Info geometry note: categorical distributions form both a mixture and exponential family
FrnkNlsn · x · 2026-09-18
A short technical note: in information geometry, the family of categorical distributions forms both a mixture family and an exponential family. The exponential-family natural reparameterization is handy because it allows unconstrained optimization over the full space, avoiding the need for constrained optimization on the probability simplex.
More from Research
- Weeks after Navier-Stokes, Hodge Conjecture reportedly cracked: Millennium Problems falling fast — haider1 · 2026-09-18
- Meaning Spark Labs experiments with inference-time metacognitive scaffolding for LLMs — PeterBowdenLive · 2026-09-18
- Virtual cell model researcher joins Cellular Intelligence to transform cell therapies — arjunrajlab · 2026-09-18
- AI text watermarking can make models more vulnerable to adversarial prompts — luisdans · 2026-09-18
- Jack Clark defends OpenAI's RSI measurement research as the '26%' figure spreads — jackclarkSF · 2026-09-18
- Salesforce releases xLAM-2: large action models extended to multi-turn agentic interactions, fully open-sourced — huan__wang · 2026-09-18