pith. sign in

arxiv: 2005.02819 · v5 · pith:S3524RFCnew · submitted 2020-05-06 · 💻 cs.CG · cs.LG

Geoopt: Riemannian Optimization in PyTorch

classification 💻 cs.CG cs.LG
keywords geooptoptimizationalgorithmsriemannianpytorchadaptiveallowallows
0
0 comments X
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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 4 Pith papers

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

  1. REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations

    cs.CL 2026-05 unverdicted novelty 8.0

    REALISTA optimizes continuous combinations of valid editing directions in latent space to produce realistic adversarial prompts that elicit hallucinations more effectively than prior methods, including on large reason...

  2. Towards Robust EEG Decoding Based on Riemannian Self-Attention

    cs.LG 2026-06 unverdicted novelty 6.0

    A Riemannian self-attention model based on the Bures-Wasserstein metric and its learnable generalized version is claimed to improve robustness of EEG decoding on three benchmark datasets.

  3. REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations

    cs.CL 2026-05 unverdicted novelty 6.0

    REALISTA generates semantically coherent adversarial prompts via latent-space optimization over input-dependent editing directions, achieving stronger hallucination elicitation than prior realistic attacks on open-sou...

  4. Foundations of Riemannian Geometry for Riemannian Optimization: A Monograph with Detailed Derivations

    math.DG 2026-05 unverdicted novelty 2.0

    The monograph organizes and derives classical Riemannian geometry structures explicitly in coordinate and matrix form for direct use in optimization algorithms on nonlinear manifolds.