Research map / Learning theory and algorithms / Matrix and tensor methods
Distributed estimation of the inverse Hessian by determinantal averaging
Michal Derezinski, Michael W. Mahoney
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 |
|---|---|---|---|
| Weight local Newton-step estimates by the determinant of each local Hessian instead of averaging uniformly | Distributed Newton's method · Abalone, cpusmall, mg, cadata | Newton-step estimation error | Improved |
| Use uniform averaging instead of determinant weighting | Distributed Newton's method · Abalone, cpusmall, mg, cadata | Newton-step estimation error | Hurt |
| Use determinant weighting of local Hessian inverses | Distributed Newton's method · As the number of machines grows | Newton-step estimation error | Improved |
| Use determinant weighting with small local sample sizes | Distributed Newton's method · Some libsvm datasets | Variance of Newton-step estimates | Hurt |
Closest papers by meaning
- Optimal Shrinkage for Distributed Second-Order Optimization (ICML 2023 · similarity 0.86)
- Fundamental Bias in Inverting Random Sampling Matrices with Application to Sub-sampled Newton (ICML 2025 · similarity 0.84)
- Debiasing Random Oblique Projections for Subsampled OLS and Fast CUR in High Dimensions (NeurIPS 2026 · similarity 0.81)
- Distributed Least Squares in Small Space via Sketching and Bias Reduction (NeurIPS 2024 · similarity 0.80)
- Private Gradient Descent for Linear Regression: Tighter Error Bounds and Instance-Specific Uncertainty Estimation (ICML 2024 · similarity 0.80)
- Distributed High-Dimensional Quantile Regression: Estimation Efficiency and Support Recovery (ICML 2024 · similarity 0.79)
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.
