Logo: University of Southern California

Events Calendar



Select a calendar:



Filter October Events by Event Type:



Events for October 14, 2021

  • Drop-In Q&A for Prospective Graduate Students

    Thu, Oct 14, 2021 @ 09:00 AM - 09:30 AM

    Viterbi School of Engineering Graduate Admission

    Workshops & Infosessions


    This webinar is designed for those that have specific questions they want to be answered. Questions will be submitted using the Q&A function and will be answered verbally by a USC Viterbi representative.

    WebCast Link: https://usc.zoom.us/webinar/register/WN_a0cbNz_jQieaByFuoP32WQ

    Audiences: Everyone Is Invited

    Contact: William Schwerin

    OutlookiCal
  • NL Seminar-Chasing the Long Tail. What Neural Networks Memorize and Why

    Thu, Oct 14, 2021 @ 11:00 AM - 12:00 PM

    Information Sciences Institute

    Conferences, Lectures, & Seminars


    Speaker: Vitaly Feldman, Apple AI Research

    Talk Title: Chasing the Long Tail: What Neural Networks Memorize and Why

    Series: NL Seminar

    Abstract: REMINDER: Meeting hosts only admit guests that they know to the Zoom meeting. Hence, you're highly encouraged to use your USC account to sign into Zoom. If you're an outside visitor, please inform nlg DASH seminar DASH host AT isi.edu beforehand so we'll be aware of your attendance and let you in.

    Deep learning algorithms that achieve state of the art results on image and text recognition tasks tend to fit the entire training dataset nearly perfectly including mislabeled examples and outliers. This propensity to memorize seemingly useless data and the resulting large generalization gap have puzzled many practitioners and is not explained by existing theories of machine learning. We provide a simple conceptual explanation and a theoretical model demonstrating that memorization of outliers and mislabeled examples is necessary for achieving close to optimal generalization error when learning from long tailed data distributions. Image and text data are known to follow such distributions and therefore our results establish a formal link between these empirical phenomena. We then demonstrate the utility of memorization and support our explanation empirically. These results rely on a new technique for efficiently estimating memorization and influence of training data points.






    Biography: Vitaly Feldman is a research scientist at Apple AI Research working on foundations of machine learning and privacy preserving data analysis. His recent research interests include tools for analysis of generalization, distributed privacy preserving learning, privacy preserving optimization, and adaptive data analysis.

    Vitaly holds a Ph.D. from Harvard 2006, advised by Leslie Valiant and was previously a research scientist at Google Research Brain Team and IBM Research Almaden. His work was recognized by the COLT Best Student Paper Award in 2005 and 2013 student co authored and by the IBM Research Best Paper Award in 2014, 2015 and 2016. His recent research on foundations of adaptive data analysis has been featured in CACM Research Highlights, Science, and the research blogs of IBM, Google, and Microsoft. He served as a program co chair for COLT 2016 and ALT 2021 conferences and as a co organizer of the Simons Institute Program on Data Privacy in 2019.


    Host: Jon May and Thamme Gowda

    More Info: https://nlg.isi.edu/nl-seminar/

    Webcast: https://youtu.be/_R8JFXvjnPc

    Location: Information Science Institute (ISI) - Virtual Only

    WebCast Link: https://youtu.be/_R8JFXvjnPc

    Audiences: NL Seminar

    Contact: Pete Zamar

    OutlookiCal
  • Lockheed Martin Information Session (Trojan Talk)

    Thu, Oct 14, 2021 @ 11:00 AM - 02:00 PM

    Viterbi School of Engineering Career Connections

    Workshops & Infosessions


    THIS IS AN EXTERNAL EVENT HOSTED BY LOCKHEED MARTIN. RSVP USING VITERBI CAREER GATEWAY.

    Join us for our Lockheed Martin Network of Women Event on Thursday, October 14, 2021 from 12:00pm to 2:00pm (PST) to meet and speak with women working in STEM and Business at Lockheed Martin; women who thrive, lead, and positively impact their communities. Learn about their career paths and goals and the importance of building relationships, identifying strong mentors, and developing a growth mindset while pursuing your professional and personal goals.

    Interested in Job Opportunities?
    https://sjobs.brassring.com/TGNewUI/Search/Home/Home?partnerid=25037&siteid=5066#home

    Lockheed Martin is looking for the best and brightest to help us fulfill our mission of keeping the world secure. We are hosting a Women's Focused Hiring Event, conducting virtual interviews on November 3, 2021.

    You must be a US citizen to be considered for an interview.
    The deadline to apply is October 25, 2021.
    Thank you and we look forward to seeing you at the event! Please let me know if you have any questions.

    For more information, log into Viterbi Career Gateway.

    Location: Virtual (via Zoom)

    Audiences: Everyone Is Invited

    Contact: RTH 218 Viterbi Career Connections

    OutlookiCal
  • Thesis Proposal - Ritesh Ahuja "Differentially Private Model Publishing for Location Services.

    Thu, Oct 14, 2021 @ 01:30 PM - 03:00 PM

    Computer Science

    University Calendar


    Thesis Proposal - Ritesh Ahuja

    "Differentially Private Model Publishing for Location Services."

