Tata Institute of Fundamental Research
Private Optimization and Statistical Physics: Low-Rank Matrix Approximation
Infosys-Chandrasekharan Random Geometry Colloquium
Speaker:
Nisheeth Vishnoi (Yale university)
Organiser:
Piyush Srivastava
Date:
Tuesday, 3 Jan 2023, 14:00 to 15:00
Venue:
AG-66
(Scan to add to calendar)
Abstract:
In this talk, I will discuss the following connections between private optimization and statistical physics in the context of the low-rank matrix approximation problem:
1) An efficient algorithm to privately compute a low-rank approximation and how it leads to an efficient way to sample from Harish-Chandra-Itzykson-Zuber densities studied in physics and mathematics, and
2) An improved analysis of the "utility" of the "Gaussian Mechanism" for private low-rank approximation using Dyson Brownian motion.
| Speaker: | Nisheeth Vishnoi (Yale university) |
| Organiser: | Piyush Srivastava |
| Date: | Tuesday, 3 Jan 2023, 14:00 to 15:00 |
| Venue: | AG-66 |
(Scan to add to calendar)
Abstract:
In this talk, I will discuss the following connections between private optimization and statistical physics in the context of the low-rank matrix approximation problem:
1) An efficient algorithm to privately compute a low-rank approximation and how it leads to an efficient way to sample from Harish-Chandra-Itzykson-Zuber densities studied in physics and mathematics, and
2) An improved analysis of the "utility" of the "Gaussian Mechanism" for private low-rank approximation using Dyson Brownian motion.
1) An efficient algorithm to privately compute a low-rank approximation and how it leads to an efficient way to sample from Harish-Chandra-Itzykson-Zuber densities studied in physics and mathematics, and
2) An improved analysis of the "utility" of the "Gaussian Mechanism" for private low-rank approximation using Dyson Brownian motion.