Comparing the functional behavior of neural network models, whether it is a single network
over time or two (or more networks) during or post-training, is an essential step in …

We propose a novel semi-supervised learning method to leverage unlabeled data alongside
minimal annotated data and improve medical imaging classification performance in realistic …

This paper investigates fairness and bias in Canonical Correlation Analysis (CCA), a widely
used statistical technique for examining the relationship between two sets of variables. We …

This paper defines fair principal component analysis (PCA) as minimizing the maximum
mean discrepancy (MMD) between the dimensionality-reduced conditional distributions of …

An established normative approach for understanding the algorithmic basis of neural
computation is to derive online algorithms from principled computational objectives and …

Generalized Eigenvalue Problems (GEPs) encompass a range of interesting dimensionality
reduction methods. Development of efficient stochastic approaches to these problems would …

Optimization over the set of matrices that satisfy $ X^\top BX= I_p $, referred to as the
generalized Stiefel manifold, appears in many applications involving sampled covariance …

In this paper, we consider a class of stochastic optimization problems over the expectation-
formulated generalized Stiefel manifold (SOEGS), where the objective function $ f $ is …

The Canonical Correlation Analysis (CCA) family of methods is foundational in multi-view
learning. Regularised linear CCA methods can be seen to generalise Partial Least Squares …

Imagine a world where images of you, data from your smartwatch, and your electronic health
records could seamlessly integrate to paint a comprehensive picture of your health. Now …