Research map / Learning theory and algorithms / Matrix and tensor methods
Learning Set Functions that are Sparse in Non-Orthogonal Fourier Bases
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 the non-orthogonal model 4 basis with SSFT instead of WHT recovery | Facility locations functions · Facility locations, |N|=50 | relative reconstruction error: 0.001744 -> 0 | Helped |
| Use model 4 SSFT rather than R-WHT | Facility locations functions · Facility locations, |N|=100 | relative reconstruction error: 0.000546 -> 0 | Helped |
| Apply random one-hop filtering before SSFT | SSFT · MRVM local bidders | relative reconstruction error: 0.5657 ± 0.4900 -> 0 ± 0 | Helped |
| Apply random one-hop filtering before SSFT | SSFT · MRVM regional bidders | relative reconstruction error: 0.0118 ± 0.0071 -> 0 ± 0 | Helped |
| Apply random one-hop filtering before SSFT | SSFT · MRVM national bidders | relative reconstruction error: 0.0123 ± 0.0014 -> 0.0149 ± 0.0089 | Hurt |
| Use SSFT+ rather than H-WHT | MRVM local bidders · MRVM local bidders | number of queries (in thousands): 781 ± 0 -> 229 ± 73 | Helped |
| Use SSFT+ rather than H-WHT | MRVM regional bidders · MRVM regional bidders | number of queries (in thousands): 781 ± 0 -> 646 ± 12 | Helped |
| Use model 4 SSFT instead of R-WHT | Facility locations functions · Facility locations, |N|=50 | number of queries: 2,103K -> 10K | Helped |
Closest papers by meaning
- Efficiently Learning Fourier Sparse Set Functions (NeurIPS 2019 · similarity 0.92)
- Distribution Free Fourier Sparsity Testing (NeurIPS 2026 · similarity 0.88)
- Learning Set Functions with Implicit Differentiation (AAAI 2025 · similarity 0.84)
- Efficiently Learning Significant Fourier Feature Pairs for Statistical Independence Testing (NeurIPS 2024 · similarity 0.83)
- On the Complexity of Learning Sparse Functions with Statistical and Gradient Queries (NeurIPS 2024 · similarity 0.83)
- Fourier Sliced-Wasserstein Embedding for Multisets and Measures (ICLR 2025 · similarity 0.82)
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.