CIS Colloquium, Nov 05, 2014, 11:00AM - 12:00PM, SERC 306

CIS Colloquium, Nov 05, 2014, 11:00AM - 12:00PM, SERC 306


Deep Boosting


Mehryar Mohri , New York University

Abstract:
This talk discusses a new ensemble learning algorithm, DeepBoost, which can use as a base classifier set deep decision trees, or other rich families. Extensive experiments show that DeepBoost consistently outperforms AdaBoost, Logisic Regression, and their L1 - regularized variants. The key to the success of the algorithm is a capa city - conscious selection criterion for the hypotheses forming the ensemble, which is grounded in a new theoretical foundation with several significant implications. Joint work with Corinna Cortes (Google Research) and Umar Syed (Google Research).

Bio:
Dr. Mehryar Mohri is a Professor of Computer Science and Mathematics at the Courant Institute of Mathematical Sciences, NYU and a Research Consultant at Google (since 2004). Prior to these positions, he served as a Department Head and a Technology Leader at AT&T Labs - Research, earlier AT&T Bell Labs (since 1994), where he worked and supervised research in several areas including text and speech processing, machine learning, and algorithms. He taught for about a year after his Ph.D. at both Ecole Polytechnique and the University of Paris 7 as an Assistant Professor and has held visiting professorship positions at several institutions, including Google Research, Ecole Normale Superieure (ENS Ulm), and Institut des Hautes Etudes Scientifiques (IHES). His research interests cover a number of different areas: machine learning, algorithms and theory, automata theory, speech processing, natural language processing, computational biology, and the design of general - purpose software libraries. He has extensively publishe d conference and journal papers in all of these areas. His research in learning theory and algorithms has been used in a variety of applications. His work on automata theory and algorithms has served as the foundation for several applications in language processing, with several of his algorithms used in virtually all spoken - dialog and speech recognitions systems used in the United States. He has also co - authored several software libraries widely used in research and academic labs. He has contributed to the organization of numerous conferences and workshops, includng as co - chair for COLT 2010. He is on the Editorial or advisory boards of several journals including the Journal of Machine Learning Research, Machine Learning journal, and the Journal of Automata , Languages and Combinatorics. He is a co - author of the machine learning textbook Foundations of Machine Learning used in graduate courses on machine learning in several universities and corporate research laboratories.

© 2001-2013 Center for Data Analytics and Biomedical Informatics, Temple University