Algorithmic Stability and Generalization of an Unsupervised Feature Selection Algorithm
–Neural Information Processing Systems
Algorithmic stability is a key characteristic of an algorithm regarding its sensitivity to perturbations of input samples. In this paper, we propose an innovative unsupervised feature selection algorithm attaining this stability with provable guarantees.
Neural Information Processing Systems
Aug-16-2025, 14:22:45 GMT
- Country:
- Asia > Russia (0.04)
- Europe
- Belgium > Flanders
- West Flanders > Bruges (0.04)
- Germany > Bavaria
- Lower Franconia > Würzburg (0.04)
- Ireland > Leinster
- County Dublin > Dublin (0.14)
- Italy > Tuscany
- Florence (0.04)
- Netherlands (0.04)
- Russia > Central Federal District
- Moscow Oblast > Moscow (0.04)
- Spain > Catalonia
- Barcelona Province > Barcelona (0.04)
- United Kingdom > Scotland
- City of Edinburgh > Edinburgh (0.04)
- Belgium > Flanders
- North America
- Canada
- Alberta > Census Division No. 6
- Calgary Metropolitan Region > Calgary (0.04)
- British Columbia (0.04)
- Ontario > Toronto (0.04)
- Quebec > Montreal (0.04)
- Alberta > Census Division No. 6
- United States
- California
- Massachusetts (0.04)
- District of Columbia > Washington (0.04)
- Washington > King County
- Seattle (0.04)
- New Jersey > Mercer County
- Princeton (0.04)
- Oregon > Benton County
- Corvallis (0.04)
- Kentucky > Fayette County
- Lexington (0.14)
- Hawaii > Honolulu County
- Honolulu (0.04)
- Texas (0.04)
- Ohio > Lucas County
- Oregon (0.04)
- Canada
- Oceania > Australia
- New South Wales > Sydney (0.04)
- South America > Chile
- Genre:
- Research Report (0.93)
- Industry:
- Technology: