3 papers
stat.ML2026
Born Discrete, Made Smooth: Variational Formulation of Shallow Neural Networks
Matej Benko, Pierre Bousquet, Iwona Chlebicka +1
Although neural networks are remarkably effective, their underlying optimization principles remain theoretically elusive, often characterized by non-convex landscapes and stochasti…
math.NA2025
Convergence rates of particle approximation of forward-backward splitting algorithm for granular medium equations
Matej Benko, Iwona Chlebicka, Jørgen Endal +1
We study the spatially homogeneous granular medium equation \[\partial_tμ=\rm{div}(μ\nabla V)+\rm{div}(μ(\nabla W \ast μ))+Îμ\,,\] within a large and natural class of the con…
stat.ML2024
Langevin Monte Carlo Beyond Lipschitz Gradient Continuity
Matej Benko, Iwona Chlebicka, Jørgen Endal +1
We present a significant advancement in the field of Langevin Monte Carlo (LMC) methods by introducing the Inexact Proximal Langevin Algorithm (IPLA). This novel algorithm broadens…