Research map / Learning theory and algorithms / Kernels and regression theory
SignRFF: Sign Random Fourier Features
Xiaoyun Li, Ping Li
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 |
|---|---|---|---|
| replace stochastic quantization (SQ-RFF) with deterministic sign quantization of RFF | random Fourier feature hashing · SIFT, MNIST, CIFAR | recall@100 | Improved |
| replace SignRP with SignRFF | LSH on cosine similarity · high-similarity datasets (CIFAR) | recall@100 | Mixed |
| replace KLSH with SignRFF | kernel hashing · SIFT, MNIST, CIFAR, b = 512 | recall@100 | Mixed |
| replace data-dependent hashing (ITQ, SpecH, BRE) with SignRFF | hashing · SIFT, MNIST, CIFAR, b >= 256 | recall@100 | Improved |
| increase bits beyond about 100-200 | data-dependent hashing (ITQ, SpecH, BRE) · SIFT, MNIST | recall@100 | No clear effect |
| replace deep hashing CIB with SignRFF/SignRP/KLSH | unsupervised hashing · CIFAR-VGG, b >= 256 | recall@1000 | Improved |
| use CIB instead of shallow LSH methods | unsupervised hashing · CIFAR-VGG, b <= 64 | recall@1000 | Improved |
| increase bits for CIB | CIB · CIFAR-VGG | recall@1000: 0.3∼0.4 | No clear effect |
| increase Gaussian parameter gamma | SignRFF vs KLSH · SIFT, MNIST, CIFAR, b = 512 | recall@100 | Mixed |
Closest papers by meaning
- TRF: Learning Kernels with Tuned Random Features (AAAI 2022 · similarity 0.84)
- A random matrix analysis of random Fourier features: beyond the Gaussian kernel, a precise phase transition, and the corresponding double descent (NeurIPS 2020 · similarity 0.84)
- Sign-Full Random Projections (AAAI 2019 · similarity 0.83)
- Efficiently Learning Significant Fourier Feature Pairs for Statistical Independence Testing (NeurIPS 2024 · similarity 0.82)
- When and Why SignSGD Outperforms SGD: A Theoretical Study Based on $\ell_1$-norm Lower Bounds (NeurIPS 2026 · similarity 0.81)
- Scaling Laws for Gradient Descent and Sign Descent for Linear Bigram Models under Zipf’s Law (NeurIPS 2025 · similarity 0.80)
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.
