Learning Reductions that Really Work
| Autor: | Hal Daumé, John Langford, Paul Mineiro, Alina Beygelzimer |
|---|---|
| Rok vydání: | 2015 |
| Předmět: |
FOS: Computer and information sciences
Computer science business.industry Active learning (machine learning) Algorithmic learning theory Stability (learning theory) Online machine learning Multi-task learning Semi-supervised learning Machine learning computer.software_genre Machine Learning (cs.LG) Computer Science - Learning Computational learning theory Artificial intelligence Instance-based learning Electrical and Electronic Engineering business computer |
| DOI: | 10.48550/arxiv.1502.02704 |
| Popis: | In this paper, we provide a summary of the mathematical and computational techniques that have enabled learning reductions to effectively address a wide class of tasks, and show that this approach to solving machine learning problems can be broadly useful. Our work is instantiated and tested in a machine learning library, Vowpal Wabbit, to prove that the techniques discussed here are fully viable in practice. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|