Select a calendar:
Filter August Events by Event Type:
Events for August 25, 2022
-
New & Continuing MS Student Group Advising Session (CSCI/DSCI)Thu, Aug 25, 2022 @ 10:00 AM - 11:00 AM
Thomas Lord Department of Computer Science
Workshops & Infosessions
If you are a New or Continuing MS student in the Computer Science Department or Data Science Program and have any questions or need assistance, please join us for today's optional group advising session via zoom. Access instructions will be sent to students directly. Note: D-clearance is not granted during advisement sessions. All requests for d-clearance must go through the myViterbi portal.
Location: Zoom
Audiences: Graduate
Contact: USC Computer Science
-
Civil and Environmental Engineering Seminar
Thu, Aug 25, 2022 @ 11:00 AM - 12:00 PM
Sonny Astani Department of Civil and Environmental Engineering
Conferences, Lectures, & Seminars
Speaker: Alberto Guadagnini, Politecnico di Milano
Talk Title: Stochastic assessment of hydrogeological and geochemical variables exhibiting multiscale spatial heterogeneity
Abstract: See attachment
Biography: See attachment
Host: Prof. Felipe de Barros
More Information: Alberto Guadagnini-8-25-22 Speaker.pdf
Location: Ronald Tutor Hall of Engineering (RTH) - 526
Audiences: Everyone Is Invited
Contact: Salina Palacios
-
How the Pandemic Has Changed Healthcare - Seminar Talk Series
Thu, Aug 25, 2022 @ 12:00 PM - 02:00 PM
Daniel J. Epstein Department of Industrial and Systems Engineering
Conferences, Lectures, & Seminars
Speaker: Paul Simon, MD, MPH (Chief Science Officer, Los Angeles County Department of Public Health) *More speakers to be announced, Moderator TBD*
Talk Title: How the Pandemic Changed Public Health
Host: Daniel J. Epstein Dept. of Industrial & Systems Engineering, USC Keck, and USC Price
More Info: Please register at: https://usc.zoom.us/webinar/register/WN_5TAO7KHxRZy26IebQQHcYw
More Information: How the Pandemic Changed Healthcare 8 2022.pdf
Location: Online/Zoom
Audiences: Everyone Is Invited
Contact: Grace Owh
Event Link: Please register at: https://usc.zoom.us/webinar/register/WN_5TAO7KHxRZy26IebQQHcYw
-
PhD Defense - Chi Zhang
Thu, Aug 25, 2022 @ 01:00 PM - 03:00 PM
Thomas Lord Department of Computer Science
University Calendar
PhD Candidate: Chi Zhang
Title: Acceleration of Deep Reinforcement Learning: Efficient Algorithms and Hardware Mapping
zoom meeting ID: 243 580 6897
Committee:
Dr. Viktor Prasanna (chair)
Dr. Aiichiro Nakano (CS department)
Dr. Paul Bogdan (Non-CS department)
Abstract:
Despite the recent success of Deep Reinforcement Learning (DRL) in game playing, robotics manipulation and data center cooling, training DRL agents takes a tremendous amount of time and computation resources. This is because it requires collecting a large amount of data by interacting with the environment and a large amount of policy updates via Stochastic Gradient Descent (SGD) to converge.
To reduce the amount of data to collect, existing work adopts model-based DRL that learns a world model using the data collected by interacting with the environment. Then, it uses the world model to generate synthetic data to perform policy updates. State-of-the-art approaches generate synthetic data by uniformly sampling initial states. This generates a large amount of similar data and makes each policy update less efficient. To accelerate performing policy updates, state-of-the-art hardware mappings of DRL propose efficient customized hardware designs on FPGA. However, most of the work is only applicable for a specific range of input parameters. To further increase the speed to perform policy updates when the input batch size of the neural network is large, existing works split the input batch into multiple sub-batches and adopt multiple learners to process each sub-batch on a learner concurrently. However, the synchronization overhead including data transfer and gradient averaging significantly impairs the scalability of existing approaches.
