Research map / Learning theory and algorithms / Matrix and tensor methods
Iterative Hard Thresholding with Adaptive Regularization: Sparser Solutions Without Sacrificing Runtime
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 |
|---|---|---|---|
| Add adaptive weighted ℓ2 regularization to IHT | IHT · Sparse convex optimization | solution sparsity: O(sκ^2) -> O(sκ) | Helped |
| Add adaptive weighted ℓ2 regularization to IHT | IHT · year regression dataset, sparsity s=11 | normalized excess loss: 17.3% less | Helped |
| Add adaptive weighted ℓ2 regularization to IHT | IHT · rcv1 binary classification dataset, sparsity s=10 | normalized excess loss: 17.2% less | Helped |
| Add adaptive weighted ℓ2 regularization to IHT | IHT · year regression dataset, sparsity values 1 to 30 | relative excess error reduction: up to 40% | Helped |
| Add adaptive weighted ℓ2 regularization to IHT | IHT · Hard synthetic IHT instance | loss reduction: more than 70% | Helped |
| Use a larger weight step size c (ablation) | Regularized IHT · year regression dataset | runtime | Helped |
| Use a larger weight step size c (ablation) | Regularized IHT · year regression dataset | error rate | Hurt |
| Use a smaller weight step size c (ablation) | Regularized IHT · year regression dataset | error rate | Helped |
| Use a smaller weight step size c (ablation) | Regularized IHT · year regression dataset | number of iterations | Hurt |
Closest papers by meaning
- Dual Iterative Hard Thresholding: From Non-convex Sparse Minimization to Non-smooth Concave Maximization (ICML 2017 · similarity 0.93)
- Sparse Convex Optimization via Adaptively Regularized Hard Thresholding (ICML 2020 · similarity 0.93)
- Fast Iterative Hard Thresholding Methods with Pruning Gradient Computations (NeurIPS 2024 · similarity 0.90)
- Iterative Regularization with k-support Norm: An Important Complement to Sparse Recovery (AAAI 2024 · similarity 0.88)
- Optimization over Sparse Support-Preserving Sets: Two-Step Projection with Global Optimality Guarantees (ICML 2025 · similarity 0.86)
- Smoothing Proximal Gradient Methods for Nonsmooth Sparsity Constrained Optimization: Optimality Conditions and Global Convergence (ICML 2024 · similarity 0.86)
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.