Lectures related to Controlled Stochastic Processes

Diffusion Models

Explores diffusion models, focusing on generating samples from a distribution and the importance of denoising in the process.

Markov Decision Processes: Foundations of Reinforcement Learning

Covers Markov Decision Processes, their structure, and their role in reinforcement learning.

Approximation Algorithms

Covers approximation algorithms for optimization problems, LP relaxation, and randomized rounding techniques.

Generalization Error

Explores generalization error in machine learning, focusing on data distribution and hypothesis impact.

Set Cover: Integrality Gap

Explores the integrality gap concept in set cover and multiplicative weights algorithms.

Optimization Methods: Theory Discussion

Explores optimization methods, including unconstrained problems, linear programming, and heuristic approaches.

Value Iteration Acceleration: PID and Operator Splitting

Explores accelerating the Value Iteration algorithm using control theory and matrix splitting techniques to achieve faster convergence.

Infinite-Horizon LQ Control: Solution & Example

Explores Infinite-Horizon Linear Quadratic (LQ) optimal control, emphasizing solution methods and practical examples.

Deep Learning Modus Operandi

Explores the benefits of deeper networks in deep learning and the importance of over-parameterization and generalization.

Markov Chains: Transition Probabilities

Explores Markov chains, transition matrices, distribution, and random walks.

Continuous Random Variables: Basic Ideas

Explores continuous random variables and their properties, including support and cumulative distribution functions.

Orchestration Graph Concepts

Explains the use of operators for transferring data between activities in an orchestration graph.

Energy System Optimization

Explores energy system optimization, including heat, cost, and CO2 emissions.

Convergence of Random Variables

Explores the convergence of random variables, the law of large numbers, and the distribution of failure time.

Supervised Learning with kNN: Regression Model

Covers a simple mathematical model for supervised learning with k-nearest neighbors in regression.

Regulation of Therapeutic Products

Explores the regulation of therapeutic products, covering legal requirements, product classification, market access, and advertising rules.

Linear Quadratic (LQ) Optimal Control: Proof of Theorem

Covers the proof of the recursive formula for the optimal gains in LQ control over a finite horizon.

Dynamic Programming: Optimal Control Log in to Mediaspace to watch this video

Explores Dynamic Programming for optimal control, focusing on stability, stationary policy, and recursive solutions.

Introduction to Reinforcement Learning: Key Concepts and Applications Log in to Mediaspace to watch this video

Introduces reinforcement learning, covering its definitions, applications, and theoretical foundations, while outlining the course structure and objectives.

Optimal Transport: Kantorovich Duality Log in to Mediaspace to watch this video

Covers optimal transport and Kantorovich duality in real-life distribution problems.