Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in Coakley et alK. L. Coakley, T. Snelleman, H. Hoos, and O. E. Gundersen, "The embrace of open science: An analysis of a decade of AI research and 56 800 conference papers," Under Review, 2026..
Efficient Optimization with Orthogonality Constraint: a Randomized Riemannian Submanifold Method
Authors: Andi Han, Pierre-Louis Poirion, Akiko Takeda
ICML 2025 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experiments verify the benefits of the proposed method, across a wide variety of problems. 6. Experiments This section conducts experiments to verify the efficacy of the proposed method. |
| Researcher Affiliation | Academia | 1RIKEN AIP 2University of Sydney 3University of Tokyo. Correspondence to: Andi Han <EMAIL>. |
| Pseudocode | Yes | Algorithm 1 RSDM |
| Open Source Code | Yes | All experiments are implemented in Pytorch and run on a single RTX4060 GPU. The code is available on https://github.com/ andyjm3/RSDM. |
| Open Datasets | Yes | We optimize neural networks (orthogonal FFN and orthogonal Vi T) to classify MNIST (Le Cun et al., 1998) and CIFAR10 (Krizhevsky et al., 2009) images. |
| Dataset Splits | Yes | We optimize neural networks (orthogonal FFN and orthogonal Vi T) to classify MNIST (Le Cun et al., 1998) and CIFAR10 (Krizhevsky et al., 2009) images. |
| Hardware Specification | Yes | All experiments are implemented in Pytorch and run on a single RTX4060 GPU. |
| Software Dependencies | No | All experiments are implemented in Pytorch and run on a single RTX4060 GPU. |
| Experiment Setup | Yes | For all experiments, we tune the learning rate in the range of [0.01, 0.05, 0.1, 0.5, 1.0, 1.5, 2.0]. For the infeasible methods, we tune the regularization parameter in the range of [0.1, 0.5, 1.0, 1.5, 2.0]. For optimization, we employ RGD and RSDM with a batch size of 16. We set learning rate for unconstrained parameters to be 0.1 and only tune the learning rate for the orthogonal parameters. |