.png){kind=icon}
Return
Information theoretic perspective on sample complexity
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neunet.2023.08.032.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
The statistical supervised learning framework assumes an input-output set with a joint probability distribution that is reliably represented by the training dataset. The learning system is then required to output a prediction rule learned from the training dataset's input-output pairs. In this work, we investigate the relationship between the sample complexity, the empirical risk and the generalization error based on the asymptotic equipartition property (AEP) (Shannon, 1948). We provide theoretical guarantees for reliable learning under the information-theoretic AEP, with respect to the generalization error and the sample size in different settings.(c) 2023 Elsevier Ltd. All rights reserved.
Keywords:
Information theory
Supervised learning
Sample complexity
Generalization
Journal
IF:
6.3
Papers:
7.9K
Citations:
3.0W
Organization
Cited Papers
A concise synthesis of (−)-conduritol F from l-quebrachitol via AlCl3-n-Bu4NI mediated demethylation
PREAI
ShareSave
ShareSaveShareSaveResponses of the Roanoke Bayhead Delta to variations in sea level rise and sediment supply during the Holocene and Anthropocene.png)
Anthropocene
AnthropoceneIF0
PREAI
ShareSave no more
no more