Pith. sign in

REVIEW 7 cited by

Geoopt: Riemannian Optimization in PyTorch

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2005.02819 v5 pith:S3524RFC submitted 2020-05-06 cs.CG cs.LG

Max Kochurov , Rasul Karimov , Serge Kozlukov This is my paper · ORCID
classification cs.CGcs.LG
keywords geooptoptimizationalgorithmsriemannianpytorchadaptiveallowallows
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Geoopt is a research-oriented modular open-source package for Riemannian Optimization in PyTorch. The core of Geoopt is a standard Manifold interface that allows for the generic implementation of optimization algorithms. Geoopt supports basic Riemannian SGD as well as adaptive optimization algorithms. Geoopt also provides several algorithms and arithmetic methods for supported manifolds, which allow composing geometry-aware neural network layers that can be integrated with existing models.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 7 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Learning Hamiltonian Dynamics at Scale: A Differential-Geometric Approach

    cs.LG 2025-09 unverdicted novelty 7.0 of 10

    RO-HNN combines a geometrically-constrained symplectic autoencoder with a geometric Hamiltonian neural network to enable physically consistent predictions on high-dimensional systems via model-order reduction.

  2. ManifoldFlow: SPD-Relaxed Stiefel Layers with Learnable Singular Spectrum

    cs.LG 2026-07 conditional novelty 6.0 of 10

    Learning a clipped SPD spectrum on top of a Stiefel basis improves fixed-spectrum Stiefel layers when an orthonormal prior is useful, especially in recurrent LM projections.

  3. A Fourier-Space Approach to Physics-Informed Magnetization Reconstruction from Nitrogen-Vacancy Measurements

    cond-mat.mes-hall 2026-02 conditional novelty 6.0 of 10

    A micromagnetic-energy-regularized Fourier-space inversion simultaneously reconstructs magnetization textures and the unknown NV sensor-sample distance (~80 nm) from stray-field maps.

  4. Continual Hyperbolic Learning of Instances and Classes

    cs.CV 2025-06 conditional novelty 6.0 of 10

    HyperCLIC embeds the instance-class hierarchy in hyperbolic space and uses hyperbolic classification and distillation losses to continuously learn both fine-grained instances and coarse-grained classes on EgoObjects, ...

  5. Cartan Networks: Group theoretical Hyperbolic Deep Learning

    cs.LG 2025-05 reject novelty 6.0 of 10

    Cartan networks compose solvable-group homomorphisms with isometries to define hyperbolic layers, and the paper reports competitive benchmark performance.

  6. ManifoldMind: Dynamic Hyperbolic Reasoning for Trustworthy Recommendations

    cs.IR 2025-07 reject novelty 5.0 of 10

    A recommender model that scores user-item pairs via beam-searched multi-hop tag paths in learnable-curvature hyperbolic space, claiming state-of-the-art accuracy, calibration, and diversity.

  7. Hyperbolic Deep Learning for Foundation Models: A Survey

    cs.LG 2025-07 conditional novelty 1.0 of 10

    A structured survey of hyperbolic-geometry methods for foundation models, concluding the approach is promising but showing limited independent evidence at scale.

Pith tools