Research map / Optimization / Nonconvex and smooth optimization
Adaptive Importance Sampling for Finite-Sum Optimization and Sampling with Decreasing Step-Sizes
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 adaptive importance sampling with Avare instead of the compared samplers | SGD on synthetic binary classification · Synthetic | dynamic regret | Helped |
| Use adaptive importance sampling with Avare instead of the compared samplers | Softmax regression · MNIST | dynamic regret | Helped |
| Use adaptive importance sampling with Avare instead of the compared samplers | Softmax regression · IJCNN1 | optimization performance | Helped |
| Use adaptive importance sampling with Avare instead of the compared samplers | Softmax regression · CIFAR10 | optimization performance | No clear effect |
| Use a minibatch estimator that samples without replacement and corrects each draw to preserve unbiasedness | Importance-sampled minibatch gradient estimation · Minibatch sampling | gradient-estimator variance | Helped |
Closest papers by meaning
- Safe Adaptive Importance Sampling (NeurIPS 2017 · similarity 0.91)
- Adaptive Sampling Probabilities for Non-Smooth Optimization (ICML 2017 · similarity 0.90)
- Adaptive Regret for Bandits Made Possible: Two Queries Suffice (ICLR 2024 · similarity 0.89)
- Only Pay for What Is Uncertain: Variance-Adaptive Thompson Sampling (ICLR 2024 · similarity 0.88)
- Small steps no more: Global convergence of stochastic gradient bandits for arbitrary learning rates (NeurIPS 2024 · similarity 0.88)
- Variance-Aware Feel-Good Thompson Sampling for Contextual Bandits (NeurIPS 2025 · 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.