← Back to papers
2010 NIPS NeurIPS 2010

Trading off Mistakes and Don't-Know Predictions

Abstract

We discuss an online learning framework in which the agent is allowed to say I don't know'' as well as making incorrect predictions on given examples. We analyze the trade off between sayingI don't know'' and making mistakes. If the number of don't know predictions is forced to be zero, the model reduces to the well-known mistake-bound model introduced by Littlestone [Lit88]. On the other hand, if no mistakes are allowed, the model reduces to KWIK framework introduced by Li et. al. [LLW08]. We propose a general, though inefficient, algorithm for general finite concept classes that minimizes the number of don't-know predictions if a certain number of mistakes are allowed. We then present specific polynomial-time algorithms for the concept classes of monotone disjunctions and linear separators.

📈 Trend Setter — Online Learning
🧭 Keyword Pioneer — don't-know predictions
🐣 Hot Topic Early Bird — online learning
🐝 Cross-Pollinator — Artificial Intelligence, Computer Science, Computer Vision, Data Science & Analytics, Deep Learning, Healthcare & Medicine, Interdisciplinary, Knowledge & Reasoning, Machine Learning, Mathematics & Optimization, Natural Language Processing, Reinforcement Learning, Robotics, Security & Privacy, Speech & Audio
🌉 Interdisciplinary Bridge — Artificial Intelligence and Machine Learning

Authors

Amin Sayedi , Morteza Zadimoghaddam , Avrim Blum

Topics

Machine Learning > Core Methods > Classification Machine Learning > Learning Types > Active Learning Machine Learning > Optimization & Theory > Learning Theory Machine Learning > Learning Types > Online Learning Artificial Intelligence > Core AI > Learning Paradigms

Keywords

online learning classification concept class don't-know predictions monotone disjunctions concept classes mistake bound prediction model linear separator kwik framework
Download PDF

Related papers

Link Discovery using Graph Feature Tracking 2010
A Novel Kernel for Learning a Neuron Model from Spike Train Data 2010
Decomposing Isotonic Regression for Efficiently Solving Large Problems 2010
Learning Kernels with Radiuses of Minimum Enclosing Balls 2010
Switching state space model for simultaneously estimating state transitions and nonstationary firing rates 2010