Research map / Learning theory and algorithms / Sample complexity
Learning with little mixing
Ingvar Ziemann, Stephen Tu
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 |
|---|---|---|---|
| assume trajectory hypercontractivity with alpha > 1 instead of alpha = 1 | least-squares estimator on dependent time-series data · theory: excess risk bound | mixing-time dependence of lower-order term | Improved |
| replace blocking-based effective sample size with one-sided isometry analysis | least-squares estimator · theory: excess risk bound | leading excess risk term | Improved |
| instantiate main result to stable GLM transition dynamics | system identification with generalized linear model transitions · stable GLM dynamics | excess risk rate | Improved |
| instantiate main result to stable linear dynamical systems | linear system identification · stable LDS | excess risk rate | No clear effect |
| allow slower-than-geometric polynomial decay of correlations in covariate process | least-squares estimator · theory: Markov chain covariates | iid rate after burn-in | No clear effect |
Closest papers by meaning
- Sharp Rates in Dependent Learning Theory: Avoiding Sample Size Deflation for the Square Loss (ICML 2024 · similarity 0.89)
- Non-stationary Online Learning for Curved Losses: Improved Dynamic Regret via Mixability (ICML 2025 · similarity 0.85)
- Statistical Guarantees for High-Dimensional Stochastic Gradient Descent (NeurIPS 2025 · similarity 0.84)
- The Collusion of Memory and Nonlinearity in Stochastic Approximation With Constant Stepsize (NeurIPS 2024 · similarity 0.84)
- The High Line: Exact Risk and Learning Rate Curves of Stochastic Adaptive Learning Rate Algorithms (NeurIPS 2024 · similarity 0.84)
- Persistent-Transient Policy Evaluation for Markov Chains via Minimal Peripheral Quotients (NeurIPS 2026 · similarity 0.84)
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.
