No-Regret Learnability for Piecewise Linear Losses.
Arthur FlajoletPatrick JailletPublished in: CoRR (2014)
Keyphrases
- piecewise linear
- regret bounds
- online learning
- lower bound
- chaotic map
- dynamic programming
- boolean functions
- learning algorithm
- loss function
- uniform distribution
- linear regression
- inductive inference
- worst case
- pattern languages
- regression algorithm
- principal curves
- finite sets
- binary classification
- low dimensional
- high resolution
- high dimensional
- multi armed bandit problems