3 papers
cs.LG2025
Permutation Randomization on Nonsmooth Nonconvex Optimization: A Theoretical and Experimental Study
Wei Zhang, Arif Hassan Zidan, Afrar Jahin +2
While gradient-based optimizers that incorporate randomization often showcase superior performance on complex optimization, the theoretical foundations underlying this superiority…
cs.LG2025
HOME-3: High-Order Momentum Estimator with Third-Power Gradient for Convex and Smooth Nonconvex Optimization
Wei Zhang, Arif Hassan Zidan, Afrar Jahin +2
Momentum-based gradients are essential for optimizing advanced machine learning models, as they not only accelerate convergence but also advance optimizers to escape stationary poi…
cs.LG2025
Evaluating Mathematical Reasoning Across Large Language Models: A Fine-Grained Approach
Afrar Jahin, Arif Hassan Zidan, Wei Zhang +2
With the rapid advancement of Artificial Intelligence (AI), Large Language Models (LLMs) have significantly impacted a wide array of domains, including healthcare, engineering, sci…