*********************************
There is now a CONTENT FREEZE for Mercury while we switch to a new platform. It began on Friday, March 10 at 6pm and will end on Wednesday, March 15 at noon. No new content can be created during this time, but all material in the system as of the beginning of the freeze will be migrated to the new platform, including users and groups. Functionally the new site is identical to the old one. webteam@gatech.edu
*********************************
Tess Malone, Communications Officer
Summary Sentence: Rethinking the Role of Optimization in Learning
Full Summary: No summary paragraph submitted.
Suriya GunasekarTITLE: Rethinking the Role of Optimization in Learning
ABSTRACT:
In this talk, I will overview our recent progress towards understanding how we learn large capacity machine learning models, especially deep neural networks. In the modern practice of deep learning, many successful models have far more trainable parameters compared to the number of training examples. Consequently, the optimization objective for training such models have multiple minimizers that perfectly fit the training data. More problematically, while some of these minimizers generalize well to new examples, most minimizers will simply overfit or memorize the training data and will perform poorly on new examples. In practice though, when such ill-posed objectives are minimized using local search algorithms like (stochastic) gradient descent ((S)GD), the “special” minimizers returned by these algorithms have remarkably good performance on new examples. In this talk, we will explore the role optimization algorithms like (S)GD in learning overparameterized models.
BIO:
Suriya Gunasekar is a research assistant professor at the Toyota Technological Institute at Chicago. Prior to joining TTIC, she finished her Ph.D. at the University of Texas at Austin advised by Professor Joydeep Ghosh. Her research interests are broadly driven by statistical, algorithmic, and societal aspects of machine learning including topics of optimization, high dimensional learning, and algorithmic fairness.
