Recently, the ConFIG method has also been applied to train physics-constrained generative models: Flow Matching Meets PDEs: A Unified Framework for Physics ...

This study introduced an efficient method for solving non-linear equations. Our approach enhances the traditional spectral conjugate gradient parameter, resulting in significant improvements in the ...

Abstract: In order to solve the global optimization problem in engineering and management, Spectral conjugate gradient methods are used in this paper. By introducing the generalized quasi-Newton ...

Multitask learning (MLT) involves training a single model to perform multiple tasks simultaneously, leveraging shared information to enhance performance. While beneficial, MLT poses challenges in ...

In this installment, I illustrate the impact of different gradient delay volumes when transferring a method between instruments and discuss some strategies that can be used to mitigate these ...

MATLAB package of iterative regularization methods and large-scale test problems. This software is described in the paper "IR Tools: A MATLAB Package of Iterative Regularization Methods and ...