On Universal Features for High-Dimensional Learning and Inference
Huang, Shao-Lun, Makur, Anuran, Wornell, Gregory W., Zheng, Lizhong
We consider the problem of identifying universal low-dimensional features from high-dimensional data for inference tasks in settings involving learning. For such problems, we introduce natural notions of universality and we show a local equivalence among them. Our analysis is naturally expressed via information geometry, and represents a conceptually and computationally useful analysis. The development reveals the complementary roles of the singular value decomposition, Hirschfeld-Gebelein-R\'enyi maximal correlation, the canonical correlation and principle component analyses of Hotelling and Pearson, Tishby's information bottleneck, Wyner's common information, Ky Fan $k$-norms, and Brieman and Friedman's alternating conditional expectations algorithm. We further illustrate how this framework facilitates understanding and optimizing aspects of learning systems, including multinomial logistic (softmax) regression and the associated neural network architecture, matrix factorization methods for collaborative filtering and other applications, rank-constrained multivariate linear regression, and forms of semi-supervised learning.
Nov-20-2019
- Country:
- North America
- Canada (0.04)
- United States
- Maryland > Baltimore (0.04)
- Texas > Travis County
- Austin (0.04)
- New Jersey > Hudson County
- Hoboken (0.04)
- Massachusetts
- Middlesex County > Cambridge (0.14)
- Suffolk County > Boston (0.04)
- Hawaii > Honolulu County
- Honolulu (0.04)
- Georgia > Fulton County
- Atlanta (0.04)
- Colorado > Denver County
- Denver (0.04)
- California
- Alameda County > Berkeley (0.04)
- Santa Clara County > San Jose (0.04)
- San Diego County > San Diego (0.04)
- Europe
- Italy (0.04)
- United Kingdom > England
- Cambridgeshire > Cambridge (0.14)
- Greater London > London (0.13)
- Switzerland > Zürich
- Zürich (0.13)
- Netherlands > South Holland
- Dordrecht (0.04)
- Middle East > Republic of Türkiye
- Istanbul Province > Istanbul (0.04)
- Greece > Attica
- Athens (0.04)
- Germany
- Berlin (0.04)
- North Rhine-Westphalia > Cologne Region
- Aachen (0.04)
- France > Île-de-France
- Asia
- Middle East
- Jordan (0.04)
- Republic of Türkiye > Istanbul Province
- Istanbul (0.04)
- Israel
- Tel Aviv District > Tel Aviv (0.04)
- Jerusalem District > Jerusalem (0.04)
- Japan > Honshū
- Kansai > Osaka Prefecture > Osaka (0.04)
- China
- Hong Kong (0.04)
- Guangdong Province
- Middle East
- North America
- Genre:
- Research Report > New Finding (0.45)
- Industry:
- Media > Film (0.45)
- Leisure & Entertainment (0.45)