Research map / Learning theory and algorithms / Matrix and tensor methods
Interaction Hard Thresholding: Consistent Sparse Quadratic Regression in Sub-quadratic Time and Space
Shuo Yang, Yanyao Shen, Sujay Sanghavi
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 approximate top-element extraction with moderately large b instead of exact top-element extraction | IntHT · Synthetic quadratic regression | parameter estimation error | No clear effect |
| Use approximate top-element extraction with b=360 | IntHT · Synthetic quadratic regression | parameter estimation error | Improved |
| Increase ATEE output-set size b with sparsity K | IntHT · Synthetic quadratic regression | support recovery | Improved |
| Increase batch size m as feature dimension p grows | IntHT with exact top-element extraction · Synthetic quadratic regression | support recovery success rate | Improved |
| Extend interaction modeling from second-order to third-order terms | IntHT · Synthetic third-order interaction regression | parameter estimation error | Improved |
Closest papers by meaning
- Structured Sparse Regression via Greedy Hard Thresholding (NeurIPS 2016 · similarity 0.88)
- A minimax optimal approach to high-dimensional double sparse linear regression (JMLR 2024 · similarity 0.88)
- Sample Efficient Stochastic Gradient Iterative Hard Thresholding Method for Stochastic Sparse Linear Regression with Limited Attribute Observation (NeurIPS 2018 · similarity 0.87)
- Learning Sparse Distributions using Iterative Hard Thresholding (NeurIPS 2019 · similarity 0.87)
- Fast Iterative Hard Thresholding Methods with Pruning Gradient Computations (NeurIPS 2024 · similarity 0.85)
- Robust Sparse Regression with Non-Isotropic Designs (NeurIPS 2024 · 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.
