Select a calendar:
Filter November Events by Event Type:
SUNMONTUEWEDTHUFRISAT
Events for November 08, 2018
-
MASCLE Machine Learning Seminar: Quanquan Gu (UCLA) - New Variance Reduction Algorithms for Nonconvex Finite-Sum Optimization
Thu, Nov 08, 2018 @ 03:30 PM - 04:50 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Quanquan Gu, UCLA
Talk Title: New Variance Reduction Algorithms for Nonconvex Finite-Sum Optimization
Series: Machine Learning Seminar Series
Abstract: Nonconvex finite-sum optimization problems are ubiquitous in machine learning such as training deep neural networks. To solve this class of problems, various variance reduction based stochastic optimization algorithms have been proposed, which are guaranteed to converge to stationary points and enjoy improved gradient complexity than vanilla stochastic gradient descent. An natural question is whether there is still space for improvement to further speed up the finding of first-order stationary points and even local minimas.
In the first part of this talk, I will introduce our work for finding first-order stationary points in nonconvex finite-sum optimization that further pushes the frontiers of this line of research. In particular, I will introduce a new stochastic nested variance reduced gradient algorithm (SNVRG) that achieves the fastest convergence rate to first-order stationary points in the literature by reducing the variance in stochastic algorithms through multiple referencing points and gradients. It outperforms the folklore variance reduction methods such as stochastic variance reduced gradient (SVRG) and stochastically controlled stochastic gradient (SCSG).
In the second part of the talk, I will talk about methods for finding second-order stationary points (i.e., local minima) in nonconvex finite-sum optimization. Specifically, I will introduce a stochastic variance reduced cubic regularization algorithm that achieves the state-of-the-art second-order oracle complexity for finding local minima in nonconvex optimization.
This lecture satisfies requirements for CSCI 591: Research Colloquium.
Host: Yan Liu, USC Machine Learning Center
Location: Henry Salvatori Computer Science Center (SAL) - 101
Audiences: Everyone Is Invited
Contact: Computer Science Department
-
Cryptoeconomics, Tokenomics, and the Economics of Blockchain
Thu, Nov 08, 2018 @ 06:00 PM - 08:00 PM
Ming Hsieh Department of Electrical and Computer Engineering
Workshops & Infosessions
Course Sessions & Times:
Session 1: Monday, November 5 | 6pm to 8pm
Session 2: Wednesday, November 7 | 6pm to 8pm
Session 3: Thursday, November 8 | 6pm to 8pm
Course Outline:
This mini-course is a collaboration between USC Viterbi Center for Cyber-Physical Systems and the Internet of Things & Prysm Group.
This three-session course provides an introduction to applicable economics for engineers and computer scientists working or interested in the blockchain and distributed ledger space. This course assumes a working knowledge of blockchain technology, but not previous knowledge of economics. By the end of the course, attendees will be able to identify the major economic challenges facing blockchain projects and current solutions.
100% of course fee will be refunded after completion of attending all sessions.
Please RSVP here: https://www.eventbrite.com/e/cryptoeconomics-tokenomics-and-the-economics-of-blockchain-mini-course-tickets-50744539283?aff=erelexpmltMore Information: 19.11.05_Cryptoecomics_MiniWorkshop_flyer.pdf
Location: Hughes Aircraft Electrical Engineering Center (EEB) - 132
Audiences: Everyone Is Invited
Contact: Brienne Moore
