Research map / Optimization / Nonconvex and smooth optimization
Harder, Better, Faster, Stronger Convergence Rates for Least-Squares Regression
Aymeric Dieuleveut, Nicolas Flammarion, Francis Bach
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 |
|---|---|---|---|
| add averaging to accelerated SGD (AvAccSGD vs AccSGD) | accelerated SGD · synthetic least-squares (d=25), variance | convergence to optimum | Improved |
| add acceleration to averaged SGD (AvAccSGD vs AvSGD) | averaged SGD · synthetic least-squares (d=25), bias | bias convergence rate | Improved |
| use AccSGD instead of AvAccSGD for late-stage bias | accelerated SGD · synthetic least-squares (d=25), bias | bias convergence | Improved |
| use AvSGD instead of AvAccSGD early in training | averaged SGD · synthetic least-squares (d=25), variance | early variance convergence | Mixed |
Closest papers by meaning
- Private Gradient Descent for Linear Regression: Tighter Error Bounds and Instance-Specific Uncertainty Estimation (ICML 2024 · similarity 0.89)
- Parallelizing Stochastic Gradient Descent for Least Squares Regression: Mini-batching, Averaging, and Model Misspecification (JMLR 2018 · similarity 0.89)
- Kernel Truncated Randomized Ridge Regression: Optimal Rates and Low Noise Acceleration (NeurIPS 2019 · similarity 0.89)
- The Implicit Regularization of Stochastic Gradient Flow for Least Squares (ICML 2020 · similarity 0.89)
- Regularized least squares learning with heavy-tailed noise is minimax optimal (NeurIPS 2025 · similarity 0.88)
- Block Acceleration Without Momentum: On Optimal Stepsizes of Block Gradient Descent for Least-Squares (ICML 2024 · similarity 0.87)
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.
