Concentration of measure for nonlinear random matrices
- Prelegent(ci)
- Radosław Adamczak
- Afiliacja
- University of Warsaw
- Język referatu
- angielski
- Termin
- 16 października 2025 12:15
- Pokój
- p. 3160
- Tytuł w języku polskim
- Concentration of measure for nonlinear random matrices
- Seminarium
- Seminarium Zakładu Rachunku Prawdopodobieństwa
I will present concentration inequalities for certain models of random matrices related to neural networks. I will discuss their optimality and dependence on the choice of activation functions and the distribution of weights. Next, I will apply them to eigenvalue statistics, in particular showing a deviation inequality for the first Wasserstein distance between the empirical and expected spectral measures of the conjugate kernel of the neural network.
Nie jesteś zalogowany |