Past year
All results
- All results
- Verbatim
May 5, 2024 · To resolve this problem, we propose a non-intrusive methodology with a novel gradient estimation technique to combine machine learning and legacy numerical ...
May 15, 2024 · To address this issue, we propose a gradient-based algorithm for MOBLO, called gMOBA, which has fewer hyperparameters to tune, making it both simple and ...
Dec 11, 2023 · Classical acceleration methods for fixed-point problems focus on designing algorithms with theoretical guarantees that apply to any fixed-point problem. We ...
Feb 14, 2024 · Accelerating Legacy Numerical Solvers by Non-intrusive Gradient-based Meta-solving ... Position: Rethinking Post-Hoc Search-Based Neural Approaches for Solving ...
Jun 19, 2024 · This paper focuses on solving DCOPF problems using gradient-based routines on Graphics Processing Units (GPUs), which have massive parallelization capability.
Missing: meta- | Show results with:meta-
May 1, 2024 · In this work, we propose a new method to solve partial differential equations (PDEs). Taking inspiration from traditional numerical methods, we view approx- ...
Missing: Accelerating | Show results with:Accelerating
Dec 9, 2023 · In this study, we suggest a path that potentially opens up a possibility for physics-informed neural networks (PINNs), emerging deep-learning-based solvers, to ...
Missing: Accelerating | Show results with:Accelerating
Mar 29, 2024 · A series of examples and numerical simulations offer insight and highlight some limitations of these approaches. Experiments on larger-scale problems show the ...
Jul 15, 2023 · A novel generative model based on SinGAN is proposed for handling the problem of few-shot diagnosis. ... A Gradient flow-based algorithm is developed to improve ...
Jun 6, 2024 · This paper introduces gradient-based adaptive neural networks to solve local fractional elliptic partial differential equations. The impact of physics-informed ...