Controlling Dependence in Implicit Generative Models via Spread Mutual Information
arXiv:2610.10021v1 Announce Type: new Abstract: Mutual information (MI) provides an objective for suppressing or encouraging statistical dependence in implicit generative models. However, direct MI evaluation is challenging in implicit models due to typically intractable densities. A remedy is esti…
Read the full story at arXiv stat.ML ↗
Timeline · 1 report
- 2026-10-08 04:00 · arXiv stat.ML
Controlling Dependence in Implicit Generative Models via Spread Mutual Information