Research map / Optimization / Nonconvex and smooth optimization
PAGE: A Simple and Optimal Probabilistic Gradient Estimator for Nonconvex Optimization
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 probabilistic switching between minibatch SGD and the recursive gradient update | PAGE · Nonconvex finite-sum | gradient complexity: O(n+\frac{\sqrt{n}}{\epsilon^2}) | Helped |
| Use probabilistic switching between minibatch SGD and the recursive gradient update | PAGE · Nonconvex online | gradient complexity: O(b+\frac{\sqrt{b}}{\epsilon^2}) | Helped |
| Set p_t=1, removing probabilistic reuse (ablation) | PAGE · Nonconvex finite-sum | gradient complexity: O(n+\frac{\sqrt{n}}{\epsilon^2}) -> O\left(\frac{n}{\epsilon^2}\right) | Hurt |
| Set p_t=1, removing probabilistic reuse (ablation) | PAGE · Nonconvex online | gradient complexity: O(b+\frac{\sqrt{b}}{\epsilon^2}) -> O\left(\frac{\sigma^2}{\epsilon^4}\right) | Hurt |
| Use PAGE instead of SGD | LeNet, VGG, and ResNet · MNIST and CIFAR-10 | training loss versus gradient computations | Helped |
| Use PAGE instead of SGD | LeNet, VGG, and ResNet · MNIST and CIFAR-10 | test accuracy | Helped |
| Use PAGE instead of SGD | ResNet · MNIST and CIFAR-10 | test loss versus gradient computations | Helped |
| Use PAGE instead of SGD | ResNet · MNIST and CIFAR-10 | training accuracy versus gradient computations | Helped |
Closest papers by meaning
- A Simple Proximal Stochastic Gradient Method for Nonsmooth Nonconvex Optimization (NeurIPS 2018 · similarity 0.91)
- Proximal Stochastic Methods for Nonsmooth Nonconvex Finite-Sum Optimization (NeurIPS 2016 · similarity 0.90)
- High-probability complexity bounds for stochastic non-convex minimax optimization (NeurIPS 2024 · similarity 0.88)
- A Bregman Proximal Stochastic Gradient Method with Extrapolation for Nonconvex Nonsmooth Problems (AAAI 2024 · similarity 0.87)
- High-Probability Bound for Non-Smooth Non-Convex Stochastic Optimization with Heavy Tails (ICML 2024 · similarity 0.87)
- Stochastic Optimization with Random Search (NeurIPS 2026 · 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.