Search Results for author: David Sontag

Found 77 papers, 35 papers with code

Conceptualizing Machine Learning for Dynamic Information Retrieval of Electronic Health Record Notes

no code implementations9 Aug 2023 Sharon Jiang, Shannon Shen, Monica Agrawal, Barbara Lam, Nicholas Kurtzman, Steven Horng, David Karger, David Sontag

The large amount of time clinicians spend sifting through patient notes and documenting in electronic health records (EHRs) is a leading cause of clinician burnout.

Information Retrieval Retrieval

Closing the Gap in High-Risk Pregnancy Care Using Machine Learning and Human-AI Collaboration

no code implementations26 May 2023 Hussein Mozannar, Yuria Utsumi, Irene Y. Chen, Stephanie S. Gervasi, Michele Ewing, Aaron Smith-McLallen, David Sontag

We aimed to build machine learning algorithms to identify pregnant patients and triage them by risk of complication to assist care management.


Large-Scale Study of Temporal Shift in Health Insurance Claims

1 code implementation8 May 2023 Christina X Ji, Ahmed M Alaa, David Sontag

Then, we construct a meta-algorithm to perform a retrospective scan for temporal shift on a large collection of tasks.

Beyond Summarization: Designing AI Support for Real-World Expository Writing Tasks

no code implementations5 Apr 2023 Zejiang Shen, Tal August, Pao Siangliulue, Kyle Lo, Jonathan Bragg, Jeff Hammerbacher, Doug Downey, Joseph Chee Chang, David Sontag

In this position paper, we argue that developing AI supports for expository writing has unique and exciting research challenges and can lead to high real-world impacts.

Conformalized Unconditional Quantile Regression

no code implementations4 Apr 2023 Ahmed M. Alaa, Zeshan Hussain, David Sontag

We develop a predictive inference procedure that combines conformal prediction (CP) with unconditional quantile regression (QR) -- a commonly used tool in econometrics that involves regressing the recentered influence function (RIF) of the quantile functional over input covariates.

Conformal Prediction Econometrics +1

Falsification of Internal and External Validity in Observational Studies via Conditional Moment Restrictions

no code implementations30 Jan 2023 Zeshan Hussain, Ming-Chieh Shih, Michael Oberst, Ilker Demirel, David Sontag

Our approach is interpretable, allowing a practitioner to visualize which subgroups in the population lead to falsification of an observational study.

Who Should Predict? Exact Algorithms For Learning to Defer to Humans

1 code implementation15 Jan 2023 Hussein Mozannar, Hunter Lang, Dennis Wei, Prasanna Sattigeri, Subhro Das, David Sontag

We show that prior approaches can fail to find a human-AI system with low misclassification error even when there exists a linear classifier and rejector that have zero error (the realizable setting).

Falsification before Extrapolation in Causal Effect Estimation

1 code implementation27 Sep 2022 Zeshan Hussain, Michael Oberst, Ming-Chieh Shih, David Sontag

Under the assumption that at least one observational estimator is asymptotically normal and consistent for both the validation and extrapolated effects, we provide guarantees on the coverage probability of the intervals output by our algorithm.

Selection bias

Sample Efficient Learning of Predictors that Complement Humans

1 code implementation19 Jul 2022 Mohammad-Amin Charusaie, Hussein Mozannar, David Sontag, Samira Samadi

One of the goals of learning algorithms is to complement and reduce the burden on human decision makers.

Active Learning

Training Subset Selection for Weak Supervision

1 code implementation6 Jun 2022 Hunter Lang, Aravindan Vijayaraghavan, David Sontag

Subset selection applies to any label model and classifier and is very simple to plug in to existing weak supervision pipelines, requiring just a few lines of code.

Evaluating Robustness to Dataset Shift via Parametric Robustness Sets

1 code implementation31 May 2022 Nikolaj Thams, Michael Oberst, David Sontag

We give a method for proactively identifying small, plausible shifts in distribution which lead to large differences in model performance.

Large Language Models are Few-Shot Clinical Information Extractors

no code implementations25 May 2022 Monica Agrawal, Stefan Hegselmann, Hunter Lang, Yoon Kim, David Sontag

A long-running goal of the clinical NLP community is the extraction of important variables trapped in clinical notes.

