Research map / Learning theory and algorithms / Sample complexity
A Sharp Error Analysis for the Fused Lasso, with Application to Approximate Changepoint Screening
Kevin Lin, James L Sharpnack, Alessandro Rinaldo, Ryan J Tibshirani
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 sharper analysis (lower interpolant) with tuning λ=(nWn)^{1/4} for fused lasso | fused lasso · sparse changepoints, s0=O(1), evenly spaced | expected squared error rate | Improved |
| Fused lasso rate is suboptimal vs. Guntuboyina et al. (2017) sharper log n/n rate | fused lasso error analysis · sparse changepoints, s0=O(1), Wn=Θ(n) | expected squared error rate | No clear effect |
| Extend fused lasso analysis to exponential family (Poisson, binomial) data with bounded parameters | fused lasso exponential family extension · Poisson/binomial changepoint data | expected squared error rate | Mixed |
| Post-process fused lasso changepoints with Haar-like filter to discard spurious changepoints | fused lasso estimated changepoints · approximate changepoint recovery, s0=O(1) | Hausdorff distance bound | Improved |
Closest papers by meaning
- An Efficient Two Step Algorithm for High Dimensional Change Point Regression Models Without Grid Search (JMLR 2019 · similarity 0.86)
- Feature Adaptation for Sparse Linear Regression (NeurIPS 2023 · similarity 0.86)
- Celer: a Fast Solver for the Lasso with Dual Extrapolation (ICML 2018 · similarity 0.86)
- Variance estimation in graphs with the fused lasso (JMLR 2024 · similarity 0.85)
- The Complete Lasso Tradeoff Diagram (NeurIPS 2020 · similarity 0.85)
- Robust Sparse Regression with Non-Isotropic Designs (NeurIPS 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.
