Sontag Lab's repositories
omop-learn
Python package for machine learning for healthcare using a OMOP common data model
sc-foundation-eval
Code for evaluating single cell foundation models scBERT and scGPT
human_ai_deferral
Human-AI Deferral Evaluation Benchmark (Learning to Defer) AISTATS23
cotrain-prompting
Code for co-training large language models (e.g. T0) with smaller ones (e.g. BERT) to boost few-shot performance
ContextualAutocomplete_MLHC2020
Code for Contextual Autocomplete paper published in MLHC2020
learn-to-defer
Code for "Consistent Estimators for Learning to Defer to an Expert" (ICML 2020)
proxy-anchor-regression
Code for ICML 2021 paper "Regularizing towards Causal Invariance: Linear Models with Proxies" (ICML 2021)
teaching-to-understand-ai
Code and webpages for our study on teaching humans to defer to an AI
amr-uti-stm
Code for "A decision algorithm to promote outpatient antimicrobial stewardship for uncomplicated urinary tract infection"
onboarding_human_ai
Onboarding Humans to work with AI: Algorithms to find regions and describe them in natural language that show how humans should collaborate with AI (NeurIPS23)
parametric-robustness-evaluation
Code for paper "Evaluating Robustness to Dataset Shift via Parametric Robustness Sets"
active_learn_to_defer
Code for Sample Efficient Learning of Predictors that Complement Humans (ICML 2022)
large-scale-temporal-shift-study
Code for Large-Scale Study of Temporal Shift in Health Insurance Claims. Christina X Ji, Ahmed M Alaa, David Sontag. CHIL, 2023. https://arxiv.org/abs/2305.05087
finding-decision-heterogeneity-regions
Code for "Finding Regions of Heterogeneity in Decision-Making via Expected Conditional Covariance" at NeurIPS 2021 https://arxiv.org/abs/2110.14508
clinicalml-scBERT-NMI
analysis code to reproduce results in NMI submission
omop-variation
Tools to identify and evaluate heterogeneity in decision-making processes.
oncology_rationale_extraction
Functionality from "Automated NLP extraction of clinical rationale for treatment discontinuation in breast cancer"
rct-obs-extrapolation
Code for paper, "Falsification before Extrapolation in Causal Effect Estimation"
rct-obs-falsification
Code for paper, "Falsification of Internal and External Validity in Observational Studies via Conditional Moment Restrictions." This repo is currently under construction. Check back later for end-to-end notebooks recreating the results of our AISTATS 2023 paper.
SCOPE
Codebase for SCOPE architecture.
wilds
A machine learning benchmark of in-the-wild distribution shifts, with data loaders, evaluators, and default models.