmark for few-shot program induction and synthesis

Ferran Alet, Javier Lopez-Contreras, James Koppel, Maxwell Nye, Armando Solar-Lezama, Tomas Lozano-Perez +2

ICML 2021spotlight

A landmark challenge for AI is to learn flexible, powerful representations from small numbers of examples. On an important class of tasks, hypotheses in the form of programs provide extreme generalization capabilities from surprisingly few examples. However, whereas large natural few-shot learning i…

Cited by 24 Source ↗PDF ↗Scholar ↗