Concept

Regret (decision theory)

Related lectures (14)

Covers the Bayes discriminant rule for allocating individuals to populations based on measurements and prior probabilities.

Introduction to Supervised Learning and Decision Theory

Covers supervised learning, decision theory, risk minimization, and goal achievement.

Decision Theory: Risk and Hypothesis Testing

Covers decision theory, risk functions, and hypothesis testing in statistical inference.

Multi-arm Bandits

Covers the exploration vs. exploitation dilemma in multi-arm bandits using the Upper Confidence Bound algorithm.

Decision Theory: Risk and Inference

Explores decision theory, risk functions, and inference in statistical analysis.

Multi-arm Bandits: Exploration vs Exploitation

Explores the balance between exploration and exploitation in multi-arm bandit algorithms.

Statistical Theory: Decision Theory Framework

Explores the Decision Theory Framework in Statistical Theory, viewing statistics as a random game with key concepts like admissibility, minimax rules, and Bayes rules.

Statistical Inference for Bandit Data

Explores statistical inference for bandit data, focusing on personalized treatment actions and challenges of standard estimators.

Maximum Likelihood Estimation

Covers Maximum Likelihood Estimation, focusing on ML Estimation-Distribution, Shrinkage Estimation, and Loss functions.

Statistical Learning: Fundamentals

Introduces the fundamentals of statistical learning, covering supervised learning, decision theory, risk minimization, and overfitting.

Statistical Theory: Cramér-Rao Bound & Hypothesis Testing

Explores the Cramér-Rao bound, hypothesis testing, and optimality in statistical theory.

Optimality in Decision Theory: Unbiased Estimation

Explores optimality in decision theory and unbiased estimation, emphasizing sufficiency, completeness, and lower bounds for risk.

Safe Learning for Autonomous Systems

Explores challenges in control, safety, and coordination for autonomous systems like autonomous cars, focusing on safe learning and Nash equilibria.

Distribution Estimation

Explores distribution estimation, constraints in estimators, and competitive analysis for robust estimation.