activity
20242026
collaborators

11 papers

math.OC2026

Local LMO: Constrained Gradient Optimization via a Local Linear Minimization Oracle

Peter Richtárik, Kaja Gruntkowska, Hanmin Li

We design Local LMO - a new projection-free gradient-type method for constrained optimization. The key algorithmic idea is to replace the global linear minimization oracle over the…

math.OC2026

Tighter Performance Theory of FedExProx

Wojciech Anyszka, Kaja Gruntkowska, Alexander Tyurin +1

We revisit FedExProx - a recently proposed distributed optimization method designed to enhance convergence properties of parallel proximal algorithms via extrapolation. In the proc…

math.OC2026

Broximal Alignment for Global Non-Convex Optimization

Kaja Gruntkowska, Hanmin Li, Xun Qian +1

Most non-convex optimization theory is built around gradient dynamics, leaving global convergence largely unexplored. The dominant paradigm focuses on stationarity, certifying only…

math.OC2026

Stabilized Proximal Point Method via Trust Region Control

Hanmin Li, Kaja Gruntkowska, Peter Richtárik

The Proximal Point Method (PPM) (Rockafellar, 1976) is a fundamental tool for nonsmooth convex optimization. However, its convergence is not linear under general convexity in the a…

cs.LG2025

Drop-Muon: Update Less, Converge Faster

Kaja Gruntkowska, Yassine Maziane, Zheng Qu +1

Conventional wisdom in deep learning optimization dictates updating all layers at every step-a principle followed by all recent state-of-the-art optimizers such as Muon. In this wo…

math.OC2025

Non-Euclidean Broximal Point Method: A Blueprint for Geometry-Aware Optimization

Kaja Gruntkowska, Peter Richtárik

The recently proposed Broximal Point Method (BPM) [Gruntkowska et al., 2025] offers an idealized optimization framework based on iteratively minimizing the objective function over…