Online Learning Applications – Politecnico di Milano

Argomenti del programma: 0. Introduction to online learning 0.1. Online learning setting 0.2. Learning with full feedback 0.2.1 Online gradient descent 0.2.2. Adversarial expert problem 0.3. Learning with bandit feedback 0.3.1. Stochastic multi-armed bandits 0.3.2. Adversarial multi-armed bandits 1. Pricing in e-commerce 1.1. Introduction to pricing 1.2. Learning in pricing 1.2.1. Learning with discrete prices 1.2.2.

Argomenti del programma: 0. Introduction to online learning 0.1. Online learning setting 0.2. Learning with full feedback 0.2.1 Online gradient descent 0.2.2. Adversarial expert problem 0.3. Learning with bandit feedback 0.3.1. Stochastic multi-armed bandits 0.3.2. Adversarial multi-armed bandits 1. Pricing in e-commerce 1.1. Introduction to pricing 1.2. Learning in pricing 1.2.1. Learning with discrete prices 1.2.2.

Argomenti del programma: 0. Introduction to online learning 0.1. Online learning setting 0.2. Learning with full feedback 0.2.1 Online gradient descent 0.2.2. Adversarial expert problem 0.3. Learning with bandit feedback 0.3.1. Stochastic multi-armed bandits 0.3.2. Adversarial multi-armed bandits 1. Pricing in e-commerce 1.1. Introduction to pricing 1.2. Learning in pricing 1.2.1. Learning with discrete prices 1.2.2.

Argomenti del programma: 0. Introduction to online learning 0.1. Online learning setting 0.2. Learning with full feedback 0.2.1 Online gradient descent 0.2.2. Adversarial expert problem 0.3. Learning with bandit feedback 0.3.1. Stochastic multi-armed bandits 0.3.2. Adversarial multi-armed bandits 1. Pricing in e-commerce 1.1. Introduction to pricing 1.2. Learning in pricing 1.2.1. Learning with discrete prices 1.2.2.