generic

Publications

Here’s my google scholar

Time After Time: Scalable Effect Estimation for Interventions on When and What to do. ICLR 2025. Yoav Wald, Mark Goldstein, Yonathan Efroni, Wouter A.C. van Amsterdam, and Rajesh Ranganath.
Contrasting with Symile: Simple Model-Agnostic Representation Learning for Unlimited Modalities. NeurIPS, 2024. Work by Adriel Saporta*, Aahlad Puli, me, and Rajesh Ranganath.
Scalable Interpolant Transformers. European Conference on Computer Vision (ECCV), 2024. Work by Nanye Willis Ma*, Mark Goldstein, Michael Albergo, Nick Boffi, Eric Vanden-Eijnden, and Saining Xie.
What’s the score? Automated Denoising Score Matching for Nonlinear Diffusions . International Conference on Machine Learning, 2024. Work by Raghav Singhal*, Mark Goldstein*, and Rajesh Ranganath.
Probabilistic Forecasting with Stochastic Interpolants and Föllmer Processes. International Conference on Machine Learning, 2024. Work by Yifan Chen*, Mark Goldstein*, Mengjian Hua*, Michael S. Albergo, Nicholas M. Boffi, and Eric Vanden-Eijnden.
Stochastic interpolants with data-dependent couplings. International Conference on Machine Learning, 2024. Work by Mark Goldstein*, Michael Albergo*, Nick Boffi, Rajesh Ranganath, and Eric Vanden-Eijnden.
A dynamic risk score for early prediction of cardiogenic shock using machine learning. European Heart Journal: Acute Cardiovascular Care, March 2024. Also available on arxiv. Work by Yuxuan Hu*, Mark Goldstein, Rajesh Ranganath, and many others.
QTNet: Predicting Drug-Induced QT Prolongation with Artificial Intelligence-Enabled Electrocardiograms. Journals of the American College of Cardiology, Clinical Electrophysiology. Hao Zhang*, Constantine Tarabanis, Neil Jethani, Mark Goldstein, Silas Smith, Larry A. Chinitz, Rajesh Ranganath, Yindalon Aphinyanaphongs, and Lior Jankelson.
Where to Diffuse, How to Diffuse, and How to Get Back: Automated Learning for Multivariate Diffusions. International Conference on Learning Representations. 2023. Work by Mark Goldstein*, Raghav Singhal*, and Rajesh Ranganath.
Survival Mixture Density Networks. Machine Learning for Healthcare Conference. PMLR, 2022. Work by Xintian Han*, Mark Goldstein, and Rajesh Ranganath.
Learning Invariant Representations with Missing Data (full version). CLeaR (Causal Learning and Reasoning) 2022. Work by Mark Goldstein*, Jörn-Henrik Jacobsen, Olina Chau, Adriel Saporta, Aahlad Puli, Rajesh Ranganath, and Andrew C. Miller. Work done as part of my internship at Apple Health AI.
Learning Invariant Representations with Missing Data. NeurIPS 2021 DistShift Workshop. Work by Mark Goldstein*, Jörn-Henrik Jacobsen, Olina Chau, Adriel Saporta, Aahlad Puli, Rajesh Ranganath, and Andrew C. Miller. Work done as part of my internship at Apple Health AI.
Inverse-Weighted Survival Games. NeurIPS 2021. Work by Mark Goldstein*, Xintian Han*, Aahlad Puli, Thomas Wies, Adler J. Perotte, and Rajesh Ranganath. A new way to estimate survival models by playing games involving both the failure and censoring distribution!
Understanding Failures in Out-of-Distribution Detection with Deep Generative Models. International Conference on Machine Learning, 2021. Work by Lily H. Zhang*, Mark Goldstein, and Rajesh Ranganath.
Understanding Out-of-Distribution Detection with Deep Generative Models. ICLR 2021 RobustML workshop. Work by Lily H. Zhang*, Mark Goldstein, and Rajesh Ranganath.
X-CAL: Explicit Calibration for Survival Analysis. NeurIPS 2020. Work by Mark Goldstein*, Xintian Han*, Aahlad Puli*, Adler J. Perotte, and Rajesh Ranganath.