Benchmarking coreference-resolution +4

Co-training Improves Prompt-based Learning for Large Language Models

no code implementations2 Feb 2022 Hunter Lang, Monica Agrawal, Yoon Kim, David Sontag

We demonstrate that co-training (Blum & Mitchell, 1998) can improve the performance of prompt-based learning by using unlabeled data.

Zero-Shot Learning

Teaching Humans When To Defer to a Classifier via Exemplars

1 code implementation22 Nov 2021 Hussein Mozannar, Arvind Satyanarayan, David Sontag

For this collaboration to perform properly, the human decision maker must have a mental model of when and when not to rely on the agent.

Multi-hop Question Answering Question Answering

Leveraging Time Irreversibility with Order-Contrastive Pre-training

no code implementations4 Nov 2021 Monica Agrawal, Hunter Lang, Michael Offin, Lior Gazit, David Sontag

Label-scarce, high-dimensional domains such as healthcare present a challenge for modern machine learning techniques.

Self-Supervised Learning

Using Time-Series Privileged Information for Provably Efficient Learning of Prediction Models

1 code implementation28 Oct 2021 Rickard K. A. Karlsson, Martin Willbo, Zeshan Hussain, Rahul G. Krishnan, David Sontag, Fredrik D. Johansson

Our question is when using this privileged data leads to more sample-efficient learning of models that use only baseline data for predictions at test time.

Time Series Time Series Analysis

Assessing the Impact of Automated Suggestions on Decision Making: Domain Experts Mediate Model Errors but Take Less Initiative

no code implementations8 Mar 2021 Ariel Levy, Monica Agrawal, Arvind Satyanarayan, David Sontag

Automated decision support can accelerate tedious tasks as users can focus their attention where it is needed most.

Decision Making Human-Computer Interaction

Regularizing towards Causal Invariance: Linear Models with Proxies

1 code implementation3 Mar 2021 Michael Oberst, Nikolaj Thams, Jonas Peters, David Sontag

In the case of two proxy variables, we propose a modified estimator that is prediction optimal under interventions up to a known strength.

Beyond Perturbation Stability: LP Recovery Guarantees for MAP Inference on Noisy Stable Instances

no code implementations26 Feb 2021 Hunter Lang, Aravind Reddy, David Sontag, Aravindan Vijayaraghavan

Several works have shown that perturbation stable instances of the MAP inference problem in Potts models can be solved exactly using a natural linear programming (LP) relaxation.

Neural Pharmacodynamic State Space Modeling

2 code implementations22 Feb 2021 Zeshan Hussain, Rahul G. Krishnan, David Sontag

Modeling the time-series of high-dimensional, longitudinal data is important for predicting patient disease progression.

Time Series Time Series Analysis

Clustering Interval-Censored Time-Series for Disease Phenotyping

no code implementations13 Feb 2021 Irene Y. Chen, Rahul G. Krishnan, David Sontag

In this work, we focus on mitigating the interference of interval censoring in the task of clustering for disease phenotyping.

Clustering Time Series +1

Graph cuts always find a global optimum for Potts models (with a catch)

no code implementations7 Nov 2020 Hunter Lang, David Sontag, Aravindan Vijayaraghavan

On "real-world" instances, MAP assignments of small perturbations of the problem should be very similar to the MAP assignment(s) of the original problem instance.

Robust Benchmarking for Machine Learning of Clinical Entity Extraction

1 code implementation31 Jul 2020 Monica Agrawal, Chloe O'Connell, Yasmin Fatemi, Ariel Levy, David Sontag

We reformulate the annotation framework for clinical entity extraction to factor in these issues to allow for robust end-to-end system benchmarking.

Benchmarking BIG-bench Machine Learning +1

Fast, Structured Clinical Documentation via Contextual Autocomplete

1 code implementation29 Jul 2020 Divya Gopinath, Monica Agrawal, Luke Murray, Steven Horng, David Karger, David Sontag

We present a system that uses a learned autocompletion mechanism to facilitate rapid creation of semi-structured clinical documentation.

PClean: Bayesian Data Cleaning at Scale with Domain-Specific Probabilistic Programming

1 code implementation23 Jul 2020 Alexander K. Lew, Monica Agrawal, David Sontag, Vikash K. Mansinghka

Data cleaning is naturally framed as probabilistic inference in a generative model of ground-truth data and likely errors, but the diversity of real-world error patterns and the hardness of inference make Bayesian approaches difficult to automate.

