Research map / Learning theory and algorithms / Sample complexity
Minimax-Optimal Location Estimation
Shivam Gupta, Jasper C.H. Lee, Eric Price, Paul Valiant
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 Algorithm 1 or Algorithm 4 instead of the MLE | location estimation · Synthetic piecewise linear distribution, n=10 | point error at 90% error rate: 25% smaller error | Improved |
| Algorithm 1 versus Algorithm 4 | location estimation · Synthetic piecewise linear distribution, n=10 | point error at 90% target: 2% better at 90%, worse over most of the range | Mixed |
| 0.3-smoothed MLE versus plain MLE | MLE · Synthetic piecewise linear distribution, n=10 | point error CDF | Improved |
Closest papers by meaning
- Finite-Sample Maximum Likelihood Estimation of Location (NeurIPS 2022 · similarity 0.90)
- Maximum Likelihood Estimation is All You Need for Well-Specified Covariate Shift (ICLR 2024 · similarity 0.81)
- Minimax Optimal Two-Stage Algorithm For Moment Estimation Under Covariate Shift (ICLR 2025 · similarity 0.81)
- Sub-Gaussian Confidence Intervals for Heavy-Tailed Data: Characterizing the Limits of Inference (NeurIPS 2026 · similarity 0.80)
- Stochastic Localization via Iterative Posterior Sampling (ICML 2024 · similarity 0.79)
- Instance-Optimality for Private KL Distribution Estimation (NeurIPS 2025 · similarity 0.79)
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.
