Research map / Learning theory and algorithms / Sample complexity
Higher-Order Total Variation Classes on Grids: Minimax Theory and Trend Filtering Methods
Veeranjaneyulu Sadhanala, Yu-Xiang Wang, James L Sharpnack, 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 Kronecker trend filtering (KTF) penalty instead of graph trend filtering (GTF) penalty on 2d grids | trend filtering on 2d grid graphs · 2d grids, minimax theory | estimation error rate (MSE upper bound order) | No clear effect |
| Use Kronecker trend filtering (KTF) penalty instead of graph trend filtering (GTF) penalty | trend filtering on d-dimensional grids · Holder smooth signals | adaptation to Holder rate n^{-(k+1)/(k+2)} for d=2 | Improved |
| Set penalty order k=0 (TV denoising, lambda ~ log n) instead of higher-order trend filtering | GTF / TV denoising on 2d grids · 2d grids, minimax theory | MSE upper bound order | No clear effect |
| Use the GTF penalty instead of KTF penalty (discrete derivatives at grid boundary) | GTF class containment of discretized Holder class · discretized Holder class | containment of Holder class in class | Hurt |
Closest papers by meaning
- Total Variation Classes Beyond 1d: Minimax Rates, and the Limitations of Linear Smoothers (NeurIPS 2016 · similarity 0.90)
- Trend Filtering on Graphs (JMLR 2016 · similarity 0.87)
- The Art of BART: Minimax Optimality over Nonhomogeneous Smoothness in High Dimension (JMLR 2023 · similarity 0.87)
- Directional Smoothness and Gradient Methods: Convergence and Adaptivity (NeurIPS 2024 · similarity 0.86)
- Generalized Smooth Variational Inequalities: Methods with Adaptive Stepsizes (ICML 2024 · similarity 0.85)
- Efficiently Escaping Saddle Points under Generalized Smoothness via Self-Bounding Regularity (NeurIPS 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.
