Research map / Optimization / Optimizers
Online Variance Reduction with Mixtures
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 VRM with a mixture of k-DPP sampling distributions instead of uniform sampling | Minibatch SGD for synthetic linear regression · Synthetic linear regression | iterations to reach a given error: 1.4× speedup | Helped |
| Use VRM to select among prioritized replay hyperparameter settings | DQN · Cartpole | reward | Helped |
| Use VRM mixture sampling instead of uniform sampling | Minibatch k-means · KDD, CSN | relative error | Helped |
| Use VRM mixture sampling instead of uniform sampling | Minibatch k-means · MNIST | relative error | No clear effect |
| Use VRM to adapt sampling toward the middle blobs containing support vectors | Online gradient descent for SVM · Six-blob synthetic dataset | iterations to reach a given accuracy | Helped |
Closest papers by meaning
- Adaptive Importance Sampling for Finite-Sum Optimization and Sampling with Decreasing Step-Sizes (NeurIPS 2020 · similarity 0.89)
- Stochastic Optimization with Variance Reduction for Infinite Datasets with Finite Sum Structure (NeurIPS 2017 · similarity 0.88)
- An Improved Analysis and Rates for Variance Reduction under Without-replacement Sampling Orders (NeurIPS 2021 · similarity 0.87)
- Double Variance Reduction: A Smoothing Trick for Composite Optimization Problems without First-Order Gradient (ICML 2024 · similarity 0.87)
- Adaptive Variance Reduction for Stochastic Optimization under Weaker Assumptions (NeurIPS 2024 · similarity 0.86)
- An Online Adaptive Sampling Algorithm for Stochastic Difference-of-convex Optimization with Time-varying Distributions (ICML 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.