- All Categories
- Featured Events
- Alumni
- Application Deadline
- Arts
- Campus Discourse
- Careers
- BU Central
- Center for the Humanities
- Charity & Volunteering
- Kilachand Center
- Commencement
- Conferences & Workshops
- Diversity & Inclusion
- Examinations
- Food & Beverage
- Global
- Health & Wellbeing
- Keyword Initiative
- Lectures
- LAW Community
- Meetings
- Orientation
- Other Events
- Religious Services & Activities
- Special Interest to Women
- Sports & Recreation
- Social Events
- Study Abroad
- Weeks of Welcome
- Alternative Visions/Sustainable FuturesAll day
- Grand Business Challenge in Digital HealthAll day
- Register: Business Start-up Boot CampAll day
- Exhibition: The Space in Between6:00 am
- The American Civil War: Treasures from the Vault9:00 am
- Astronomy Dissertation Defense of Christopher B. Mendillo9:00 am
- Improving Your Customer Service Skills9:30 am
- Exhibition: Teaching the Body10:00 am
- The Doors of Perception: Vision and Innovation in Alternative Processes10:00 am
- Exhibition: Simultaneity11:00 am
- Executive MBA Online Information Session Webinar12:00 pm
- ECE Seminar with Daniel Hsu12:00 pm
- Marsh Chapel: Silence Practice12:00 pm
- Marsh Chapel: Common Ground Communion12:20 pm
- Massachusetts Legislative History1:00 pm
- Express Workshop: Preparing for an Interview1:00 pm
- Express Workshop: Inside an Interview 1:30 pm
- Multiple Choice2:00 pm
- Ethics in Science2:00 pm
- ISSO: Interviewing in the USA3:00 pm
- Networking 101 Workshop3:00 pm
- Sargent Choice Night4:00 pm
- Westfield State University Education and Nonprofit Job Fair4:00 pm
- Herold Dehling, Ruhr-University Bochum, Germany4:00 pm
- Coffee and Conversation with Rabbi Beyo4:00 pm
- MacGuffin Series: Once Upon a Time in Anatolia5:00 pm
- Lectures in Criticism: Joseph Roach: New Poetics: Performance Studies and the Research University5:00 pm
- Teaching the Body: The Apotheosis of the Dissected Plate, or Spectacles of Layering and Transparency in 19th- & 20th-Century Anatomy, a Lecture by Dr. Michael Sappol, Historian, National Library of Medicine5:00 pm
- Catholic Vocations in a Time of Change5:00 pm
- Trillium Trading Information Session5:00 pm
- Exhibition: Simultaneity Opening Reception5:30 pm
- Madewell Pop-Up Denim Party5:30 pm
- Silent Film Classics: Victor Sjostrom's "The Wind"6:00 pm
- BU Women's Basketball vs. Sacred Heart6:00 pm
- Beyond These Walls: Religious Leaders' Civic Engagement of Silently-Loud Issues6:00 pm
- Guest Artist Masterclass: Francisco Araiza, tenor6:00 pm
- Crime Pays: Villains & Sleuths in Fact & Fiction6:00 pm
- A Fine "Linea": How Italian Food Advertisements Reflected and Affected Gender Division6:00 pm
- Chocolate Seder6:30 pm
- Women's Basketball at Albany7:00 pm
- Redstone Film Festival West7:30 pm
- Mr. and Ms. BU8:00 pm
- Election Day Presented by Stage Troupe8:00 pm
- Alice in FitRec Land8:00 pm
- Tora Dojo8:00 pm
- NOROUZ CULTURAL SHOW8:30 pm
- Norouz Celebration9:00 pm
ECE Seminar with Daniel Hsu
Fast Learning Algorithms for Discovering the Hidden Structure in DataWith Daniel HsuPostdoctoral ResearcherMicrosoft Research New EnglandFaculty Host: Ioannis PaschalidisRefreshments will be served outside Room 339 at 11:45 a.m.Abstract: A major challenge in machine learning is to reliably and automatically discover hidden structure in data without any human intervention. Examples of such structure found in numerous applications include the stratification of a population into clusters, the thematic structure of document collections, and the dynamical processes governing complex time series. Many of the core statistical estimation problems of these types are, in general, provably intractable for both computational and information-theoretic reasons. However, much progress has been made over the past decade or so to overcome these hardness barriers by focusing on realistic cases that rule out the intractable instances. In this talk, I’ll describe a general computational approach for correctly estimating a wide class of statistical models, including Gaussian mixture models, Hidden Markov models, Latent Dirichlet Allocation, Probabilistic Context Free Grammars, and several more. The key idea is to exploit the structure of low-order correlations that is present in high-dimensional data. The scope of the new approach extends beyond the purview of previous algorithms, and it leads to both new theoretical guarantees for unsupervised learning, as well as fast and practical algorithms for large-scale data analysis.About the Speaker: Daniel Hsu is a postdoc at Microsoft Research New England. Previously, he was a postdoc with the Department of Statistics at Rutgers University and the Department of Statistics at the University of Pennsylvania from 2010 to 2011, supervised by Tong Zhang and Sham M. Kakade. He received his Ph.D. in Computer Science in 2010 from UC San Diego, where he was advised by Sanjoy Dasgupta, and his B.S. in Computer Science and Engineering in 2004 from UC Berkeley. His research interests are in algorithmic statistics and machine learning.
When | 12:00 pm on Thursday, March 21, 2013 |
---|---|
Location | Photonics Center, 8 Saint Mary’s St., Room 339 |