Research map / Optimization / Optimizers
Variance Reduction in Stochastic Particle-Optimization Sampling
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 |
|---|---|---|---|
| Apply SAGA-based gradient variance reduction to SPOS | SPOS · Synthetic log-normal distribution | log-MSE | Helped |
| Apply SVRG-based gradient variance reduction to SPOS | SPOS · Synthetic log-normal distribution | log-MSE | Helped |
| Use SAGA-based variance reduction instead of standard SPOS | SPOS · Australian, Pima, Diabetic, SUSY | testing accuracy | Helped |
| Use SVRG-based variance reduction instead of standard SPOS | SPOS · Australian, Pima, Diabetic, SUSY | testing accuracy | Helped |
| Use SVRG-POS+ instead of SVRG-POS | SPOS · SUSY | testing accuracy | Helped |
| Use SAGA-POS instead of SVRG-POS or SVRG-POS+ | SPOS · Australian, Pima, Diabetic, SUSY | convergence speed | Helped |
| Use SAGA-POS instead of SAGA-LD | variance-reduced SGLD · Australian, Pima, Diabetic, SUSY | convergence speed | Helped |
| Use SVRG-POS instead of SVRG-LD | variance-reduced SGLD · Australian, Pima, Diabetic, SUSY | convergence speed | Helped |
| Use SVRG-LD instead of standard SGLD | SGLD · Pima | convergence speed | Hurt |
| Increase the number of particles (ablation) | SAGA-POS and SVRG-POS · Australian and Pima | testing log-likelihood | Helped |
Closest papers by meaning
- On the Theory of Variance Reduction for Stochastic Gradient Monte Carlo (ICML 2018 · similarity 0.91)
- Variance Reduction in Stochastic Gradient Langevin Dynamics (NeurIPS 2016 · similarity 0.90)
- Improved Convergence Rate of Stochastic Gradient Langevin Dynamics with Variance Reduction and its Application to Optimization (NeurIPS 2022 · similarity 0.90)
- De-randomizing MCMC dynamics with the diffusion Stein operator (NeurIPS 2021 · similarity 0.90)
- Faster Sampling via Stochastic Gradient Proximal Sampler (ICML 2024 · similarity 0.89)
- Path-Guided Particle-based Sampling (ICML 2024 · 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.