activity
20242026
collaborators

8 papers

cs.SI2026

ALM-MTA:Front-Door Causal Multi-Touch Attribution Method for Creator-Ecosystem Optimization

Yuguang Liu, Luyao Xia, Hu Liu +4

Consumption Drives Production (CDP) on social platforms aims to deliver interpretable incentive signals for creator ecosystem building and resource utilization improvement, which s…

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

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…

math.OC2025

The Ball-Proximal (="Broximal") Point Method: a New Algorithm, Convergence Theory, and Applications

Kaja Gruntkowska, Hanmin Li, Aadi Rane +1

Non-smooth and non-convex global optimization poses significant challenges across various applications, where standard gradient-based methods often struggle. We propose the Ball-Pr…

math.OC2024

Variance Reduced Distributed Non-Convex Optimization Using Matrix Stepsizes

Hanmin Li, Avetik Karagulyan, Peter Richtárik

Matrix-stepsized gradient descent algorithms have been shown to have superior performance in non-convex optimization problems compared to their scalar counterparts. The det-CGD alg…