van der Schaar Lab

van der Schaar Lab at ICLR 2021: 5 papers and 3 workshops

Note: this post originally appeared on January 13, but was updated and republished on April 30 with details regarding ICLR 2021 poster sessions and workshops.

The van der Schaar Lab’s researchers have had a total of 5 papers accepted to ICLR 2021 (May 4 – 8, 2021). Additionally, Mihaela van der Schaar will be taking part in 3 workshops, one of which will be organized by Ioana Bica, one of the lab’s PhD students.

ICLR is globally renowned for presenting and publishing cutting-edge research on all aspects of deep learning used in the fields of artificial intelligence, statistics and data science.

Collectively, these ICLR 2021 workshops and papers showcase the diverse strengths of the lab’s small research team, and cover a number of its key research pillars, such as understanding clinical decision-making, automated machine learning (autoML), time-series learning, interpretability, and synthetic data generation.

Titles, authors and abstracts for all 5 papers, and details regarding all 3 workshops, are provided below.

Clairvoyance: A Pipeline Toolkit for Medical Time Series

Daniel Jarrett, Jinsung Yoon, Ioana Bica, Zhaozhi Qian, Ari Ercole, Mihaela van der Schaar

Abstract

Learning “What-if” Explanations for Sequential Decision-Making

Ioana Bica, Daniel Jarrett, Alihan Hüyük, Mihaela van der Schaar

Abstract

Explaining by Imitating: Understanding Decisions by Interpretable Policy Learning

Alihan Hüyük, Daniel Jarrett, Cem Tekin, Mihaela van der Schaar

Abstract

Scalable Bayesian Inverse Reinforcement Learning

Alex Chan, Mihaela van der Schaar

Abstract

Generative Time-series Modeling with Fourier Flows

Ahmed Alaa, Alex Chan, Mihaela van der Schaar

Abstract

About ICLR

For a full list of the van der Schaar Lab’s publications, click here.

Nick Maxfield

From 2020 to 2022, Nick oversaw the van der Schaar Lab’s communications, including media relations, content creation, and maintenance of the lab’s online presence.