Research

Distribution Matching

Distribution matching is a tool for trustworthy ML and has the opposite objective of classification.

Localized Learning

Localized learning avoids end-to-end learning by updating model parts via non-global objectives.

Explainable AI

Explaining distribution shifts and prediction uncertainty are important for modern AI systems.

Preprints

Vertical Federated learning (VFL) is a class of FL where each client shares the same sample space but only holds a subset of the …

Selected Publications

In high-stake domains such as healthcare and hiring, the role of machine learning (ML) in decision-making raises significant fairness …

As Diffusion Models have shown promising performance, a lot of efforts have been made to improve the controllability of Diffusion …

There has been a growing excitement that implicit graph generative models could be used to design or discover new molecules for …

Answering counterfactual queries has important applications such as explainability, robustness, and fairness but is challenging when …

While prior federated learning (FL) methods mainly consider client heterogeneity, we focus on the Federated Domain Generalization (DG) …

Distribution matching can be used to learn invariant representations with applications in fairness and robustness. Most prior works …

A distribution shift can have fundamental consequences such as signaling a change in the operating environment or significantly …

Spatial reasoning tasks in multi-agent environments such as event prediction, agent type identification, or missing data imputation are …

A central theme in federated learning (FL) is the fact that client data distributions are often not independent and identically …

Unsupervised distribution alignment estimates a transformation that maps two or more source distributions to a shared aligned …

While normalizing flows for continuous data have been extensively researched, flows for discrete data have only recently been explored. …

The unsupervised task of aligning two or more distributions in a shared latent space has many applications including fair …

Shapley values have become one of the most popular feature attribution explanation methods. However, most prior work has focused on …

While previous distribution shift detection approaches can identify if a shift has occurred, these approaches cannot localize which …

In practical applications of machine learning, it is necessary to look beyond standard metrics such as test accuracy in order to …

We consider objective evaluation measures of explanations of complex black-box machine learning models. We propose simple robust …

We propose a unified framework for deep density models by formally defining density destructors. A density destructor is an invertible …

The Poisson distribution has been widely studied and used for modeling univariate count-valued data. Multivariate generalizations of …

Square Root Graphical Models (SQR), a novel class of parametric graphical models that provides multivariate generalizations of …

We propose a novel distribution that generalizes the Multinomial distribution to enable dependencies between dimensions. Our novel …

We develop a fast algorithm for the Admixture of Poisson MRFs (APM) topic model and propose a novel metric to directly evaluate this …

This paper introduces a new topic model based on an admixture of Poisson Markov Random Fields (APM), which can model dependencies …

Other Publications

Distribution shift can have fundamental consequences such as signaling a change in the operating environment or significantly reducing …

Existing research on label noise often focuses on simple uniform or classconditional noise. However, in many real-world settings, label …

Owing to the sheer volume of text generated by a microblog site like Twitter, it is often difficult to fully understand what is being …

Noise cancellation in an MRI environment is difficult due to the high noise levels that are in the spectral range of human speech. This …

Due to the sheer volume of text generated by a micro log site like Twitter, it is often difficult to fully understand what is being …

Teaching

An introduction to artificial intelligence (AI).

A graduate-level project-based introduction to artificial intelligence (AI) with a primary focus on unsupervised learning. The lecture …

An introduction to artificial intelligence (AI).

A graduate-level project-based introduction to artificial intelligence (AI) with a primary focus on unsupervised learning. The lecture …

A graduate-level project-based introduction to artificial intelligence (AI) with a primary focus on unsupervised learning. The lecture …

This course introduces Python programming to students through data science problems. Students learn Python concepts as well as …

A graduate-level project-based introduction to artificial intelligence (AI) with a primary focus on unsupervised learning. The lecture …

This course introduces Python programming to students through data science problems. Students learn Python concepts as well as …

A graduate-level project-based introduction to artificial intelligence (AI) with a primary focus on unsupervised learning. The lecture …

Contact