Are you an EPFL student looking for a semester project?
Work with us on data science and visualisation projects, and deploy your project as an app on top of Graph Search.
This lecture covers the concept of estimation using linear estimators, focusing on the criteria for optimal estimation and the orthogonality principle. The instructor explains the requirements for a good choice of estimator, emphasizing the importance of Hilbert space and the mean-squared error. Various tricks and criteria for optimal choices are discussed, including the use of Fisher information. The lecture also delves into the assumptions and considerations for invertible functions and the implications of closeness according to the given data.