Research map / Optimization / Optimizers
Iterative Double Sketching for Faster Least-Squares Optimization
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 |
|---|---|---|---|
| Iteration efficient sketching with gradient sketch sizes doubling across iterations (IDS, Algorithm 3) instead of full-data gradients (IHS) | least-squares iterative sketching · Theoretical complexity (N=Omega(d^2)) | computing time to reach eps relative error | Helped |
| Sketched gradients with sketch sizes doubling per iteration (IDS) vs. full gradient (IHS) | IDS vs IHS · Synthetic Model I and II, N=2^20, d=2^6 and 2^7 | Delta_t vs computing time | Helped |
| Sketched gradient (IDS) compared with PCG | IDS vs PCG · Synthetic Model I and II | Delta_t vs computing time | No clear effect |
Closest papers by meaning
- Can Gaussian Sketching Converge Faster on a Preconditioned Landscape? (ICML 2024 · similarity 0.89)
- Sketching for Convex and Nonconvex Regularized Least Squares with Sharp Guarantees (ICLR 2025 · similarity 0.89)
- Distributed Least Squares in Small Space via Sketching and Bias Reduction (NeurIPS 2024 · similarity 0.87)
- Newton Meets Marchenko-Pastur: Massively Parallel Second-Order Optimization with Hessian Sketching and Debiasing (ICLR 2025 · similarity 0.86)
- Optimal Sketching for Residual Error Estimation for Matrix and Vector Norms (ICLR 2024 · similarity 0.86)
- Matrix Product Sketching via Coordinated Sampling (ICLR 2025 · similarity 0.86)
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.