van der Schaar Lab

Mihaela van der Schaar to give AAAI-22 tutorial and workshop talk

Mihaela van der Schaar and postdoc Fergus Imrie will deliver a tutorial at the Thirty-Sixth AAAI Conference on Artificial Intelligence (AAAI-22). Additionally, Mihaela van der Schaar will give an invited talk at the Workshop on Information-Theoretic Methods for Causal Inference and Discovery (ITCI’22), and one of the lab’s recent papers has been accepted for publication at AAAI-22.

AAAI-22 tutorial

Event details

Title

Time Series in Healthcare: Challenges and Solutions

Abstract

Time series datasets such as electronic health records (EHR) and registries represent valuable (but imperfect) sources of information spanning a patient’s entire lifetime of care. While learning from temporal data is an established field and has been covered in a number of prior tutorials, the healthcare domain raises unique problems and challenges that require new methodologies and ways of thinking.

Perhaps the most common application of time series is forecasting. While we will discuss state-of-the-art approaches for disease forecasting, we will also focus on other important problems in time series, such as time-to-event or survival analysis, personalized monitoring, and treatment effects over time. These topics will be introduced in the context of healthcare, but they have broad applicability to other domains beyond medicine.

In addition, we will explore several characteristics that are necessary to make AI and machine learning models as useful as possible in the clinical setting. We will discuss automated machine learning and we will address the challenges of understanding and explaining machine learning models as well as uncertainty estimation, both of which are critical in high-stakes scenarios such as healthcare.

We will aim for minimal required prerequisite knowledge. However, we will assume basic knowledge of standard machine learning methods (e.g. MLPs, RNNs). While our tutorial will include some detailed explanations of machine learning techniques, significant focus will be placed on the problem areas, their unique challenges, and ways of thinking to overcome these.

Location and local date/time

This event will take place online on February 23, 2022 at 10:45 PST (18:45 GMT).

About the event

The purpose of the AAAI conference is to promote research in artificial intelligence (AI) and scientific exchange among AI researchers, practitioners, scientists, and engineers in affiliated disciplines. AAAI-22 will have a diverse technical track, student abstracts, poster sessions, invited speakers, tutorials, workshops, and exhibit and competition programs, all selected according to the highest reviewing standards. AAAI-22 welcomes submissions on mainstream AI topics as well as novel crosscutting work in related areas.

ITCI’22 invited talk

Event details

Mihaela van der Schaar will deliver an invited talk as part of the AAAI-22 Workshop on Information-Theoretic Methods for Causal Inference and Discovery (ITCI’22).

Title

TBD

Abstract

TBD

Location and local date/time

This event will take place online on March 1.

About the event

The goal of ITCI’22 is to bring together researchers working at the intersection of information theory, causal inference and machine learning in order to foster new collaborations and provide a venue to brainstorm new ideas, exemplify to the information theory community causal inference and discovery as an application area and highlight important technical challenges motivated by practical ML problems, draw the attention of the wider machine learning community to the problems at the intersection of causal inference and information theory, demonstrate to the community the utility of information-theoretic tools to tackle causal ML problems.

AAAI-22 paper

One of the lab’s recent papers has been accepted for publication at AAAI-22; details are provided below.

Inferring Lexicographically-Ordered Rewards from Preferences

Alihan Hüyük, William R. Zame, Mihaela van der Schaar

AAAI-22

Modeling the preferences of agents over a set of alternatives is a principal concern in many areas. The dominant approach has been to find a single reward/utility function with the property that alternatives yielding higher rewards are preferred over alternatives yielding lower rewards. However, in many settings, preferences are based on multiple—often competing—objectives; a single reward function is not adequate to represent such preferences.

This paper proposes a method for inferring multi-objective reward-based representations of an agent’s observed preferences. We model the agent’s priorities over different objectives as entering lexicographically, so that objectives with lower priorities matter only when the agent is indifferent with respect to objectives with higher priorities.

We offer two example applications in healthcare—one inspired by cancer treatment, the other inspired by organ transplantation—to illustrate how the lexicographically-ordered rewards we learn can provide a better understanding of a decision-maker’s preferences and help improve policies when used in reinforcement learning.

The purpose of the AAAI conference is to promote research in artificial intelligence (AI) and scientific exchange among AI researchers, practitioners, scientists, and engineers in affiliated disciplines. AAAI-22 will have a diverse technical track, student abstracts, poster sessions, invited speakers, tutorials, workshops, and exhibit and competition programs, all selected according to the highest reviewing standards. AAAI-22 welcomes submissions on mainstream AI topics as well as novel crosscutting work in related areas.

Source: https://aaai.org/Conferences/AAAI-22/

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.