-
Follow the Leader (FL) and Follow the Perturbed Leader (FPL) in Online Learning
Discover how Follow the Leader (FL) and Follow the Perturbed Leader (FPL) work in online learning, their mathematical foundations, and how perturbations help achieve better stability and regret bounds.
-
Bayesian Conditional Models
Learn how Bayesian conditional models leverage prior knowledge, posterior updates, and predictive distributions to make principled, uncertainty-aware predictions in machine learning.
-
On-line to Batch Conversion
Understanding how online learning algorithms can be used to derive hypotheses with small generalization error in a stochastic setting.
-
Randomized Weighted Majority Algorithm
Learn how the Randomized Weighted Majority (RWM) Algorithm leverages probabilistic prediction to minimize regret and defend against adversarial strategies in online learning environments.
-
Bayesian Decision Theory - Concepts and Recap
A comprehensive guide to Bayesian decision theory, exploring its key components, point estimation, loss functions, and connections to classical probability modeling.