Probabilistic Programming

Deep Contextual Clinical Prediction with Reverse Distillation

1 code implementation10 Jul 2020 Rohan S. Kodialam, Rebecca Boiarsky, Justin Lim, Neil Dixit, Aditya Sai, David Sontag

Healthcare providers are increasingly using machine learning to predict patient outcomes to make meaningful interventions.

Consistent Estimators for Learning to Defer to an Expert

1 code implementation ICML 2020 Hussein Mozannar, David Sontag

Learning algorithms are often used in conjunction with expert decision makers in practical scenarios, however this fact is largely ignored when designing these algorithms.

Treatment Policy Learning in Multiobjective Settings with Fully Observed Outcomes

1 code implementation1 Jun 2020 Soorajnath Boominathan, Michael Oberst, Helen Zhou, Sanjat Kanjilal, David Sontag

In several medical decision-making problems, such as antibiotic prescription, laboratory testing can provide precise indications for how a patient will respond to different treatment options.

Decision Making

Knowledge Base Completion for Constructing Problem-Oriented Medical Records

1 code implementation27 Apr 2020 James Mullenbach, Jordan Swartz, T. Greg McKelvey, Hui Dai, David Sontag

Both electronic health records and personal health records are typically organized by data type, with medical problems, medications, procedures, and laboratory results chronologically sorted in separate areas of the chart.

Knowledge Base Completion

Generalization Bounds and Representation Learning for Estimation of Potential Outcomes and Causal Effects

no code implementations21 Jan 2020 Fredrik D. Johansson, Uri Shalit, Nathan Kallus, David Sontag

Practitioners in diverse fields such as healthcare, economics and education are eager to apply machine learning to improve decision making.

Decision Making Generalization Bounds +2

Estimation of Bounds on Potential Outcomes For Decision Making

no code implementations ICML 2020 Maggie Makar, Fredrik D. Johansson, John Guttag, David Sontag

Estimation of individual treatment effects is commonly used as the basis for contextual decision making in fields such as healthcare, education, and economics.

Decision Making

Open Set Medical Diagnosis

no code implementations7 Oct 2019 Viraj Prabhu, Anitha Kannan, Geoffrey J. Tso, Namit Katariya, Manish Chablani, David Sontag, Xavier Amatriain

Machine-learned diagnosis models have shown promise as medical aides but are trained under a closed-set assumption, i. e. that models will only encounter conditions on which they have been trained.

Medical Diagnosis Open Set Learning

Robustly Extracting Medical Knowledge from EHRs: A Case Study of Learning a Health Knowledge Graph

no code implementations2 Oct 2019 Irene Y. Chen, Monica Agrawal, Steven Horng, David Sontag

Increasingly large electronic health records (EHRs) provide an opportunity to algorithmically learn medical knowledge.

Benefits of Overparameterization in Single-Layer Latent Variable Generative Models

no code implementations25 Sep 2019 Rares-Darius Buhai, Andrej Risteski, Yoni Halpern, David Sontag

One of the most surprising and exciting discoveries in supervising learning was the benefit of overparameterization (i. e. training a very large model) to improving the optimization landscape of a problem, with minimal effect on statistical performance (i. e. generalization).

Variational Inference

Empirical Study of the Benefits of Overparameterization in Learning Latent Variable Models

1 code implementation ICML 2020 Rares-Darius Buhai, Yoni Halpern, Yoon Kim, Andrej Risteski, David Sontag

One of the most surprising and exciting discoveries in supervised learning was the benefit of overparameterization (i. e. training a very large model) to improving the optimization landscape of a problem, with minimal effect on statistical performance (i. e. generalization).

Variational Inference

Counterfactual Off-Policy Evaluation with Gumbel-Max Structural Causal Models

1 code implementation14 May 2019 Michael Oberst, David Sontag

We introduce an off-policy evaluation procedure for highlighting episodes where applying a reinforcement learned (RL) policy is likely to have produced a substantially different outcome than the observed policy.

Management Off-policy evaluation

Support and Invertibility in Domain-Invariant Representations

no code implementations8 Mar 2019 Fredrik D. Johansson, David Sontag, Rajesh Ranganath

In this work, we give generalization bounds for unsupervised domain adaptation that hold for any representation function by acknowledging the cost of non-invertibility.

