University of Cambridge > Talks.cam > Machine Learning Reading Group @ CUED > Hyperparameter Optimisation

  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

Hyperparameter Optimisation

Download to your calendar using vCal

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

As machine learning models become more complex, so do the spaces of their hyperparameters – those parameters not directly concerned with the model’s adaptability, but rather the design of its training method or architecture. With the exposure of pathological comparability issues in the literature, and the suggestion that many respected contributions see marked improvement under a more systematic configuration selection strategy, hyperparameter optimisation is fast becoming an essential component of the research workflow. In this talk, we will survey the evolution of modern hyperparameter optimisation, from the key elements of fundamental algorithms, such as Bayesian optimisation, to state-of-the-art methods for intelligent and efficient optimisation, such as BOHB . We will also discuss the practicalities of implementing hyperparmeter optimsiation in research projects, including an overview of suitable libraries and off-the-shelf implementations.

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

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

Average on weekdays: 8911.46572581 kWh Webinar & LT2, Computer Laboratory, William Gates Building. Bateman Auditorium, Gonville & Caius College

Other talks

Afternoon Break Title to be confirmed Title to be confirmed Fairy Tales Paediatric Medicine and Rheumatology Title to be confirmed
 

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