Skip to content
Search events. View events.
 

All Categories

Welcome to the CU-Boulder Events Calendar.

Click for help in using calendar displays. Print the contents of the current screen.

Advanced Search

(New Search)
  From:
  To:



Submit
Event Details
Notify me if this event changes.Add this event to my personal calendar.Email this event to a friend.
Go Back
CS Colloquium: Tianbao Yang (NEC Laboratories America, Inc.)
Start Date: 2/27/2014Start Time: 3:30 PM
End Date: 2/27/2014End Time: 4:30 PM
Event Description:
"Optimization in Machine Learning: Algorithms, Theories and Applications"

Abstract:
The goal of Machine Learning is to learn from data to make intelligent decisions. Most machine learning problems are formulated as optimization problems. Optimization has emerged as a critical step in solving machine learning problems, especially when confronting a huge number of training data and/or high dimensional data. In this talk, I will motivate from several applications arising in machine learning, present the efficient optimization algorithms for obtaining the optimal solution and discuss their theoretical performance. In particular, the talk focuses on addressing three problems: (i) how to efficiently select the best kernel among multiple kernels for learning a kernel predictor; (ii) how to learn a robust classifier in the presence of noise; (iii) how to solve a big data problem in a distributed environment. To address the first problem, an efficient algorithm that combines two state-of-the-art optimization algorithms is proposed, analyzed and demonstrated by experiments for image classification. For solving the second problem, we developed a robust optimization approach and a fast convergent optimization algorithm for solving the associated min-max problem. As a solution to the third problem, I will present a distributed optimization algorithm, analyze its theoretical performance and validate it by empirical studies. I will begin the talk with a brief introduction to machine learning and optimization and end with highlights on other research contributions and the future plan.

Bio:
Tianbao Yang received the Ph.D. degree in Computer Science from Michigan State University in 2012. Dr. Yang is a researcher in NEC Laboratories America, Inc. Before joining NEC Labs, he worked as a machine learning researcher in GE Global Research. Dr. Yang's research interests lie at the intersection of machine learning and optimization. He has focused on several research topics, including social network analysis, robust optimization, online optimization and large-scale optimization in machine learning. He has published over 25 papers in prestigious machine learning conferences and journals. He has won the Mark Fulk Best student paper award at 25th Conference on Learning Theory (COLT) in 2012. Dr. Yang also served as program committee or reviewer for several conferences and journals, including AAAI’12, CIKM’12, CIKM’13, IJCAI’13, ACML’12, NIPS’13, TKDD, TKDE.

Hosted by Bor-Yuh Evan Chang.

Location Information:
Main Campus - Engineering Classroom Wing  (View Map)
1111 Engineering DR
Boulder, CO
Room: 265
Contact Information:
Name: Bor-Yuh Evan Chang
Phone: 303-492-8894
Email: evan.chang@colorado.edu
Tianbao Yang
This event is open to
  • Everyone
  • Of note:
    Free and open to all.
    Light refreshments will be served.

    Calendar Software powered by Dude Solutions   
    Select item(s) to Search
    Select item(s) to Search
    Select item(s) to Search
    Select item(s) to Search

    Featured Events

    Today's Events