Research map / Optimization / Optimizers
Scaling-Up Robust Gradient Descent Techniques
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 distance-based merging of independent SGD candidates instead of robustly aggregating gradients at every step | DC-SGD · Strongly convex risks with heavy-tailed losses and gradients | excess risk | Helped |
| Use distance-based merging of independent SGD candidates instead of robustly aggregating gradients at every step | DC-SGD · Simulated noisy convex minimization, including log-Normal noise | excess risk | Mixed |
| Use two-pass DC-SGD rather than many-pass batch methods | DC-SGD · Simulated noisy convex minimization with d = 1024 | computation time | Helped |
| Use DC-SGD rather than well-tuned RGD methods | DC-SGD · Simulated noisy convex minimization | excess risk | Mixed |
Closest papers by meaning
- Estimating Generalization Performance Along the Trajectory of Proximal SGD in Robust Regression (NeurIPS 2024 · similarity 0.88)
- Statistical Guarantees for High-Dimensional Stochastic Gradient Descent (NeurIPS 2025 · similarity 0.87)
- Error Analysis Affected by Heavy-Tailed Gradients for Non-Convex Pairwise Stochastic Gradient Descent (AAAI 2025 · similarity 0.87)
- Emergence of heavy tails in homogenized stochastic gradient descent (NeurIPS 2024 · similarity 0.87)
- Gradient Descent Converges Arbitrarily Fast for Logistic Regression via Large and Adaptive Stepsizes (ICML 2025 · similarity 0.87)
- Distributionally Robust Optimization with Bias and Variance Reduction (ICLR 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.