Research map / Learning theory and algorithms / Sample complexity
Alternating Estimation for Structured High-Dimensional Multi-Response Models
Sheng Chen, Arindam Banerjee
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 noise-covariance-aware AltEst instead of ordinary GDS with identity covariance | Sparse multi-response linear regression · Synthetic data, m = 10, n from 40 to 90 | estimation error | Improved |
| Use resampling between AltEst iterations (ablation) | AltEst · Synthetic data, m = 10, especially small n | estimation error | Improved |
| Use resampling between AltEst iterations (ablation) | AltEst · Synthetic data, m = 10, suitably large n | estimation error | No clear effect |
| Estimate the covariance iteratively with AltEst rather than use oracle GDS | Sparse multi-response linear regression · Synthetic data, m = 10, n from 40 to 90 | estimation error | Hurt |
| Run AltEst with n = 40 | AltEst · Synthetic data, m = 10, n = 40 | estimation error | Mixed |
Closest papers by meaning
- An Improved Analysis of Alternating Minimization for Structured Multi-Response Regression (NeurIPS 2018 · similarity 0.89)
- Estimation of Graphical Models through Structured Norm Minimization (JMLR 2018 · similarity 0.84)
- Structured Matrix Recovery via the Generalized Dantzig Selector (NeurIPS 2016 · similarity 0.84)
- CoLiDE: Concomitant Linear DAG Estimation (ICLR 2024 · similarity 0.84)
- Learning Low-dimensional Latent Dynamics from High-dimensional Observations: Non-asymptotics and Lower Bounds (ICML 2024 · similarity 0.82)
- Flat Minima in Linear Estimation and an Extended Gauss Markov Theorem (ICLR 2024 · similarity 0.81)
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.
