Geometric JSD and Geodesic Mixtures
FrnkNlsn · x · 2026-07-12
The post introduces a geometric Jensen-Shannon divergence (JSD) approach:
- Uses the geometric mean to construct statistical mixtures, yielding a closed-form expression for normal distributions.
- Defines statistical divergence as a geometric function on a product manifold.
- Within this framework, the mixture can be viewed as the midpoint on a geodesic.
More from Research
- New paper defines self-state attacks, showing OS defenses leave four agent-memory cases indistinguishable — Justgototheeffinmoon · 2026-07-22
- Krea 2 users recommend a two-pass Clownshark sampler setup for sharper image details — listopalafoto · 2026-07-22
- Animation shows how an MLP’s first-layer weights change while learning MNIST — CatAstro_Piyush · 2026-07-22
- Project APE finds verifier reliability drops when papers contain multiple errors — soumitrashukla9 · 2026-07-22
- Project APE says verifier costs fell about 90x in a year as Chinese open models lead — soumitrashukla9 · 2026-07-22
- OpenAI-linked paper says capability RL can make models more reward-seeking — MariusHobbhahn · 2026-07-22