Research map / Learning theory and algorithms / Sample complexity
High-dimensional Location Estimation via Norm Concentration for Subgamma Vectors
Shivam Gupta, Jasper C.H. Lee, Eric Price
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 |
|---|---|---|---|
| Extend smoothed MLE analysis to high dimensions using subgamma norm concentration | High-dimensional Global MLE · High-dimensional location estimation | Euclidean estimation error: (1 + \eta) \sqrt{\Tr(\mathcal{I}_R^{-1})/n} + 5 \sqrt{\norm{\mathcal{I}_R^{-1}} \log(4/\delta)/n} | Improved |
| Generalize directional subgaussian norm concentration to vectors with subgamma marginals | Norm concentration bound · Subgamma random vectors | high-probability norm bound: \sqrt{\Tr(\Sigma)} + 4\sqrt{\norm{\Sigma}\log(2/\delta)} + 16\norm{C}\log(2/\delta) + \min(4\norm{C}_F\sqrt{\log(2/\delt | Improved |
| Use root-finding for the empirical score rather than a one-step Newton update | 1D smoothed MLE · 1D location estimation | finite-sample estimation error | Hurt |
Closest papers by meaning
- Nearly $d$-Linear Convergence Bounds for Diffusion Models via Stochastic Localization (ICLR 2024 · similarity 0.85)
- Stochastic Localization via Iterative Posterior Sampling (ICML 2024 · similarity 0.84)
- PAC-Bayes-Chernoff bounds for unbounded losses (NeurIPS 2024 · similarity 0.83)
- Simple and Optimal Sublinear Algorithms for Mean Estimation (NeurIPS 2025 · similarity 0.83)
- Sampling from Binary Quadratic Distributions via Stochastic Localization (ICML 2025 · similarity 0.83)
- Flat Minima in Linear Estimation and an Extended Gauss Markov Theorem (ICLR 2024 · similarity 0.83)
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.
