Learning curve prediction for AutoML

Add to your list(s) Download to your calendar using vCal

• Andy Lin
• Wednesday 04 December 2024, 11:00-12:30
• Cambridge University Engineering Department, CBL Seminar room BE4-38..

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

Zoom link available upon request (it is sent out on our mailing list, eng-mlg-rcc [at] lists.cam.ac.uk). Sign up to our mailing list for easier reminders via lists.cam.ac.uk.

Automated machine learning (AutoML) aims to automate the process of selecting hyper-parameters for machine learning models, such as learning rate, batch size, or layer width. To this end, machine learning models are trained with different hyper-parameter configurations, their final performance is recorded, and new candidate configurations are selected via Bayesian optimisation. The latter typically constructs a probabilistic surrogate of final model performances as a function of hyper-parameter configurations. However, individual training runs are usually subject to intermediate evaluations, which produce learning curves in addition to their final performance. These learning curves could be leveraged to 1) save resources by stopping unpromising runs early, and 2) improve the probabilistic surrogate to select better candidate configurations. This reading group will review the literature on building scalable probabilistic surrogate models of such learning curves, discussing approaches using Gaussian processes, power laws, Bayesian neural networks, and Transformers.

This talk is part of the Machine Learning Reading Group @ CUED series.

This talk is included in these lists:

• All Talks (aka the CURE list)
• Cambridge Centre for Data-Driven Discovery (C2D3)
• Cambridge Forum of Science and Humanities
• Cambridge Language Sciences
• Cambridge University Engineering Department Talks
• Cambridge University Engineering Department, CBL Seminar room BE4-38.
• Cambridge talks
• Centre for Smart Infrastructure & Construction
• Chris Davis' list
• Computational Continuum Mechanics Group Seminars
• Featured lists
• Guy Emerson's list
• Hanchen DaDaDash
• Inference Group Journal Clubs
• Inference Group Summary
• Information Engineering Division seminar list
• Interested Talks
• ML
• Machine Learning Reading Group
• Machine Learning Reading Group @ CUED
• Machine Learning Summary
• Quantum Matter Journal Club
• Required lists for MLG
• School of Technology
• Simon Baker's List
• TQS Journal Clubs
• Trust & Technology Initiative - interesting events
• bld31
• custom
• ndk22's list
• ob366-ai4er
• rp587
• yk373's list

Note that ex-directory lists are not shown.