Research map / Learning theory and algorithms / Matrix and tensor methods
Learning a Latent Simplex in Input Sparsity Time
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 an input-sparsity mixed spectral-Frobenius approximation instead of computing the top-k subspace with power iteration | Latent simplex learning · Synthetic data | runtime | Helped |
| Use an input-sparsity mixed spectral-Frobenius approximation instead of computing the top-k subspace with power iteration | Latent simplex learning · email-Eu-core network | runtime | Helped |
| Use an input-sparsity mixed spectral-Frobenius approximation instead of computing the top-k subspace with power iteration | Latent simplex learning · com-Youtube | runtime | Helped |
| Use the input-sparsity approximation algorithm instead of the top-k subspace algorithm | Latent simplex learning · com-Youtube | least squares loss | Helped |
| Use a mixed spectral-Frobenius approximation under the Significant Singular Values assumption | Latent simplex learning · Latent Simplex Model | running time: O(nnz(A) + (n+d)poly(k/φ)) | Helped |
Closest papers by meaning
- Is Input Sparsity Time Possible for Kernel Low-Rank Approximation? (NeurIPS 2017 · similarity 0.87)
- Linear-Sample Learning of Low-Rank Distributions (NeurIPS 2020 · similarity 0.86)
- Exploiting Numerical Sparsity for Efficient Learning : Faster Eigenvector Computation and Regression (NeurIPS 2018 · similarity 0.86)
- Learning-Based Low-Rank Approximations (NeurIPS 2019 · similarity 0.85)
- On Statistical Rates and Provably Efficient Criteria of Latent Diffusion Transformers (DiTs) (NeurIPS 2024 · similarity 0.84)
- Learning Low-dimensional Latent Dynamics from High-dimensional Observations: Non-asymptotics and Lower Bounds (ICML 2024 · similarity 0.84)
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.