Statistics Seminar

  • Remote Access Enabled - Zoom
  • Virtual Presentation
  • Assistant Professor
  • Data Sciences and Operations Department, Marshall School of Business
  • University of Southern California

Precise Tradeoffs in Adversarial Training

Despite breakthrough performance, modern learning models are known to be highly vulnerable to small adversarial perturbations in their inputs. While a wide variety of recent adversarial training methods have been effective at improving robustness to perturbed inputs (robust accuracy), often this benefit is accompanied by a decrease in accuracy on benign inputs (standard accuracy), leading to a tradeoff between often competing objectives. Complicating matters further, recent empirical observations suggest that a variety of other factors (size and quality of training data, model size, etc.) affect this tradeoff in somewhat surprising ways. In this talk we will provide a precise and comprehensive understanding of the role of adversarial training in the context of linear regression with Gaussian features and binary classification in a mixture model. We precisely characterize the standard/robust accuracy and the corresponding tradeoff achieved by a contemporary mini-max adversarial training approach in a high-dimensional regime where the number of data points and the parameters of the model grow in proportion to each other. Our theory for adversarial training algorithms also facilitates the rigorous study of how a variety of factors (size and quality of training data, model overparameterization etc.) affect the tradeoff between these two competing accuracies.

Adel Javanmard is an assistant professor in the department of Data Sciences and Operation, Marshall School of Business at the University of Southern California, where he also holds a courtesy appointment with the computer science department. Prior to joining USC in 2015, he was a NSF postdoctoral research fellow at the Center for Science of Information, with worksite at UC Berkeley and Stanford University. He completed his PhD at Stanford University in 2014. His research interests are broadly in the area of high-dimensional statistics, machine learning, optimization, and personalized decision-making. Adel is the recipient of several awards and fellowships, including the IMS Tweedie Researcher award, the NSF CAREER award, Adobe Faculty Research award, Google Faculty Research award, the Thomas Cover dissertation award from the IEEE Society, Douglas Basil Award for Junior Business Faculty, the Zumberge Faculty Research and Innovation award, and the NSF CSoI Postdoctoral Fellowship.

Zoom Participation. See announcement.

For More Information, Please Contact: