Sequential Multi-Dimensional Self-Supervised Learning for Clinical Time Series

no code implementations • 20 Jul 2023 • Aniruddh Raghu, Payal Chandak, Ridwan Alam, John Guttag, Collin M. Stultz

However, most existing SSL methods for clinical time series are limited in that they are designed for unimodal time series, such as a sequence of structured features (e. g., lab values and vitals signs) or an individual high-dimensional physiological signal (e. g., an electrocardiogram).

Self-Supervised Learning Time Series

Data Augmentation for Electrocardiograms

1 code implementation • 9 Apr 2022 • Aniruddh Raghu, Divya Shanmugam, Eugene Pomerantsev, John Guttag, Collin M. Stultz

In experiments, considering three datasets and eight predictive tasks, we find that TaskAug is competitive with or improves on prior work, and the learned policies shed light on what transformations are most effective for different tasks.

Data Augmentation

Meta-Learning to Improve Pre-Training

no code implementations • NeurIPS 2021 • Aniruddh Raghu, Jonathan Lorraine, Simon Kornblith, Matthew McDermott, David Duvenaud

Pre-training (PT) followed by fine-tuning (FT) is an effective method for training neural networks, and has led to significant performance improvements in many domains.

Data Augmentation Hyperparameter Optimization +1

Learning to Predict with Supporting Evidence: Applications to Clinical Risk Prediction

1 code implementation • 4 Mar 2021 • Aniruddh Raghu, John Guttag, Katherine Young, Eugene Pomerantsev, Adrian V. Dalca, Collin M. Stultz

Inference of latent variables in this model corresponds to both making a prediction and providing supporting evidence for that prediction.

Teaching with Commentaries

1 code implementation • ICLR 2021 • Aniruddh Raghu, Maithra Raghu, Simon Kornblith, David Duvenaud, Geoffrey Hinton

We find that commentaries can improve training speed and/or performance, and provide insights about the dataset and training process.

Data Augmentation

Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAML

2 code implementations • ICLR 2020 • Aniruddh Raghu, Maithra Raghu, Samy Bengio, Oriol Vinyals

We conclude with a discussion of the rapid learning vs feature reuse question for meta-learning algorithms more broadly.

Few-Shot Image Classification Few-Shot Learning +1

Model-Based Reinforcement Learning for Sepsis Treatment

no code implementations • 23 Nov 2018 • Aniruddh Raghu, Matthieu Komorowski, Sumeetpal Singh

Sepsis is a dangerous condition that is a leading cause of patient mortality.

Model-based Reinforcement Learning reinforcement-learning +1

Behaviour Policy Estimation in Off-Policy Policy Evaluation: Calibration Matters

no code implementations • 3 Jul 2018 • Aniruddh Raghu, Omer Gottesman, Yao Liu, Matthieu Komorowski, Aldo Faisal, Finale Doshi-Velez, Emma Brunskill

In this work, we consider the problem of estimating a behaviour policy for use in Off-Policy Policy Evaluation (OPE) when the true behaviour policy is unknown.

Representation Balancing MDPs for Off-Policy Policy Evaluation

1 code implementation • NeurIPS 2018 • Yao Liu, Omer Gottesman, Aniruddh Raghu, Matthieu Komorowski, Aldo Faisal, Finale Doshi-Velez, Emma Brunskill

We study the problem of off-policy policy evaluation (OPPE) in RL.

Deep Reinforcement Learning for Sepsis Treatment

2 code implementations • 27 Nov 2017 • Aniruddh Raghu, Matthieu Komorowski, Imran Ahmed, Leo Celi, Peter Szolovits, Marzyeh Ghassemi

Sepsis is a leading cause of mortality in intensive care units and costs hospitals billions annually.

Decision Making reinforcement-learning +1

Continuous State-Space Models for Optimal Sepsis Treatment - a Deep Reinforcement Learning Approach

no code implementations • 23 May 2017 • Aniruddh Raghu, Matthieu Komorowski, Leo Anthony Celi, Peter Szolovits, Marzyeh Ghassemi

In this work, we propose a new approach to deduce optimal treatment policies for septic patients by using continuous state-space models and deep reinforcement learning.

Decision Making Reinforcement Learning (RL)