Adaptive scale-invariant online algorithms for learning linear models
arXiv: Learning, 2019.
We consider online learning with linear models, where the algorithm predicts on sequentially revealed instances (feature vectors), and is compared against the best linear function (comparator) in hindsight. Popular algorithms in this framework, such as Online Gradient Descent (OGD), have parameters (learning rates), which ideally should b...More
PPT (Upload PPT)