3 papers
math.OC2026
Last-Iterate Convergence of Stochastic Gradient Methods for Unbounded Problems
Kevin Kurian Thomas Vaidyan, Ahmet Alacaoglu, Michael P. Friedlander
Last-iterate convergence guarantees for stochastic gradient methods have attracted significant attention as practical implementations typically return the last iterate instead of a…
math.NA2026
Sparse Random-Feature Neural Networks with Krylov-Based SVD for Singularly Perturbed ODE
Kevin Kurian Thomas Vaidyan, Siddharth Rout
Random-feature neural networks (RFNNs), including architectures with fixed hidden layers and analytically determined output weights, offer fast training but often suffer from issue…
math.OC2026
Convergence Rate of the Last Iterate of Stochastic Proximal Algorithms
Kevin Kurian Thomas Vaidyan, Michael P. Friedlander, Ahmet Alacaoglu
We analyze two classical algorithms for solving additively composite convex optimization problems where the objective is the sum of a smooth term and a nonsmooth regularizer: proxi…