    Time:1:30-3:00pm PST, Oct 14 (Thursday)

    Committee: Cyrus Shahabi, Aleksandra Korolova, Bhaskar Krishnamachari, Muhammad Naveed, Srivatsan Ravi

    Zoom link: https://usc.zoom.us/j/7125668882

    Abstract:
    Mobile users share their coordinates with service providers (e.g., Google Maps) in exchange for receiving services customized to their location. The service providers analyze the data and publish powerful machine learning models for location search and recommendation. Even though individual location data are not disclosed directly, the model itself retains significant amounts of specific movement details, which in turn may leak sensitive information about an individual. To preserve individual privacy, one must first sanitize location data, which is commonly done using the powerful differential privacy (DP) concept. However, existing solutions fall short of properly capturing skewness inherent to sparse location datasets, and as a result yield poor accuracy

    In this proposal, we first focus on the Spatial Range Count primitive that forms the basis for many important applications such as improving POI placement, or studying disease spread. We propose a neural histogram system (SNH) that models spatial datasets such that important density and correlation features present in the data are preserved, even when DP-compliant noise is added. SNH employs a set of neural networks that learn from diverse regions of the dataset and at varying granularities, leading to superior accuracy. We also devise a framework for effective system parameter tuning on top of public data, which helps practitioners set important system parameters while avoiding privacy leakages.

    Finally, we focus on the next-location recommendation task, which is fundamentally more challenging. Learning user-user correlations from trajectory data requires increasing the dimensionality of intermediate layers in the neural network, and in the context of privacy-preserving learning, it increases data sensitivity, and requires a large amount of noise to be introduced. We briefly show that specific model architectures and data handling processes during DP-compliant training can significantly boost learning accuracy by keeping under tight control the amount of noise required to meet the privacy constraint. We conclude by suggesting ways to learn even richer models that can accurately recommend to a user entire location sequences, as opposed to only the next location.



    WebCast Link: https://usc.zoom.us/j/7125668882

    Audiences: Everyone Is Invited

    Contact: Lizsl De Leon

    OutlookiCal
  • Repeating EventVirtual First-Year Admission Information Session

    Thu, Oct 14, 2021 @ 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

    View All Dates

    Contact: Viterbi Admission

    OutlookiCal
  • Drop-In Q&A for Prospective Graduate Students

    Thu, Oct 14, 2021 @ 04:00 PM - 04:30 PM

    Viterbi School of Engineering Graduate Admission

    Workshops & Infosessions


    This webinar is designed for those that have specific questions they want answered. Questions will be submitted using the Q&A function and will be answered verbally by a USC Viterbi representative.

    WebCast Link: https://usc.zoom.us/webinar/register/WN_MYe4mGEpQGWUDZnivSKgNw

    Audiences: Everyone Is Invited

    Contact: William Schwerin

    OutlookiCal
  • Spotlight: Advanced Design & Construction Technology

    Thu, Oct 14, 2021 @ 05:00 PM - 06:00 PM

    Sonny Astani Department of Civil and Environmental Engineering, Viterbi School of Engineering Graduate Admission

    Workshops & Infosessions


    What does it take to be an innovative leader of the built environment? USC's new Master of Science program in Civil Engineering - Advanced Design & Construction Technology develops professionals to think holistically about design and engineering of sustainable cities, infrastructure, buildings, and systems of the future.

    Learn more in this upcoming information session hosted by Associate Professor and Program Director, Dr. David Gerber. Students who have earned or are in the process of earning a Bachelor's degree in engineering, architecture, computer science, mathematics, or a hard science are welcome to attend.

    Register

    WebCast Link: https://usc.zoom.us/webinar/register/WN__pA_q_qSSDOq0XTyxMvHxA

    Audiences: Everyone Is Invited

    Contact: Jessica Viterbi Admission & Student Engagement

    OutlookiCal
  • Clark Construction Information Session (Trojan Talk)

    Thu, Oct 14, 2021 @ 06:00 PM - 07:00 PM

    Viterbi School of Engineering Career Connections

    Workshops & Infosessions


    Informational session on Clark Construction and opportunities for internships and full-time employment. Students can learn more about the company, the opportunities we have, and ask questions.



    Located IN-PERSON on campus in RTH 211

    Location: Ronald Tutor Hall of Engineering (RTH) - 211

    Audiences: Everyone Is Invited

    Contact: Viterbi Career Connections

    OutlookiCal
  • Clark Construction Information Session (Trojan Talk)

    Thu, Oct 14, 2021 @ 06:00 PM - 07:00 PM

    Viterbi School of Engineering Career Connections

    Workshops & Infosessions


    Learn About a Career with Clark Construction!

    Tuesday October 12th, 6-7 pm
    Location: On-campus, SGM 101

    Join us for this fun an interactive session on Clark Construction! We'll share our opportunities for internships and full-time employment. Students can learn more about the company, the opportunities we have, and ask questions.

    Target majors: Civil & Mechanical Engineering

    RSVP for this on-campus session in Viterbi Career Gateway.
    https://shibboleth-viterbi-usc-csm.symplicity.com/sso/

    Location: Seeley G. Mudd Building (SGM) - 101

    Audiences: Everyone Is Invited

    Contact: RTH 218 Viterbi Career Connections

    OutlookiCal