Research map / Learning theory and algorithms / Matrix and tensor methods
Online robust non-stationary estimation
Abishek Sankararaman, Murali Balakrishnan
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 learning rate 1/T^alpha with alpha<1 instead of 1/(t+1) when the mean drifts (ablation) | clipped-SGD · Time-varying mean estimation (synthetic) | regret | Improved |
| decrease alpha as drift Phi_T or corruption count Lambda_T increases (ablation) | clipped-SGD · Mean estimation, 10000 steps | regret | Improved |
| tune learning rate alpha for linear regression under drift and corruptions (ablation) | clipped-SGD · Linear regression (appendix Figure 3) | regret | Improved |
Closest papers by meaning
- Near-Optimal Streaming Heavy-Tailed Statistical Estimation with Clipped SGD (NeurIPS 2024 · similarity 0.91)
- Anytime Guarantees under Heavy-Tailed Data (AAAI 2022 · similarity 0.88)
- Statistical Guarantees for High-Dimensional Stochastic Gradient Descent (NeurIPS 2025 · similarity 0.86)
- Adaptive Estimation and Learning under Temporal Distribution Shift (ICML 2025 · similarity 0.86)
- High-Probability Bound for Non-Smooth Non-Convex Stochastic Optimization with Heavy Tails (ICML 2024 · similarity 0.85)
- Adaptive Data Collection for Robust Learning Across Multiple Distributions (ICML 2025 · similarity 0.85)
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.
