Skip to content
conftrace_
2011 COLT COLT 2011

Missing Information Impediments to Learnability

Abstract

To what extent is learnability impeded when information is missing in learning instances? We present relevant known results and concrete open problems, in the context of a natural extension of the PAC learning model that accounts for arbitrarily missing information.

🚀 Conference Pioneer - COLT 2011
📈 Trend Setter - Knowledge Representation
🐣 Hot Topic Early Bird - sample complexity

Authors

Loizos Michael

Topics

Machine Learning > Optimization & Theory > Learning Theory Machine Learning > Learning Types > Online Learning Machine Learning > Learning Types > Supervised Learning Artificial Intelligence > Core AI > Knowledge Representation

Keywords

information theory learning theory online learning sample complexity pac learning missing information feature missing
Download PDF

More from COLT 2011

All COLT 2011 papers →
Identifiability of Priors from Bounded Sample Sizes with Applications to Transfer Learning
Does an Efficient Calibrated Forecasting Strategy Exist?
Bounds on Individual Risk for Log-loss Predictors
A simple multi-armed bandit algorithm with optimal variation-bounded regret
Minimax Algorithm for Learning Rotations
Monotone multi-armed bandit allocations