Differential Equations and Continuous-Time Dynamics in Optimization and Sampling
Event details
Date | 23.08.2018 |
Hour | 13:00 › 15:00 |
Speaker | Ali Kavis |
Location | |
Category | Conferences - Seminars |
EDIC candidacy exam
Exam president: Prof. Ali Sayed
Thesis advisor: Prof. Volkan Cevher
Co-examiner: Prof. Patrick Thiran
Abstract
In the recent years, there has been an increasing number of works that couples continuous-time processes with iterative descent methods in optimization literature to provide alternative perspective to convergence analysis and develop new algorithms.
Background papers
Coupling and Convergence for Hamiltonian Monte Carlo, by Bou-Rabee, N., et al.
A Variational Perspective on Accelerated Methods in Optimization, by Wibisono, A., et al.
Direct Runge-Kutta Discretization Achieves Acceleration, by Zhang, J., et al.
Exam president: Prof. Ali Sayed
Thesis advisor: Prof. Volkan Cevher
Co-examiner: Prof. Patrick Thiran
Abstract
In the recent years, there has been an increasing number of works that couples continuous-time processes with iterative descent methods in optimization literature to provide alternative perspective to convergence analysis and develop new algorithms.
Background papers
Coupling and Convergence for Hamiltonian Monte Carlo, by Bou-Rabee, N., et al.
A Variational Perspective on Accelerated Methods in Optimization, by Wibisono, A., et al.
Direct Runge-Kutta Discretization Achieves Acceleration, by Zhang, J., et al.
Practical information
- General public
- Free
Contact
- EDIC - [email protected]