Research map / Learning theory and algorithms / Sample complexity
Multi-Fidelity Covariance Estimation in the Log-Euclidean Geometry
Aimee Maurais, Terrence Alsup, Benjamin Peherstorfer, Youssef Marzouk
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use LEMF instead of high-fidelity-only covariance estimation | Covariance estimation · Motivating Gaussian example | log-Euclidean MSE: 1.72 -> 0.83 | Improved |
| Use LEMF instead of truncated Euclidean MF | Covariance estimation · Motivating Gaussian example | log-Euclidean MSE: 66.88 -> 0.83 | Improved |
| Use LEMF instead of high-fidelity-only covariance estimation | Covariance estimation · Motivating Gaussian example | affine-invariant MSE: 4.99 -> 2.69 | Improved |
| Use LEMF instead of truncated Euclidean MF | Covariance estimation · Motivating Gaussian example | affine-invariant MSE: 125.11 -> 2.69 | Improved |
| Use LEMF instead of Euclidean MF | Covariance estimation · Motivating Gaussian example | Euclidean MSE: 0.51 -> 0.71 | Hurt |
| Combine surrogate samples with high-fidelity samples using LEMF | Heat-flow covariance estimation · Heat flow | speedup: 32× | Improved |
| Use LEMF for covariance estimates in metric learning | Surface quasi-geostrophy metric learning · Surface quasi-geostrophy | mean relative error of distances: >20% | Improved |
| Use Euclidean MF rather than LEMF | Heat-flow covariance estimation · Heat flow | positive-definiteness validity: more than 10% of the 100 trials | Hurt |
Closest papers by meaning
- Intrinsic Riemannian Cross-covariance for Manifold-valued Random Objects (NeurIPS 2026 · similarity 0.86)
- Spectral Estimation with Deformed Decompression (NeurIPS 2026 · similarity 0.85)
- Fundamental Limits of Distributed Covariance Matrix Estimation Under Communication Constraints (ICML 2024 · similarity 0.85)
- The Implicit Bias of Heterogeneity towards Invariance: A Study of Multi-Environment Matrix Sensing (NeurIPS 2024 · similarity 0.84)
- The Value of Covariance Matching in Gaussian DDPMs and the Lanczos Sampler (NeurIPS 2026 · similarity 0.84)
- Manifold Diffusion Fields (ICLR 2024 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
