description [ICLR 2026][Optimization][SignSGD] This work systematically analyzes the scaling laws of SignSGD under the Power-Law Random Features (PLRF) model, revealing two unique ...

Understanding the mechanism of how neural networks learn features from data is a fundamental problem in machine learning. Our work explicitly connects the mechanism of neural feature learning to a ...

The minimization of matrix bandwidth is a cornerstone challenge in computational linear algebra and graph theory, with direct implications for the efficiency of numerical solvers, finite-element ...

Chemical Physics Theory Group, Department of Chemistry, University of Toronto, Toronto, Ontario, Canada M5S 3H6 Department of Physical and Environmental Sciences, University of Toronto Scarborough, ...

Operations research professionals need the best linear programming software for Windows to solve optimization problems. Below we offer a tool that comes with all the essentials to help you perform a ...

This paper presents a method of equilibrium path analysis and stability analysis of an equilibrium state for a rigid origami, which consists of rigid flat faces connected by straight crease lines ...

Physics-Informed Neural Networks (PINN) are neural networks encoding the problem governing equations, such as Partial Differential Equations (PDE), as a part of the neural network. PINNs have emerged ...