Generalization Bounds Unsupervised Domain Adaptation

Overcomplete Independent Component Analysis via SDP

no code implementations24 Jan 2019 Anastasia Podosinnikova, Amelia Perry, Alexander Wein, Francis Bach, Alexandre d'Aspremont, David Sontag

Moreover, we conjecture that the proposed program recovers a mixing component at the rate k < p^2/4 and prove that a mixing component can be recovered with high probability when k < (2 - epsilon) p log p when the original components are sampled uniformly at random on the hyper sphere.

Block Stability for MAP Inference

no code implementations12 Oct 2018 Hunter Lang, David Sontag, Aravindan Vijayaraghavan

The simplest stability condition assumes that the MAP solution does not change at all when some of the pairwise potentials are (adversarially) perturbed.

Why Is My Classifier Discriminatory?

no code implementations NeurIPS 2018 Irene Chen, Fredrik D. Johansson, David Sontag

Recent attempts to achieve fairness in predictive models focus on the balance between fairness and accuracy.


Optimality of Approximate Inference Algorithms on Stable Instances

no code implementations6 Nov 2017 Hunter Lang, David Sontag, Aravindan Vijayaraghavan

Approximate algorithms for structured prediction problems---such as LP relaxations and the popular alpha-expansion algorithm (Boykov et al. 2001)---typically far exceed their theoretical performance guarantees on real-world instances.

Structured Prediction

Causal Effect Inference with Deep Latent-Variable Models

5 code implementations NeurIPS 2017 Christos Louizos, Uri Shalit, Joris Mooij, David Sontag, Richard Zemel, Max Welling

Learning individual-level causal effects from observational data, such as inferring the most effective medication for a specific patient, is a problem of growing importance for policy makers.

Causal Inference

Grounded Recurrent Neural Networks

no code implementations23 May 2017 Ankit Vani, Yacine Jernite, David Sontag

In this work, we present the Grounded Recurrent Neural Network (GRNN), a recurrent neural network architecture for multi-label prediction which explicitly ties labels to specific dimensions of the recurrent hidden state (we call this process "grounding").

Discourse-Based Objectives for Fast Unsupervised Sentence Representation Learning

no code implementations23 Apr 2017 Yacine Jernite, Samuel R. Bowman, David Sontag

This work presents a novel objective function for the unsupervised training of neural network sentence encoders.

Representation Learning

Simultaneous Learning of Trees and Representations for Extreme Classification and Density Estimation

no code implementations ICML 2017 Yacine Jernite, Anna Choromanska, David Sontag

We consider multi-class classification where the predictor has a hierarchical structure that allows for a very large number of labels both at train and test time.

Density Estimation General Classification +4

Structured Inference Networks for Nonlinear State Space Models

3 code implementations30 Sep 2016 Rahul G. Krishnan, Uri Shalit, David Sontag

We introduce a unified algorithm to efficiently learn a broad class of linear and non-linear state space models, including variants where the emission and transition distributions are modeled by deep neural networks.

Multivariate Time Series Forecasting

Multi-task Prediction of Disease Onsets from Longitudinal Lab Tests

1 code implementation2 Aug 2016 Narges Razavian, Jake Marcus, David Sontag

Disparate areas of machine learning have benefited from models that can take raw data with little preprocessing as input and learn rich representations of that raw data in order to perform well on a given prediction task.

Clinical Tagging with Joint Probabilistic Models

no code implementations2 Aug 2016 Yoni Halpern, Steven Horng, David Sontag

We describe a method for parameter estimation in bipartite probabilistic graphical models for joint prediction of clinical conditions from the electronic medical record.

Identifiable Phenotyping using Constrained Non-Negative Matrix Factorization

no code implementations2 Aug 2016 Shalmali Joshi, Suriya Gunasekar, David Sontag, Joydeep Ghosh

This work proposes a new algorithm for automated and simultaneous phenotyping of multiple co-occurring medical conditions, also referred as comorbidities, using clinical notes from the electronic health records (EHRs).

Estimating individual treatment effect: generalization bounds and algorithms

3 code implementations ICML 2017 Uri Shalit, Fredrik D. Johansson, David Sontag

We give a novel, simple and intuitive generalization-error bound showing that the expected ITE estimation error of a representation is bounded by a sum of the standard generalization-error of that representation and the distance between the treated and control distributions induced by the representation.

