Search Results for author:
Found 25 papers, 3 papers with code
FuseMoE: Mixture-of-Experts Transformers for Fleximodal Fusion
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.
Data Augmentations for Improved (Large) Language Model Generalization
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.
JAWS: Auditing Predictive Uncertainty Under Covariate Shift
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.
Beyond Low Earth Orbit: Biological Research, Artificial Intelligence, and Self-Driving Labs
Space biology research aims to understand fundamental effects of spaceflight on organisms, develop foundational knowledge to support deep space exploration, and ultimately bioengineer spacecraft and habitats to stabilize the ecosystem of plants, crops, microbes, animals, and humans for sustained multi-planetary life.
Beyond Low Earth Orbit: Biomonitoring, Artificial Intelligence, and Precision Space Health
Human space exploration beyond low Earth orbit will involve missions of significant distance and duration.
Partial Identifiability in Discrete Data With Measurement Error
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
We consider shifts in user defined conditional distributions, allowing some distributions to shift while keeping other portions of the data distribution fixed.
I-SPEC: An End-to-End Framework for Learning Transportable, Shift-Stable Models
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.
A Unifying Causal Framework for Analyzing Dataset Shift-stable Learning Algorithms
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
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).
Active Learning for Decision-Making from Imbalanced Observational Data
Machine learning can help personalized decision support by learning models to predict individual treatment effects (ITE).
Learning Models from Data with Measurement Error: Tackling Underreporting
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
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.
Preventing Failures Due to Dataset Shift: Learning Predictive Models That Transport
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
Time series data that are not measured at regular intervals are commonly discretized as a preprocessing step.
Counterfactual Normalization: Proactively Addressing Dataset Shift and Improving Reliability Using Causal Mechanisms
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
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.
Treatment-Response Models for Counterfactual Reasoning with Continuous-time, Continuous-valued Interventions
Treatment effects can be estimated from observational data as the difference in potential outcomes.
Reliable Decision Support using Counterfactual Models
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.
A Bayesian Nonparametric Approach for Estimating Individualized Treatment-Response Curves
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.
Trading-Off Cost of Deployment Versus Accuracy in Learning Predictive Models
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.
A Framework for Individualizing Predictions of Disease Trajectories by Exploiting Multi-Resolution Structure
For many complex diseases, there is a wide variety of ways in which an individual can manifest the disease.
High Frequency Remote Monitoring of Parkinson's Disease via Smartphone: Platform Overview and Medication Response Detection
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
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
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.
