4 papers
Convergence analysis of a full discretization of operator-valued differential Riccati equations
Eskil Hansen, Tony Stillfjord, Teodor à berg
In recent previous work [E. Hansen, T. Stillfjord and T. Ã berg, SIAM J. Numer. Anal., to appear], we analyzed the convergence of operator splitting methods applied to operator-val…
Almost sure convergence of stochastic Hamiltonian descent methods
MÃ¥ns Williamson, Tony Stillfjord
Gradient normalization and soft clipping are two popular techniques for tackling instability issues and improving convergence of stochastic gradient descent (SGD) with momentum. In…
Convergence analysis of Lie and Strang splitting for operator-valued differential Riccati equations
Eskil Hansen, Tony Stillfjord, Teodor à berg
Differential Riccati equations (DREs) are semilinear matrix- or operator-valued differential equations with quadratic non-linearities. They arise in many different areas, and are p…
Analysis of a Class of Stochastic Component-Wise Soft-Clipping Schemes
MÃ¥ns Williamson, Monika Eisenmann, Tony Stillfjord
Choosing the optimization algorithm that performs best on a given machine learning problem is often delicate, and there is no guarantee that current state-of-the-art algorithms wil…