David Sontag

Probably approximately correct high-dimensional causal effect estimation given a valid adjustment set CLeaR 2025 Benchmarking Observational Studies with Experimental Data under Right-Censoring AISTATS 2024 Learning to Decode Collaboratively with Multiple Language Models ACL 2024 Med-Real2Sim: Non-Invasive Medical Digital Twins using Physics-Informed Self-Supervised Learning NeurIPS 2024 Prediction-powered Generalization of Causal Inferences ICML 2024 Theoretical Analysis of Weak-to-Strong Generalization NeurIPS 2024 Conceptualizing Machine Learning for Dynamic Information Retrieval of Electronic Health Record Notes MLHC 2023 Conformalized Unconditional Quantile Regression AISTATS 2023 Effective Human-AI Teams via Learned Natural Language Rules and Onboarding NeurIPS 2023 Falsification of Internal and External Validity in Observational Studies via Conditional Moment Restrictions AISTATS 2023 TabLLM: Few-shot Classification of Tabular Data with Large Language Models AISTATS 2023 Who Should Predict? Exact Algorithms For Learning to Defer to Humans AISTATS 2023 Clustering Interval-Censored Time-Series for Disease Phenotyping AAAI 2022 Co-training Improves Prompt-based Learning for Large Language Models ICML 2022 ETAB: A Benchmark Suite for Visual Representation Learning in Echocardiography NeurIPS 2022 Evaluating Robustness to Dataset Shift via Parametric Robustness Sets NeurIPS 2022 Falsification before Extrapolation in Causal Effect Estimation NeurIPS 2022 Generalization Bounds and Representation Learning for Estimation of Potential Outcomes and Causal Effects JMLR 2022 Large language models are few-shot clinical information extractors EMNLP 2022 Leveraging Time Irreversibility with Order-Contrastive Pre-training AISTATS 2022 Sample Efficient Learning of Predictors that Complement Humans ICML 2022 Teaching Humans When to Defer to a Classifier via Exemplars AAAI 2022 Training Subset Selection for Weak Supervision NeurIPS 2022 Using time-series privileged information for provably efficient learning of prediction models AISTATS 2022 Beyond Perturbation Stability: LP Recovery Guarantees for MAP Inference on Noisy Stable Instances AISTATS 2021 CLIP: A Dataset for Extracting Action Items for Physicians from Hospital Discharge Notes ACL 2021 Deep Contextual Clinical Prediction with Reverse Distillation AAAI 2021 Directing Human Attention in Event Localization for Clinical Timeline Creation MLHC 2021 Finding Regions of Heterogeneity in Decision-Making via Expected Conditional Covariance NeurIPS 2021 Graph Cuts Always Find a Global Optimum for Potts Models (With a Catch) ICML 2021 Neural Pharmacodynamic State Space Modeling ICML 2021 PClean: Bayesian Data Cleaning at Scale with Domain-Specific Probabilistic Programming AISTATS 2021 Regularizing towards Causal Invariance: Linear Models with Proxies ICML 2021 Characterization of Overlap in Observational Studies AISTATS 2020 Consistent Estimators for Learning to Defer to an Expert ICML 2020 Empirical Study of the Benefits of Overparameterization in Learning Latent Variable Models ICML 2020 Estimation of Bounds on Potential Outcomes For Decision Making ICML 2020 Fast, Structured Clinical Documentation via Contextual Autocomplete MLHC 2020 Knowledge Base Completion for Constructing Problem-Oriented Medical Records MLHC 2020 Robust Benchmarking for Machine Learning of Clinical Entity Extraction MLHC 2020 Block Stability for MAP Inference AISTATS 2019 Counterfactual Off-Policy Evaluation with Gumbel-Max Structural Causal Models ICML 2019 Few-Shot Learning for Dermatological Disease Diagnosis MLHC 2019 Overcomplete Independent Component Analysis via SDP AISTATS 2019 Support and Invertibility in Domain-Invariant Representations AISTATS 2019 Train and Test Tightness of LP Relaxations in Structured Prediction JMLR 2019 Optimality of Approximate Inference Algorithms on Stable Instances AISTATS 2018 Semi-Amortized Variational Autoencoders ICML 2018 Why Is My Classifier Discriminatory? NeurIPS 2018 Causal Effect Inference with Deep Latent-Variable Models NeurIPS 2017 Estimating individual treatment effect: generalization bounds and algorithms ICML 2017 Simultaneous Learning of Trees and Representations for Extreme Classification and Density Estimation ICML 2017 Clinical Tagging with Joint Probabilistic Models MLHC 2016 Identifiable Phenotyping using Constrained Non-Negative Matrix Factorization MLHC 2016 Learning Representations for Counterfactual Inference ICML 2016 Multi-task Prediction of Disease Onsets from Longitudinal Laboratory Tests MLHC 2016 Tightness of LP Relaxations for Almost Balanced Models AISTATS 2016 Train and Test Tightness of LP Relaxations in Structured Prediction ICML 2016 A Fast Variational Approach for Learning Markov Random Field Language Models ICML 2015 Barrier Frank-Wolfe for Marginal Inference NeurIPS 2015 How Hard is Inference for Structured Prediction? ICML 2015 A Practical Algorithm for Topic Modeling with Provable Guarantees ICML 2013 Discovering Hidden Variables in Noisy-Or Networks using Quartet Tests NeurIPS 2013 Complexity of Inference in Latent Dirichlet Allocation NeurIPS 2011 Dual Decomposition for Parsing with Non-Projective Head Automata EMNLP 2010 Learning Bayesian Network Structure using LP Relaxations AISTATS 2010 More data means less inference: A pseudo-max approach to structured learning NeurIPS 2010 On Dual Decomposition and Linear Programming Relaxations for Natural Language Processing EMNLP 2010 Clusters and Coarse Partitions in LP Relaxations NeurIPS 2008 New Outer Bounds on the Marginal Polytope NeurIPS 2007 Tree Block Coordinate Descent for MAP in Graphical Models AISTATS 2005