Causal Inference Generalization Bounds

Learning Representations for Counterfactual Inference

no code implementations12 May 2016 Fredrik D. Johansson, Uri Shalit, David Sontag

Observational studies are rising in importance due to the widespread accumulation of data in fields such as healthcare, education, employment and ecology.

Counterfactual Inference Domain Adaptation +1

Temporal Convolutional Neural Networks for Diagnosis from Lab Tests

1 code implementation25 Nov 2015 Narges Razavian, David Sontag

Early diagnosis of treatable diseases is essential for improving healthcare, and many diseases' onsets are predictable from annual lab tests and their temporal trends.


Deep Kalman Filters

3 code implementations16 Nov 2015 Rahul G. Krishnan, Uri Shalit, David Sontag

Motivated by recent variational methods for learning deep generative models, we introduce a unified algorithm to efficiently learn a broad spectrum of Kalman filters.

Counterfactual Inference Time Series Analysis

Anchored Discrete Factor Analysis

no code implementations10 Nov 2015 Yoni Halpern, Steven Horng, David Sontag

We present a semi-supervised learning algorithm for learning discrete factor analysis models with arbitrary structure on the latent variables.

Medical Diagnosis TAG

Barrier Frank-Wolfe for Marginal Inference

1 code implementation NeurIPS 2015 Rahul G. Krishnan, Simon Lacoste-Julien, David Sontag

We introduce a globally-convergent algorithm for optimizing the tree-reweighted (TRW) variational objective over the marginal polytope.

Variational Inference

Train and Test Tightness of LP Relaxations in Structured Prediction

no code implementations4 Nov 2015 Ofer Meshi, Mehrdad Mahdavi, Adrian Weller, David Sontag

Structured prediction is used in areas such as computer vision and natural language processing to predict structured outputs such as segmentations or parse trees.

Structured Prediction

Character-Aware Neural Language Models

14 code implementations26 Aug 2015 Yoon Kim, Yacine Jernite, David Sontag, Alexander M. Rush

We describe a simple neural language model that relies only on character-level inputs.

Language Modelling

Tight Error Bounds for Structured Prediction

no code implementations19 Sep 2014 Amir Globerson, Tim Roughgarden, David Sontag, Cafer Yildirim

We show that the prospects for achieving low expected Hamming error depend on the structure of the graph $G$ in interesting ways.

Structured Prediction

Lifted Tree-Reweighted Variational Inference

no code implementations17 Jun 2014 Hung Hai Bui, Tuyen N. Huynh, David Sontag

We first show that for these graphical models, the tree-reweighted variational objective lends itself to a compact lifted formulation which can be solved much more efficiently than the standard TRW formulation for the ground graphical model.

Variational Inference

Discovering Hidden Variables in Noisy-Or Networks using Quartet Tests

no code implementations NeurIPS 2013 Yacine Jernite, Yonatan Halpern, David Sontag

We show that the existence of such a quartet allows us to uniquely identify each latent variable and to learn all parameters involving that latent variable.

SparsityBoost: A New Scoring Function for Learning Bayesian Network Structure

no code implementations26 Sep 2013 Eliot Brenner, David Sontag

We give a new consistent scoring function for structure learning of Bayesian networks.

Unsupervised Learning of Noisy-Or Bayesian Networks

no code implementations26 Sep 2013 Yonatan Halpern, David Sontag

This paper considers the problem of learning the parameters in Bayesian networks of discrete variables with known structure and hidden variables.

Medical Diagnosis

A Practical Algorithm for Topic Modeling with Provable Guarantees

2 code implementations19 Dec 2012 Sanjeev Arora, Rong Ge, Yoni Halpern, David Mimno, Ankur Moitra, David Sontag, Yichen Wu, Michael Zhu

Topic models provide a useful method for dimensionality reduction and exploratory data analysis in large text corpora.

Dimensionality Reduction Topic Models

Complexity of Inference in Latent Dirichlet Allocation

no code implementations NeurIPS 2011 David Sontag, Dan Roy

In contrast, we show that, when a document has a large number of topics, finding the MAP assignment of topics to words in LDA is NP-hard.

Clusters and Coarse Partitions in LP Relaxations

no code implementations NeurIPS 2008 David Sontag, Amir Globerson, Tommi S. Jaakkola

We propose a new class of consistency constraints for Linear Programming (LP) relaxations for finding the most probable (MAP) configuration in graphical models.

Protein Design

Cannot find the paper you are looking for? You can Submit a new open access paper.