University of Cambridge > Talks.cam > Isaac Newton Institute Seminar Series > Automating stochastic gradient methods with adaptive batch sizes

  Browse A-Z

Log in

University Account External (via Google)

🔐 Log In

Information on

Subscribing to talksdetails Finding a talkdetails Adding a talkdetails Disseminating talksdetails Help and Documentationdetails

ℹī¸ Information

Automating stochastic gradient methods with adaptive batch sizes

Download to your calendar using vCal

If you have a question about this talk, please contact INI IT .

VMVW01 - Variational methods, new optimisation techniques and new fast numerical algorithms

This talk will address several issues related to training neural networks using stochastic gradient methods.  First, we'll talk about the difficulties of training in a distributed environment, and present a new method called centralVR for boosting the scalability of training methods.  Then, we'll talk about the issue of automating stochastic gradient descent, and show that learning rate selection can be simplified using “Big Batch” strategies that adaptively choose minibatch sizes.

This talk is part of the Isaac Newton Institute Seminar Series series.

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

test Webinar - https://zoom.us/j/97224999053?pwd=aitsUFFSQ3dKVlM0MUFVWC83S0E0UT09 Cambridge Enterprise

Other talks

Title to be confirmed Scientific Steering Committee meeting Feedback and the circumgalactic medium Mergers all the way down: simulating the origin of globular clusters in a galactic context Title TBC John Kendrew Lecture - Title TBC
 

Š 2006-2025 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity