New IEEE IT paper: geometric Jensen-Shannon divergence between Gaussian measures on Hilbert space
FrnkNlsn · x · 2026-10-28
Frank Nielsen (IEEE Fellow) and Hà Quang Minh published 'Geometric Interpolation and Geometric Jensen-Shannon Divergence Between Gaussian Measures On Hilbert Space' in IEEE Transactions on Information Theory. The paper derives a closed-form expression for the geometric Jensen-Shannon divergence between Gaussian measures in infinite-dimensional Hilbert space, defines a Regularized version via infinite-dimensional Log-Det divergence on trace-class operators that recovers the exact divergence as regularization vanishes, and proves consistent, efficient finite-dimensional approximations for centered Gaussian processes with dimension-independent sample complexity.
More from Research
- EMNLP 2026 to host tutorial on failure modes in agentic AI, two years after agent risks debut — wzenus · 2026-10-28
- 'The free energy principle is free because it's not that useful' — researchers clash over FEP — mjdramstead · 2026-10-28
- 2020 physics paper links learning rate, Hessian and gradient noise via fluctuation-dissipation theorem — burny_tech · 2026-10-28
- Jeremy Avigad: the AI debate belongs at the center with us, not the AI — Machine Learning Street Talk · 2026-10-28
- Meituan LongCat's FVQ makes discrete visual tokens match continuous representations — meituan-longcat · 2026-10-28
- Single neuron steering works far worse than contrastive-pair control vectors in practice — burny_tech · 2026-10-28