Search Results for author: Suchi Saria

Found 26 papers, 4 papers with code

Conformal Validity Guarantees Exist for Any Data Distribution

1 code implementation10 May 2024 Drew Prinster, Samuel Stanton, Anqi Liu, Suchi Saria

As machine learning (ML) gains widespread adoption, practitioners are increasingly seeking means to quantify and control the risk these systems incur.

Active Learning Conformal Prediction

FuseMoE: Mixture-of-Experts Transformers for Fleximodal Fusion

no code implementations5 Feb 2024 Xing Han, Huy Nguyen, Carl Harris, Nhat Ho, Suchi Saria

As machine learning models in critical fields increasingly grapple with multimodal data, they face the dual challenges of handling a wide array of modalities, often incomplete due to missing elements, and the temporal irregularity and sparsity of collected samples.

Missing Elements

Data Augmentations for Improved (Large) Language Model Generalization

no code implementations NeurIPS 2023 Amir Feder, Yoav Wald, Claudia Shi, Suchi Saria, David Blei

The reliance of text classifiers on spurious correlations can lead to poor generalization at deployment, raising concerns about their use in safety-critical domains such as healthcare.

Attribute counterfactual +3

JAWS: Auditing Predictive Uncertainty Under Covariate Shift

1 code implementation21 Jul 2022 Drew Prinster, Anqi Liu, Suchi Saria

We propose \textbf{JAWS}, a series of wrapper methods for distribution-free uncertainty quantification tasks under covariate shift, centered on the core method \textbf{JAW}, the \textbf{JA}ckknife+ \textbf{W}eighted with data-dependent likelihood-ratio weights.

Uncertainty Quantification

Partial Identifiability in Discrete Data With Measurement Error

no code implementations23 Dec 2020 Noam Finkelstein, Roy Adams, Suchi Saria, Ilya Shpitser

When data contains measurement errors, it is necessary to make assumptions relating the observed, erroneous data to the unobserved true phenomena of interest.


Evaluating Model Robustness and Stability to Dataset Shift

no code implementations28 Oct 2020 Adarsh Subbaswamy, Roy Adams, Suchi Saria

We consider shifts in user defined conditional distributions, allowing some distributions to shift while keeping other portions of the data distribution fixed.

BIG-bench Machine Learning

I-SPEC: An End-to-End Framework for Learning Transportable, Shift-Stable Models

no code implementations20 Feb 2020 Adarsh Subbaswamy, Suchi Saria

However, these approaches assume that the data generating process is known in the form of a full causal graph, which is generally not the case.

Mortality Prediction

A Unifying Causal Framework for Analyzing Dataset Shift-stable Learning Algorithms

no code implementations27 May 2019 Adarsh Subbaswamy, Bryant Chen, Suchi Saria

Recent interest in the external validity of prediction models (i. e., the problem of different train and test distributions, known as dataset shift) has produced many methods for finding predictive distributions that are invariant to dataset shifts and can be used for prediction in new, unseen environments.

Tutorial: Safe and Reliable Machine Learning

no code implementations15 Apr 2019 Suchi Saria, Adarsh Subbaswamy

This document serves as a brief overview of the "Safe and Reliable Machine Learning" tutorial given at the 2019 ACM Conference on Fairness, Accountability, and Transparency (FAT* 2019).

BIG-bench Machine Learning Fairness

Active Learning for Decision-Making from Imbalanced Observational Data

1 code implementation10 Apr 2019 Iiris Sundin, Peter Schulam, Eero Siivola, Aki Vehtari, Suchi Saria, Samuel Kaski

Machine learning can help personalized decision support by learning models to predict individual treatment effects (ITE).

Active Learning Decision Making

Learning Models from Data with Measurement Error: Tackling Underreporting

no code implementations25 Jan 2019 Roy Adams, Yuelong Ji, Xiaobin Wang, Suchi Saria

In this paper we present a method for estimating the distribution of an outcome given a binary exposure that is subject to underreporting.

