Select a calendar:
Filter March Events by Event Type:
SUNMONTUEWEDTHUFRISAT
Events for March 07, 2019
-
CS Colloquium: Eunsol Choi (University of Washington) - Learning to Understand Entities In Text
Thu, Mar 07, 2019 @ 09:30 AM - 10:30 AM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Eunsol Choi, University of Washington
Talk Title: Learning to Understand Entities In Text
Series: CS Colloquium
Abstract: Real world entities such as people, organizations and countries play a critical role in text. Reading offers rich explicit and implicit information about these entities, such as the categories they belong to, relationships they have with other entities, and events they participate in. In this talk, we introduce approaches to infer implied information about entities, and to automatically query such information in an interactive setting. We expand the scope of information that can be learned from text for a range of tasks, including sentiment extraction, entity typing and question answering. To this end, we introduce new ideas for how to find effective training data, including crowdsourcing and large-scale naturally occurring weak supervision data. We also describe new computational models, that represent rich social and conversation contexts to tackle these tasks. Together, these advances significantly expand the scope of information that can be incorporated into the next generation of machine reading systems.
This lecture satisfies requirements for CSCI 591: Research Colloquium.
Biography: Eunsol Choi is a Ph.D candidate at the Paul G. Allen School of Computer Science at the University of Washington. Her research focuses on natural language processing, specifically applying machine learning to recover semantics from text. She completed a B.A. in Computer Science and Mathematics at Cornell University, and is a recipient of the Facebook fellowship.
Host: Xiang Ren
Location: Ronald Tutor Hall of Engineering (RTH) - 109
Audiences: Everyone Is Invited
Contact: Assistant to CS chair
-
CS Colloquium: Chi Jin (UC Berkeley) Machine Learning: Why Do Simple Algorithms Work So Well?
Thu, Mar 07, 2019 @ 11:00 AM - 12:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Chi Jin, UC Berkely
Talk Title: Machine Learning: Why Do Simple Algorithms Work So Well?
Series: CS Colloquium
Abstract: While state-of-the-art machine learning models are deep, large-scale, sequential and highly nonconvex, the backbone of modern learning algorithms are simple algorithms such as stochastic gradient descent, or Q-learning (in the case of reinforcement learning tasks). A basic question endures---why do simple algorithms work so well even in these challenging settings?
This talk focuses on two fundamental problems: (1) in nonconvex optimization, can gradient descent escape saddle points efficiently? (2) in reinforcement learning, is Q-learning sample efficient? We will provide the first line of provably positive answers to both questions. In particular, we will show that simple modifications to these classical algorithms guarantee significantly better properties, which explains the underlying mechanisms behind their favorable performance in practice.
This lecture satisfies requirements for CSCI 591: Research Colloquium
Biography: Chi Jin is a Ph.D. candidate in Computer Science at UC Berkeley, advised by Michael I. Jordan. He received a B.S. in Physics from Peking University. His research interests lie in machine learning, statistics, and optimization, with his PhD work primarily focused on nonconvex optimization and reinforcement learning.
Host: Haipeng Luo
Location: Olin Hall of Engineering (OHE) - 132
Audiences: Everyone Is Invited
Contact: Assistant to CS chair
-
Individual Grammar Tutorials
Thu, Mar 07, 2019 @ 11:00 AM - 12:00 PM
Viterbi School of Engineering Student Affairs
Workshops & Infosessions
Viterbi graduate and undergraduate students are invited to sign up for individual grammar assistance from professors at the Engineering Writing Program. Sign up for one-on-one individual sessions here: http://bit.ly/grammaratUSC
Questions? Email helenhch@usc.edu
Location: Olin Hall of Engineering (OHE) - 106
Audiences: Graduate and Undergraduate Students
Contact: Helen Choi
-
NL Seminar: Separating the Sheep from the Goats: On Recognizing the Literal and Figurative Usages of Idioms
Thu, Mar 07, 2019 @ 11:00 AM - 12:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Rebecca Hwa, University of Pitt
Talk Title: Separating the Sheep from the Goats: On Recognizing the Literal and Figurative Usages of Idioms
Series: Natural Language Seminar
Abstract: Typically, we think of idioms as colorful expressions whose literal interpretations don't match their underlying meaning. However, many idiomatic expressions can be used either figuratively or literally, depending on their contexts. In this talk, we survey both supervised and unsupervised methods for training a classifier to automatically distinguish usages of idiomatic expressions. We will conclude with a discussion about some potential applications.
