Upcoming Seminars
Shifting attachments to social groups are a constant in the modern era.They are especially pronounced in the contemporary workplace. What accounts for variation in the strength of organizational identification?
I am an epidemiologist with research interests in developing and applying causal inference methods to understand social and contextual influences on mental health, substance use, and violence in disadvantaged, urban areas of the United States.
Previous Seminars
Suppose you observe very few entries from a large matrix. Can we predict the missing entries, say assuming the matrix is (approximately) low rank ? We describe a very simple method to solve this matrix completion problem. We show our method is able to recover matrices from very few entries and/or with ill conditioned matrices, where many other popular methods fail.
Universal dynamic regret is a natural metric for the performance of an online learner in nonstationary environments. The optimal dynamic regret for strongly convex and exponential concave losses, however, had been open for nearly two decades. In this talk, I will cover some recent advances on this problem from my group that largely settled this open problem.
In this talk, recent results on various aspects of the Empirical Risk Minimization (ERM) problem with Relative Entropy Regularization (ERM-RER) are presented. The regularization is with respect to a sigma-finite measure, instead of a probability measure, which provides a larger flexibility for including prior knowledge on the models. Special cases of this general formulation include the ERM problem with (discrete or differential) entropy regularization and the information-risk minimization problem.
The motivation for the seminar is to build a platform to discuss and disseminate the progress made by the community in solving some of the core challenges. We intend to host weekly talks from leading researchers in both academia and industry. Each session will be split into a talk (40 mins) followed by a Q&A + short discussion session (20 mins).
The motivation for the seminar is to build a platform to discuss and disseminate the progress made by the community in solving some of the core challenges. We intend to host weekly talks from leading researchers in both academia and industry. Each session will be split into a talk (40 mins) followed by a Q&A + short discussion session (20 mins).
The motivation for the seminar is to build a platform to discuss and disseminate the progress made by the community in solving some of the core challenges. We intend to host weekly talks from leading researchers in both academia and industry. Each session will be split into a talk (40 mins) followed by a Q&A + short discussion session (20 mins).
The motivation for the seminar is to build a platform to discuss and disseminate the progress made by the community in solving some of the core challenges. We intend to host weekly talks from leading researchers in both academia and industry. Each session will be split into a talk (40 mins) followed by a Q&A + short discussion session (20 mins).
A good learning algorithm is characterized primarily by its ability to predict beyond the training data, i.e., its ability to generalize. What makes a learning algorithm have the ability to generalize? And can we predict when a learning algorithm will generalize well? We believe that a clear answer to these questions is still elusive. In this talk, we will share some perspectives based on our work to understand generalization in deep learning algorithms.
The motivation for the seminar is to build a platform to discuss and disseminate the progress made by the community in solving some of the core challenges. We intend to host weekly talks from leading researchers in both academia and industry. Each session will be split into a talk (40 mins) followed by a Q&A + short discussion session (20 mins).
Many new random matrix ensembles arise in learning and modern signal processing. As shown in recent studies, the spectral properties of these matrices help answer crucial questions regarding the training and generalization performance of neural networks, and the fundamental limits of high-dimensional signal recovery. As a result, there has been growing interest in precisely understanding the spectra and other asymptotic properties of these matrices. Unlike their classical counterparts, these new random matrices are often highly structured and are the result of nonlinear transformations.