Research map / Probabilistic and scientific modeling / Variational and generative sampling
Information Estimation with Discrete Diffusion
Alberto Foresti, Giulio Franzese, Pietro Michiardi
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 INFO-SEDD instead of embedding-trick neural estimators on high-dimensional discrete synthetic data | MI estimation · High-dim synthetic MI (MI=50, D=50) | MI estimate (true 50): 47.77 vs best baseline 32.60 (MINDE) | Improved |
| use INFO-SEDD in low-dimensional synthetic benchmark | MI estimation · Low-dim synthetic MI (D=10) | MI estimate | No clear effect |
| use INFO-SEDD instead of GAN-DIME/SMILE etc. for training convergence | MI estimators · High-dim synthetic | epochs to converge | Improved |
| use INFO-SEDD instead of variational estimators for memory | MI estimators · High-dim synthetic (MI=50, D=50) | max memory (MB): 3180.49 -> 1666.30 | Improved |
| use INFO-SEDD instead of MINDE for runtime | MI estimators · High-dim synthetic (MI=50, D=50) | runtime per epoch (s): 4.68 -> 7.06 | Hurt |
| use INFO-SEDD-C instead of INFO-SEDD-J for label-vs-DNA MI (ablation) | INFO-SEDD · Human vs. worm consistency test | MI consistency | Improved |
| use INFO-SEDD instead of variational estimators on text consistency test | MI estimation · SummEval consistency test | MI consistency with rho | Improved |
Closest papers by meaning
- Information-Theoretic Discrete Diffusion (NeurIPS 2025 · similarity 0.88)
- Approximating mutual information of high-dimensional variables using learned representations (NeurIPS 2024 · similarity 0.87)
- Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution (ICML 2024 · similarity 0.86)
- Steering Masked Discrete Diffusion Models via Discrete Denoising Posterior Prediction (ICLR 2025 · similarity 0.86)
- Simple Guidance Mechanisms for Discrete Diffusion Models (ICLR 2025 · similarity 0.85)
- Scalable Discrete Diffusion Samplers: Combinatorial Optimization and Statistical Physics (ICLR 2025 · 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.