Biography: Rebecca Hwa is an Associate Professor in the Department of Computer Science at the University of Pittsburgh. Her recent research focuses on understanding persuasion from a computational linguistics perspective. Some of her recent projects include: modeling student behaviors in revising argumentative essays, identifying symbolisms in visual rhetorics, and understanding idiomatic expressions. Dr Hwa is a recipient of the NSF CAREER Award. Her work has also been supported by NIH and DARPA.
Host: Xusen Yin
More Info: https://nlg.isi.edu/nl-seminar/
Location: Information Science Institute (ISI) - Conf Room #689
Audiences: Everyone Is Invited
Contact: Peter Zamar
Event Link: https://nlg.isi.edu/nl-seminar/
-
ECE Seminar: Information and Incentives in Learning and Decision Making on Networks
Thu, Mar 07, 2019 @ 11:15 AM - 12:15 PM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: Dr. Parinaz Naghizadeh, Postdoctoral Research Associate/ Purdue University and Princeton University Edge Lab
Talk Title: Information and Incentives in Learning and Decision Making on Networks
Abstract: Networks play a central role in determining the outcomes of a variety of socio-technological and economic interactions. Examples include investing in security, sharing of congestible resources, and learning by teams of agents, in network environments. In this talk, I aim to analyze the role of information and incentives in distributed learning and decision making in such problems.
I will first discuss the role of information sharing in a multi-agent (reinforcement) learning problem. We study learning and decision making by agents who have heterogeneous information about their unknown, partially observable environment. We identify two benefits of information sharing between such agents: it facilitates coordination among them, and further enhances the learning rate of both better informed and less informed agents. We show however that these benefits will depend on the communication timing, in that delayed information sharing may be preferred in certain scenarios.
I will then present a framework for characterizing the effects of the network topology on strategic decision making over networks. Specifically, we establish a connection between the equilibrium outcomes of network games with non-linear (resp. linear) best-response functions, and variational inequality (resp. linear complementarity) problems. Through these connections, we outline conditions for existence, uniqueness, and stability of equilibria in these games, extending several existing results in the literature. We further discuss the effects of the network topology on the design of incentive mechanisms in such settings, with applications in improving cybersecurity.
Biography: Parinaz Naghizadeh is a postdoctoral research associate in the Department of Electrical and Computer Engineering at Purdue University and Princeton University Edge Lab. She received her Ph.D. in electrical engineering from the University of Michigan in 2016, M.Sc. degrees in electrical engineering and mathematics, both from the University of Michigan, in 2013 and 2014, respectively, and her B.Sc. in electrical engineering from Sharif University of Technology, Iran, in 2010. Her research interests are in network economics, learning theory, game theory, reinforcement learning, and data analytics. She was a recipient of the Barbour Scholarship in 2014, a finalist for the ProQuest Dissertation Award in 2016, and a Rising Stars in EECS in 2017.
Host: Professor Richard Leahy, leahy@sipi.usc.edu
Location: Hughes Aircraft Electrical Engineering Center (EEB) - EEB 132
Audiences: Everyone Is Invited
Contact: Mayumi Thrasher
-
Internship/Job Search Open Forum
Thu, Mar 07, 2019 @ 04:00 PM - 05:00 PM
Viterbi School of Engineering Career Connections
Workshops & Infosessions
Increase your career and internship knowledge on the job/internship search by attending this professional development Q&A moderated by Viterbi Career Connections staff or Viterbi employer partners.
For more information about Labs & Open Forums, please visit viterbicareers.usc.edu/workshops.
Location: Ronald Tutor Hall of Engineering (RTH) - 211
Audiences: All Viterbi Students
Contact: RTH 218 Viterbi Career Connections
