Research map / Optimization / Implicit bias and generalization
Stochastic Gradient Descent in Correlated Settings: A Study on Gaussian Processes
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 |
|---|---|---|---|
| train GP hyperparameters with minibatch SGD (sgGP) instead of exact GP with PCG | GP · Levy | RMSE: 0.312 -> 0.265 | Helped |
| sgGP instead of exact GP | GP · Protein | RMSE: 0.694 -> 0.663 | Helped |
| sgGP instead of exact GP | GP · PM2.5 | RMSE: 0.286 -> 0.287 | No clear effect |
| sgGP instead of SVGP | GP · Levy | RMSE: 0.582 -> 0.265 | Helped |
| sgGP instead of exact GP | GP · Protein | training time (min): 500.33 -> 3.40 | Helped |
| sgGP instead of SVGP on 1M points | GP · Borehole | training time (min): 1380.86 -> 67.29 | Helped |
| larger minibatch size m (ablation) | minibatch SGD for GP · simulation n=1024, full gradient norm | convergence of full gradient | Helped |
Closest papers by meaning
- Sampling from Gaussian Process Posteriors using Stochastic Gradient Descent (NeurIPS 2023 · similarity 0.91)
- Determinantal point processes based on orthogonal polynomials for sampling minibatches in SGD (NeurIPS 2021 · similarity 0.91)
- A Guide Through the Zoo of Biased SGD (NeurIPS 2023 · similarity 0.91)
- Demystifying SGD with Doubly Stochastic Gradients (ICML 2024 · similarity 0.89)
- Nonasymptotic Analysis of Stochastic Gradient Descent with the Richardson–Romberg Extrapolation (ICLR 2025 · similarity 0.88)
- Gradient correlation is a key ingredient to accelerate SGD with momentum (ICLR 2025 · similarity 0.88)
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.