YINS Seminar: “Boosting for Online Convex Optimization”
Speaker: Karan Singh
Microsoft Research
Talk summary: Boosting is a computational framework for compositional learning. There are two traditions to the theory of boosting. First: Classical boosting, arising from theoretical CS, converts weak slightly-better-than-random learners to an accurate one, enhancing the accuracy. Originally designed for the binary classification setting, the literature on boosting was extended to multi-class, multi-label, and ranking-based settings (all examples of linear loss) with specialized constructions in each case. Second: Gradient boosting, on the other hand, aggregates simple (but accurate) learners into a more expressive one; it guarantees competitiveness with the convex hull of the weak hypothesis class. The main contribution of this work is an efficient algorithm that enhances the accuracy and expressivity of the learning process at the same time, while operating on general convex loss (vs. linear for classical boosting) and any convex decision set. This resultant excess risk (average regret) guarantee unifies and delivers on the twin objectives of classical boosting and gradient boosting. The reduction holds for both the (non-stochastic) online and statistical settings, and is amenable to bandit feedback.
Speaker bio: Karan Singh is a postdoctoral researcher at Microsoft Research in Redmond. He received a PhD in Computer Science, under the supervision of Prof. Elad Hazan, from Princeton University in 2021. His research looks at questions in supervised and interactive learning through the lens of optimization. This has, in recent years, shaped into a quest towards an algorithmic (vs. traditionally, analytic) foundation for control theory, for learning in dynamical systems that do not “forget”, and for provably sound mechanisms of compositional learning.
About the Yale Institute for Network Science (YINS): We produce and disseminate knowledge related to network science, in all its forms and applications. Network phenomena are now studied in many disciplines, including engineering, computer science, sociology, economics, political science, biology, physics, medicine, public health, and management. Hence, the study of networks is dramatically transforming scientific fields traversing engineering and the social and natural sciences. One of the major goals for YINS is to expose researchers to the phenomena, measurements, methodologies, and challenges of diverse disciplines. With this goal in mind, we proudly present the YINS Seminar Series, intended to promote the development and application of network science. Speakers include faculty from throughout Yale who are interested in networks, as well as distinguished guest lecturers who are scientists and innovators in the field. Visit us online at http://yins.yale.edu
Информация по комментариям в разработке