Research map / Learning theory and algorithms / Sample complexity
Learning a distance measure from the information-estimation geometry of data
Guy Ohayon, Pierre-Etienne H Fiquet, Florentin Guth, Jona Ballé, Eero P Simoncelli
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 the learned-function generalized IEM (IEM_f_omega) instead of identity or quadratic f (ablation) | IEM · TID2013, LIVE, CSIQ and TQD textures | SRCC with human judgments | Improved |
| use quadratic f (IEM_sq, Gamma=10^6) instead of identity f (ablation) | IEM · TID2013, LIVE, CSIQ | SRCC with human MOS | Hurt |
| use quadratic f (IEM_sq, Gamma=10^6) on texture pairs (ablation) | IEM · TQD textures | agreement with human judgments | Improved |
| minimize IEM instead of DISTS under a fixed PSNR constraint | maximum differentiation competition vs PSNR · PSNR-constrained image optimization (10dB) | perceptual quality of optimized image | Improved |
Closest papers by meaning
- Sampling Binary Data by Denoising through Score Functions (ICML 2025 · similarity 0.84)
- On the Posterior Distribution in Denoising: Application to Uncertainty Quantification (ICLR 2024 · similarity 0.84)
- Interpretable Diffusion via Information Decomposition (ICLR 2024 · similarity 0.83)
- Likelihood Training of Cascaded Diffusion Models via Hierarchical Volume-preserving Maps (ICLR 2024 · similarity 0.83)
- Information-Theoretic Discrete Diffusion (NeurIPS 2025 · similarity 0.83)
- Generalization in diffusion models arises from geometry-adaptive harmonic representations (ICLR 2024 · similarity 0.83)
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.
