Select a calendar:
Filter December Events by Event Type:
Events for December 01, 2022
-
NL Seminar -Prioritized training on points that are learnable, worth learning, and not yet learned
Thu, Dec 01, 2022 @ 11:00 AM - 12:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Sören Mindermann & Jan Brauner, University of Oxford
Talk Title: Prioritized training on points that are learnable, worth learning, and not yet learned
Series: NL Seminar
Abstract: REMINDER
Meeting hosts only admit guests that they know to the Zoom meeting. Hence, you are highly encouraged to use your USC account to sign into Zoom.
If you are an outside visitor, please inform us at nlg DASH seminar DASH host AT isi DOT edu beforehand so we will be aware of your attendance and let you in.
In person attendance will be permitted for USC ISI faculty, staff, students only. Open to the public virtually via the zoom link and online.
Training on web scale data can take months. But much computation and time is wasted on redundant and noisy points that are already learnt or not learnable. To accelerate training, we introduce Reducible Holdout Loss Selection RHO LOSS , a simple but principled technique which selects approximately those points for training that most reduce the models generalization loss.
As a result, RHO LOSS mitigates the weaknesses of existing data selection methods techniques from the optimization literature typically select hard eg high loss points, but such points are often noisy not learnable or less task relevant. Conversely, curriculum learning prioritizes easy points, but such points need not be trained on once learned. In contrast, RHO LOSS selects points that are learnable, worth learning, and not yet learnt. RHO LOSS trains in far fewer steps than prior art, improves accuracy, and speeds up training on a wide range of datasets, hyperparameters, and architectures MLPs, CNNs, and BERT. On the large web scraped image dataset Clothing 1M, RHO LOSS trains in 18 times fewer steps and reaches 2 percent higher final accuracy than uniform data shuffling.
Biography: Bio Soren Mindermann
Soren is a final year PhD student in machine learning at the University of Oxford, supervised by Yarin Gal. My interests in machine learning include how it scales, causal inference and statistical modeling, as well as robustly aligning machine learning models to adopt human wishes and value.
Bio Jan Brauner
Jan is a PhD candidate in the Centre for Doctoral Training on Intelligent and Autonomous Machines and Systems AIMS CDT, supervised by Yarin Gal. His current research interests include AI safety and applications of AI in medicine biomedical research.
Host: Jon May and Meryem M'hamdi
More Info: https://nlg.isi.edu/nl-seminar/
Webcast: https://www.youtube.com/watch?v=uRKrSBRAG0kLocation: Information Science Institute (ISI) - Virtual and ISI-Conf Rm#689
WebCast Link: https://www.youtube.com/watch?v=uRKrSBRAG0k
Audiences: Everyone Is Invited
Contact: Pete Zamar
Event Link: https://nlg.isi.edu/nl-seminar/
-
CEE Seminar Series
Thu, Dec 01, 2022 @ 02:00 PM - 03:00 PM
Sonny Astani Department of Civil and Environmental Engineering
Conferences, Lectures, & Seminars
Speaker: Karen Daniels PhD, North Carolina State University
Talk Title: Looking Inside Granular Materials
Abstract: See attached
Host: Dr Thomas Petersen
More Info: https://usc.zoom.us/j/96591420807
Webcast: https://usc.zoom.us/j/96591420807More Information: Daniels_Announcement.docx
Location: ZOOM
WebCast Link: https://usc.zoom.us/j/96591420807
Audiences: Everyone Is Invited
Contact: Salina Palacios
Event Link: https://usc.zoom.us/j/96591420807
-
Wind Down for Finals with KIUEL
Thu, Dec 01, 2022 @ 05:00 PM - 06:00 PM
USC Viterbi School of Engineering
Conferences, Lectures, & Seminars
Are nerves starting to kick in because of the upcoming finals season? If so, attend KIUEL's Wind Down for Finals and get some advice about how to tackle exams from Viterbi upperclassmen and professors, while enjoying sandwiches and hot chocolate.
Location: Sign into EngageSC to View Location
Audiences:
Contact: Kevin Giang
Event Link: https://engage.usc.edu/viterbi/rsvp?id=387780
