Boosting Simple Learners
Boosting is a celebrated machine learning approach which is based on the idea of combining weak and moderately inaccurate hypotheses to a strong and accurate one. We study boosting under the assumption that the weak hypotheses belong to a class of bounded capacity. This assumption is inspired by the...
Main Authors: | Noga Alon, Alon Gonen, Elad Hazan, Shay Moran |
---|---|
Format: | Article |
Language: | English |
Published: |
TheoretiCS Foundation e.V.
2023-06-01
|
Series: | TheoretiCS |
Subjects: | |
Online Access: | https://theoretics.episciences.org/9253/pdf |
Similar Items
-
Empirical performance of simple statistical inference-type models with feature extraction in comparison to modern machine learning methods concerning regression and classification problems
by: Dittgen, M
Published: (2019) -
Key questions for the quantum machine learner to ask themselves
by: Nathan Wiebe
Published: (2020-01-01) -
Integrated Sequence Tagging for Medieval Latin Using Deep Representation Learning
by: Mike Kestemont, et al.
Published: (2017-08-01) -
Inference on Markov random fields: methods and applications
by: Lienart, T
Published: (2017) -
Neural networks and statistical learning /
by: Du, Ke-Lin, author, et al.
Published: (2014)