Intensive Lectures for

Optimal Transport and Machine Learning,

Geometric Measure Theory


Date: July - August, 2017       Place: Rm. 1503, KIAS

Titles & Abstracts Home > Titles & Abstracts

Optimal Transport and Machine Learning
Lecturer: Seungjin Choi (Computer Science and Engineering, POSTECH)
Title: TBA

Lecturer: Marco Cuturi (ENSAE / CREST)
Title: TBA

Lecturer: Jinwoo Shin (Electrical Engineering, KAIST)
Title: Generative Machine Learning
Abstract: Generative models randomly generate observable data values, typically given some hidden parameters. In this talk, I will introduce most successful generative models and their underlying theory, which have developed in the machine learning community: (a) graphical models (e.g., Gaussian, Markov random fields, Boltzmann machines) and (b) neural networks (e.g., variational auto-encoders, generative adversarial networks).

Geometric Measure Theory
Lecturer: Giovanni Alberti (University of Pisa)
Title: An introduction to Geometric Measure Theory and Finite Perimeter Sets.
Abstract: In this course I will introduce the basic notions of Geometric Measure Theory (Hausdorff measures, rectifiable sets) and give an overview of the theory of Finite Perimeter Sets, including the proof of De Giorgi's rectifiability theorem. 
Then I will show how this theory can be used to prove (easy) existence result for some geometric variational problems. If time allows I will also touch some additional topics, such as the theory of integral currents, the basic regularity for minimizers, and the elliptic approximation of the area functional.