Research map / Learning theory and algorithms / Prediction and decision losses
Locality-Sensitive Hashing for f-Divergences: Mutual Information Loss and Beyond
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 |
|---|---|---|---|
| Vary the GJS parameter across λ=1/2, 1/3, and 1/10 (ablation) | GJS LSH · Fashion MNIST, MNIST, and CIFAR-10 | precision | No clear effect |
| Increase the number of compound hash functions L from 20 to 40 (ablation) | GJS LSH · Fashion MNIST, MNIST, and CIFAR-10 | precision and speed-up factor | Mixed |
| Increase the number of concatenated hash functions K (ablation) | JS LSH · Fashion MNIST, MNIST, and CIFAR-10 | speed-up factor | Helped |
Closest papers by meaning
- S2JSD-LSH: A Locality-Sensitive Hashing Schema for Probability Distributions (AAAI 2017 · similarity 0.91)
- Approximate Nearest Neighbor Search through Modern Error-Correcting Codes (ICLR 2023 · similarity 0.88)
- K-Nearest Neighbors Hashing (CVPR 2019 · similarity 0.88)
- Learning Space Partitions for Nearest Neighbor Search (ICLR 2020 · similarity 0.87)
- Locality Sensitive Hashing for p-Exponential Kernels with Applications to Density Estimation (NeurIPS 2026 · similarity 0.87)
- Connecting Jensen–Shannon and Kullback–Leibler Divergences: A New Bound for Representation Learning (NeurIPS 2025 · similarity 0.84)
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.