Papers › Momentum Stiefel Optimizer, with Applications to Suitably-Orthogonal Attention, and...

Momentum Stiefel Optimizer, with Applications to Suitably-Orthogonal Attention, and Optimal Transport

27 May 2022arXiv:2205.14173archive 2025-07-28

Lingkai Kong, Yuqing Wang, Molei Tao

The problem of optimization on Stiefel manifold, i.e., minimizing functions of (not necessarily square) matrices that satisfy orthogonality constraints, has been extensively studied. Yet, a new approach is proposed based on, for the first time, an interplay between thoughtfully designed continuous and discrete dynamics. It leads to a gradient-based optimizer with intrinsically added momentum. This method exactly preserves the manifold structure but does not require additional operation to keep momentum in the changing (co)tangent space, and thus has low computational cost and pleasant accuracy. Its generalization to adaptive learning rates is also demonstrated. Notable performances are observed in practical tasks. For instance, we found that placing orthogonal constraints on attention heads of trained-from-scratch Vision Transformer [Dosovitskiy et al. 2022] could markedly improve its performance, when our optimizer is used, and it is better that each head is made orthogonal within itself but not necessarily to other heads. This optimizer also makes the useful notion of Projection Robust Wasserstein Distance [Paty & Cuturi 2019; Lin et al. 2020] for high-dim. optimal transport even more effective.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2205.14173")

Code

Syntology Ran 7 of 7 code samples harvested from 1 repository linked to this paper; 0 have no recorded run. Of those that ran: 1 ran · violated contract; 6 ran with no contract checked.

By repository: official repository: 7 samples from 1 repository, 7 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

konglk1203/variationalstiefeloptimizer officialmentioned in papermentioned on GitHubpytorchMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

7 samples harvested; 7 ran; 0 honoured the contract we drafted; 0 have no recorded run. Read from Syntology's graph 2026-09-25; that is when this build read the record, not when the samples ran.

1ran · violated contract
6ran

Licence: 0 of the 7 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from konglk1203/variationalstiefeloptimizer. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

bures_wasserstein konglk1203/variationalstiefeloptimizer/ProjectionRobustWasserstein/utils.py official repository ran MIT (permissive) · 11f75e7ba9b99252 · report
euclidean_proj_simplex konglk1203/variationalstiefeloptimizer/ProjectionRobustWasserstein/utils.py official repository ran fingerprinted MIT (permissive) · 8c58d2935bdccfe6 · report
matrix_root konglk1203/variationalstiefeloptimizer/utils_StiefelOptimizers.py official repository ran fingerprinted MIT (permissive) · 9b40536aafe9e6c8 · report
matrix_root_inv konglk1203/variationalstiefeloptimizer/utils_StiefelOptimizers.py official repository ran fingerprinted MIT (permissive) · f27a35e212b683b4 · report
matrix_square_root konglk1203/variationalstiefeloptimizer/utils_StiefelOptimizers.py official repository ran MIT (permissive) · d53df6acf4c93e3b · report
pair konglk1203/variationalstiefeloptimizer/ViT/ViT.py official repository ran · violated contract fingerprinted MIT (permissive) · 6ba8cee9f5daea41 · report
sample_simplex konglk1203/variationalstiefeloptimizer/ProjectionRobustWasserstein/utils.py official repository ran fingerprinted MIT (permissive) · 4e8159ee568761a8 · report

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformerVision Transformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections