193 citations · 476 across the 39 of their papers we have counts for
4 papers · 1 filter
A Strongly Monotonic Polygonal Euler Scheme
Tim Johnston, Sotirios Sabanis
In recent years tamed schemes have become an important technique for simulating SDEs and SPDEs whose continuous coefficients display superlinear growth. The taming method, which in…
Statistical Finite Elements via Langevin Dynamics
Ömer Deniz Akyildiz, Connor Duffin, Sotirios Sabanis +1
The recent statistical finite element method (statFEM) provides a coherent statistical framework to synthesise finite element models with observed data. Through embedding uncertain…
Non-asymptotic estimates for TUSLA algorithm for non-convex learning with applications to neural networks with ReLU activation function
Dong-Young Lim, Ariel Neufeld, Sotirios Sabanis +1
We consider non-convex stochastic optimization problems where the objective functions have super-linearly growing and discontinuous stochastic gradients. In such a setting, we prov…
Polygonal Unadjusted Langevin Algorithms: Creating stable and efficient adaptive algorithms for neural networks
Dong-Young Lim, Sotirios Sabanis
We present a new class of Langevin based algorithms, which overcomes many of the known shortcomings of popular adaptive optimizers that are currently used for the fine tuning of de…