In this work, we address these limitations by developing efficient algorithms and hardware mappings. First, we propose Maximum Entropy Model Rollouts (MEMR) that generates diverse synthetic data by prioritized sampling of the initial states such that the entropy of the generated synthetic data is maximized. We mathematically derived the maximum entropy sampling criteria assuming that the synthetic data distribution is Gaussian. To accomplish this criteria, we utilize a Prioritized Replay Buffer. Second, we propose a framework for mapping DRL algorithms with a Prioritized Replay Buffer onto heterogeneous platforms consisting of a multi-core CPU, a GPU and a FPGA. We develop specific accelerators for each primitive on CPU, FPGA and GPU. Given a DRL algorithm input parameters, our design space exploration automatically chooses the optimal mapping of various primitives based on an analytical performance model.
Finally, we propose Scalable Policy Optimization (SPO) that improves the scalability of existing multi-learner DRL by reducing the synchronization overhead via local Stochastic Gradient Descent. Our experimental evaluations on widely used benchmark environments suggest i) MEMR reduces the number of policy updates to converge compared with state-of-the-art model-based DRL; ii) our framework for hardware mapping achieves superior policy updates per second compared with other mapping methods; iii) SPO achieves nearly linear scalability as the number of learners increases.
Audiences: Everyone Is Invited
Contact: Lizsl De Leon
-
CS Undergraduate Live Chat Drop-in Advisement
Thu, Aug 25, 2022 @ 01:30 PM - 02:30 PM
Thomas Lord Department of Computer Science
Workshops & Infosessions
CS Advisors will be available on Tuesdays/Wednesdays/Thursdays this fall from 1:30pm to 2:30pm to assist undergraduates in our four majors (CSCI, CSBA, CSGA, and CECS) via Live Chat. Access the live chat through our website at https://cs.usc.edu/chat
Location: Live Chat on Website
Audiences: Undergrad
Contact: USC Computer Science
-
Civil and Environmental Engineering Seminar
Thu, Aug 25, 2022 @ 02:00 PM - 03:00 PM
Sonny Astani Department of Civil and Environmental Engineering
Conferences, Lectures, & Seminars
Speaker: Alberto Guadagnini, Politecnico di Milano
Talk Title: Stochastic assessment of hydrogeological and geochemical variables exhibiting multiscale spatial heterogeneity
Abstract: See attachment
Biography: See attachment
Host: Prof. Felipe de Barros
Location: Ronald Tutor Hall of Engineering (RTH) - 526
Audiences: Everyone Is Invited
Contact: Salina Palacios
-
New & Continuing MS Student Group Advising Session (CSCI/DSCI)
Thu, Aug 25, 2022 @ 03:30 PM - 04:30 PM
Thomas Lord Department of Computer Science
Workshops & Infosessions
If you are a New or Continuing MS student in the Computer Science Department or Data Science Program and have any questions or need assistance, please join us for today's optional group advising session via zoom. Access instructions will be sent to students directly. Note: D-clearance is not granted during advisement sessions. All requests for d-clearance must go through the myViterbi portal.
Location: Zoom
Audiences: Graduate
Contact: USC Computer Science
-
[Virtual] First-Year Admission Information Session
Thu, Aug 25, 2022 @ 04:00 PM - 05:00 PM
Viterbi School of Engineering Undergraduate Admission
Workshops & Infosessions
Our virtual information session is a live presentation from a USC Viterbi admission counselor designed for high school students and their family members to learn more about the USC Viterbi undergraduate experience. Our session will cover an overview of our undergraduate engineering programs, the application process, and more on student life. Guests will be able to ask questions and engage in further discussion toward the end of the session.
Register Here!
Audiences: Everyone Is Invited
Contact: Viterbi Admission
-
Gateway Lab Workshop
Thu, Aug 25, 2022 @ 04:00 PM - 05:00 PM
Viterbi School of Engineering Career Connections
Workshops & Infosessions
THIS EVENT WILL BE HOSTED VIRTUALLY
Take part in a live tutorial to help you navigate Viterbi Career Gateway, a powerful job and internship search tool available ONLY to Viterbi students.
To access the ZOOM link and for more information on this workshop, log into Viterbi Career Gateway>> Events>>Workshops: https://shibboleth-viterbi-usc-csm.symplicity.com/sso/
To access more information on all workshops, please visit viterbicareers.usc.edu/workshops.
Location: ZOOM
Audiences: Everyone Is Invited
Contact: RTH 218 Viterbi Career Connections
