Population Risk Improvement with Model Compression: An Information-Theoretic Approach
It has been reported in many recent works on deep model compression that the population risk of a compressed model can be even better than that of the original model. In this paper, an information-theoretic explanation for this population risk improvement phenomenon is provided by jointly studying t...
Main Authors: | Yuheng Bu, Weihao Gao, Shaofeng Zou, Venugopal V. Veeravalli |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-09-01
|
Series: | Entropy |
Subjects: | |
Online Access: | https://www.mdpi.com/1099-4300/23/10/1255 |
Similar Items
-
A New Method for Short Text Compression
by: Murat Aslanyurek, et al.
Published: (2023-01-01) -
Universality of Logarithmic Loss in Fixed-Length Lossy Compression
by: Albert No
Published: (2019-06-01) -
Remote Sensing Image Compression Based on the Multiple Prior Information
by: Chuan Fu, et al.
Published: (2023-04-01) -
A method of storing vector data in compressed form using clustering
by: Nikita A. Tomilov, et al.
Published: (2024-02-01) -
Information-Theoretic Characterization and Undersampling Ratio Determination for Compressive Radar Imaging in a Simulated Environment
by: Jingxiong Zhang, et al.
Published: (2015-07-01)