# geoopt/geoopt

Riemannian Adaptive Optimization Methods with pytorch optim

Repository: https://github.com/geoopt/geoopt
Canonical: https://ross.abutalabs.com/products/geoopt
Homepage: https://geoopt.readthedocs.io
Language: Python
License: NOASSERTION
License Family: other
Topics: optimization, pytorch, riemannian-optimization, riemannian-geometry, riemannian-manifold
Last push: 2026-05-09T15:51:57+00:00

## Health v2 (maintenance only)
Score: 59/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 81, release rhythm 8, longevity 100
- inputs: {"age_days": 2856, "days_push": 116, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1091, forks 94 (observed 2026-08-28T04:03:32.957706+00:00)

## What it is
Geoopt is a PyTorch library providing manifold-aware optimizers and manifold tensor containers for Riemannian optimization. It implements Riemannian Adaptive Optimization Methods (ICLR 2019) plus a variety of manifolds such as the Poincare ball, sphere, Stiefel, and hyperboloid models.

## Use cases
- optimize neural network parameters constrained to a Riemannian manifold in PyTorch
- train models with hyperbolic embeddings using the Poincare ball
- perform gradient descent on the sphere or Stiefel manifold
- implement Riemannian Adam and SGD optimizers
- project tensors and gradients onto manifolds in deep learning pipelines

## When to choose
- you need Riemannian optimizers integrated with torch.optim
- your model parameters live on manifolds like spheres, hyperbolic spaces, or Stiefel matrices
- you want manifold-aware tensors that work with standard PyTorch modules

## When to avoid
- you only need standard Euclidean optimization
- you need a fully stable, frozen API - the project is under active development and the API may change
- you use a PyTorch version older than 2.0.1

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, math
- domain: machine-learning, deep-learning, mathematics
- platform: python
- tags: riemannian-optimization, pytorch, manifolds, hyperbolic-embeddings, optimizers, optimization, algorithms

## Member repositories
- geoopt/geoopt (main) score 59

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:32.957706+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:49:07.999422+00:00, confidence not recorded.
  - readme: https://github.com/geoopt/geoopt (fetched 2026-08-28T04:03:32.957706+00:00, sha 20b30b7ee208)
  - registry_pypi: https://pypi.org/pypi/geoopt/json (fetched 2026-08-29T12:51:56.750999+00:00, sha d39a9723f3fe)
- Data as of 2026-08-30T08:39:29.467469+00:00.