Research map / Learning theory and algorithms / Matrix and tensor methods
Dual Iterative Hard Thresholding: From Non-convex Sparse Minimization to Non-smooth Concave Maximization
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 DIHT instead of IHT or HTP | Sparse linear regression · Synthetic datasets | parameter estimation error | Helped |
| Use DIHT instead of IHT or HTP | Sparse linear regression · Synthetic datasets | percentage of successful support recovery (PSSR) | Helped |
| Use DIHT or SDIHT instead of IHT, HTP, or SVR-GHT | Sparse Huber loss minimization · RCV1 and News20 | running time | Helped |
| Use DIHT or SDIHT instead of primal IHT-style algorithms | Sparse hinge loss minimization · RCV1 and News20 | running time | Helped |
Closest papers by meaning
- Iterative Hard Thresholding with Adaptive Regularization: Sparser Solutions Without Sacrificing Runtime (ICML 2022 · similarity 0.93)
- Learning Sparse Distributions using Iterative Hard Thresholding (NeurIPS 2019 · similarity 0.93)
- Sparse Convex Optimization via Adaptively Regularized Hard Thresholding (ICML 2020 · similarity 0.92)
- Smoothing Proximal Gradient Methods for Nonsmooth Sparsity Constrained Optimization: Optimality Conditions and Global Convergence (ICML 2024 · similarity 0.89)
- Fast Iterative Hard Thresholding Methods with Pruning Gradient Computations (NeurIPS 2024 · similarity 0.89)
- Optimization over Sparse Support-Preserving Sets: Two-Step Projection with Global Optimality Guarantees (ICML 2025 · similarity 0.88)
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.