Events for October 14, 2016
-
AI Seminar-Matrix Completion, Saddlepoints, and Gradient Descent
Fri, Oct 14, 2016 @ 11:00 AM - 12:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Jason Lee , USC
Talk Title: Matrix Completion, Saddlepoints, and Gradient Descent
Series: Artificial Intelligence Seminar
Abstract: Matrix completion is a fundamental machine learning problem with wide applications in collaborative filtering and recommender systems. Typically, matrix completion are solved by non-convex optimization procedures, which are empirically extremely successful. We prove that the symmetric matrix completion problem has no spurious local minima, meaning all local minima are also global. Thus the matrix completion objective has only saddlepoints an global minima.
Next, we show that saddlepoints are easy to avoid for even Gradient Descent -- arguably the simplest optimization procedure. We prove that with probability 1, randomly initialized Gradient Descent converges to a local minimizer.
Biography: Jason Lee is an assistant professor in Data Sciences and Operations at the University of Southern California. Prior to that, he was a postdoctoral researcher at UC Berkeley working with Michael Jordan. Jason received his PhD at Stanford University advised by Trevor Hastie and Jonathan Taylor. His research interests are in statistics, machine learning, and optimization. Lately, he has worked on high dimensional statistical inference, analysis of non-convex optimization algorithms, and theory for deep learning.
Host: Emilio Ferrara
Location: Information Science Institute (ISI) - 6th Floor -CR # 689; ISI-Marina del Rey
Audiences: Everyone Is Invited
Contact: Peter Zamar
This event is open to all eligible individuals. USC Viterbi operates all of its activities consistent with the University's Notice of Non-Discrimination. Eligibility is not determined based on race, sex, ethnicity, sexual orientation, or any other prohibited factor. -
EMNLP PRACTICE TALK: UNDERSTANDING NEURAL MACHINE TRANSLATION: LENGTH CONTROL AND SYNTACTIC STRUCTURE
Fri, Oct 14, 2016 @ 03:00 PM - 04:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Xing Shi, USC/ISI
Talk Title: EMNLP PRACTICE TALK: UNDERSTANDING NEURAL MACHINE TRANSLATION: LENGTH CONTROL AND SYNTACTIC STRUCTURE
Series: Natural Language Seminar
Abstract: Neural Machine Translation is powerful but we know little about the black box. We conduct the following two investigations to gain a better understanding: First, we investigate how neural, encoder-decoder translation systems output target strings of appropriate lengths, finding that a collection of hidden units learns to explicitly implement this functionality. Second, we investigate whether a neural, encoderdecoder translation system learns syntactic information on the source side as a by-product of training. We propose two methods to detect whether the encoder has learned local and global source syntax. A fine-grained analysis of the syntactic structure learned by the encoder reveals which kinds of syntax are learned and which are missing.
Biography: Xing Shi is a PhD student at ISI working with Prof. Kevin Knight.
Host: Kevin Knight
More Info: http://nlg.isi.edu/nl-seminar/
Location: Information Science Institute (ISI) - 6th Floor -CR # 689; ISI-Marina del Rey
Audiences: Everyone Is Invited
Contact: Peter Zamar
Event Link: http://nlg.isi.edu/nl-seminar/
This event is open to all eligible individuals. USC Viterbi operates all of its activities consistent with the University's Notice of Non-Discrimination. Eligibility is not determined based on race, sex, ethnicity, sexual orientation, or any other prohibited factor.