Can You Trust This Prediction? Auditing Pointwise Reliability After Learning

no code implementations2 Jan 2019 Peter Schulam, Suchi Saria

To use machine learning in high stakes applications (e. g. medicine), we need tools for building confidence in the system and evaluating whether it is reliable.

Bayesian Inference

Preventing Failures Due to Dataset Shift: Learning Predictive Models That Transport

no code implementations11 Dec 2018 Adarsh Subbaswamy, Peter Schulam, Suchi Saria

Classical supervised learning produces unreliable models when training and target distributions differ, with most existing solutions requiring samples from the target domain.

Discretizing Logged Interaction Data Biases Learning for Decision-Making

no code implementations6 Oct 2018 Peter Schulam, Suchi Saria

Time series data that are not measured at regular intervals are commonly discretized as a preprocessing step.

Decision Making Time Series +1

Counterfactual Normalization: Proactively Addressing Dataset Shift and Improving Reliability Using Causal Mechanisms

no code implementations9 Aug 2018 Adarsh Subbaswamy, Suchi Saria

Predictive models can fail to generalize from training to deployment environments because of dataset shift, posing a threat to model reliability and the safety of downstream decisions made in practice.


Scalable Joint Models for Reliable Uncertainty-Aware Event Prediction

no code implementations16 Aug 2017 Hossein Soleimani, James Hensman, Suchi Saria

Alternatively, state-of-the-art joint modeling techniques can be used for jointly modeling the longitudinal and event data and compute event probabilities conditioned on the longitudinal observations.

Gaussian Processes Imputation +2

Reliable Decision Support using Counterfactual Models

no code implementations NeurIPS 2017 Peter Schulam, Suchi Saria

The key issue is that supervised learning algorithms are highly sensitive to the policy used to choose actions in the training data, which causes the model to capture relationships that do not generalize.

counterfactual Decision Making

A Bayesian Nonparametric Approach for Estimating Individualized Treatment-Response Curves

no code implementations18 Aug 2016 Yanbo Xu, Yanxun Xu, Suchi Saria

We study the problem of estimating the continuous response over time to interventions using observational time series---a retrospective dataset where the policy by which the data are generated is unknown to the learner.

Decision Making Kidney Function +2

Trading-Off Cost of Deployment Versus Accuracy in Learning Predictive Models

no code implementations20 Apr 2016 Daniel P. Robinson, Suchi Saria

For the challenging real-world application of risk prediction for sepsis in intensive care units, the use of our regularizer leads to models that are in harmony with the underlying cost structure and thus provide an excellent prediction accuracy versus cost tradeoff.

High Frequency Remote Monitoring of Parkinson's Disease via Smartphone: Platform Overview and Medication Response Detection

2 code implementations5 Jan 2016 Andong Zhan, Max A. Little, Denzil A. Harris, Solomon O. Abiola, E. Ray Dorsey, Suchi Saria, Andreas Terzis

Objective: The aim of this study is to develop a smartphone-based high-frequency remote monitoring platform, assess its feasibility for remote monitoring of symptoms in Parkinson's disease, and demonstrate the value of data collected using the platform by detecting dopaminergic medication response.

Computers and Society

Deformable Distributed Multiple Detector Fusion for Multi-Person Tracking

no code implementations18 Dec 2015 Andy J. Ma, Pong C. Yuen, Suchi Saria

For robustness to significant pose variations, deformable spatial relationship between detectors are learnt in our multi-person tracking system.

Learning (Predictive) Risk Scores in the Presence of Censoring due to Interventions

no code implementations27 Jul 2015 Kirill Dyagilev, Suchi Saria

Extending existing ranking algorithms, DSSL learns a function that maps a vector of patient's measurements to a scalar severity score such that the resulting score is temporally smooth and consistent with the expert's ranking of pairs of disease states.

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