COOKIES: By using this website you agree that we can place Google Analytics Cookies on your device for performance monitoring. |
University of Cambridge > Talks.cam > Machine Learning Reading Group @ CUED > Predicting generalization of ML models.
Predicting generalization of ML models.Add to your list(s) Download to your calendar using vCal
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. Generalization is critical for ML applications. The standard measures of generalization using held-out splits of in-distribution (ID) data, however, tend to overestimate performance in the real-world. Moreover, it is unclear whether in-distribution performance correlates well with generalisation. Evaluating generalisation using performance on a few out-of-distribution (OOD) datasets may also fall short due to selection bias. We will begin with a discussion of large scale experiments that study the behaviour of deep learning models on OOD data. We will then discuss empirically developed generalization measures that map a trained model and training data to test error (in the real-world). These measures depend on model properties such as calibration, spectral complexity, smoothness, sensitivity to augmentations, and performance on in-domain data. We will then conclude with a discussion of theoretical developments on this thread. Required Reading: 1: Assaying Out-Of-Distribution Generalization in Transfer Learning https://arxiv.org/pdf/2207.09239.pdf Summary: A very large scale study of generalization. They study correlation between OOD performance and multiple model properties. They find that ID accuracy is the best predictor of OOD , but some secondary metrics can provide additional insights. Sections to read: Abstract, Introduction 2: Methods and Analysis of The First Competition in Predicting Generalization of Deep Learning http://proceedings.mlr.press/v133/jiang21a/jiang21a.pdf Summary: Introduces NeurIPS 2020 competition and summarizes its top-3 solutions. Contains a good motivation for the problem and big picture. Sections to read: Abstract, Introduction, Section 3 (Solutions) up to 3.1. 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 listsHistory talk about Napoleon III cu palestine societyOther talksSolitary wave fission in dispersive hydrodynamics Plenary Talk: Mode-2 solitary waves in 3-layer flows CHRISTMAS BREAK Non-Hermitian dispersive hydrodynamics Probing matter waves with a dilute-gas Bose-Einstein condensate: new experiments with an atom laser |