Hybrid Least Squares/Gradient Descent Methods for MIONets

Jun Choi, Chang-Ock Lee, Minam Moon
7/8/2026
cs.LGcs.AImath.NA

No confident code implementation found for this paper. 4 possible matches can be shown below.

Abstract

In this paper, we propose an efficient hybrid least squares/gradient descent (LSGD) method for MIONets to accelerate training. This method generalizes the LSGD method for DeepONets. Since MIONet is the sum of the entrywise product of multiple branch networks and a trunk network, it can be viewed as a multilinear function with respect to the last layer parameters of each branch network. These sets of parameters can be optimized using the alternating least squares method, where we solve the LS system for a single branch network in turn. To handle the large-sized system matrix, we introduce Kronecker and Khatri-Rao products and tensor permutation matrices to factor the large matrix into small ones. Our method is compatible with a general type of $L^2$ loss with regularization terms for the last layer parameters of each branch, where linear operators can be applied to the MIONet output in each loss term.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 4 weaker matches are hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Hybrid Least Squares/Gradient Descent Methods for DeepONets

86% match2025

A Solver + Gradient Descent Training Algorithm for Deep Neural Networks

84% match2022

Adaptive Hybrid Subspace Levenberg Marquardt Algorithm with Adequacy Monitor for Large Scale Least Squares Problems

80% match2026

Improving Energy Natural Gradient Descent through Woodbury, Momentum, and Randomization

80% match2025

A Layer-Wise Natural Gradient Optimizer for Training Deep Neural Networks

79% match2026

Hybrid Coordinate Descent for Efficient Neural Network Learning Using Line Search and Gradient Descent

79% match2024

Cite this paper

@article{choi2026hybrid,
  title  = {Hybrid Least Squares/Gradient Descent Methods for MIONets},
  author = {Jun Choi and Chang-Ock Lee and Minam Moon},
  year   = {2026},
  eprint = {2607.06976},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2607.06976v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2607.06976.svg)](https://codeofpaper.com/paper/2607.06976)

Discussion