RICA replaces ICA's global generative model with local Riemannian geometry, introducing a disentanglement tensor based on the Hessian of the log-likelihood and Ricci curvature to measure pointwise disentanglement, which recovers sources across manifolds in controlled tests.
Riemannian metric learning: Closer to you than you imagine
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
representative citing papers
Global uniqueness with Lipschitz stability for two reaction coefficients and logarithmic stability for initial condition in a nonlinear cell invasion PDE, plus a decoupled numerical reconstruction method.
Riemannian archetypal analysis projects data onto a manifold of geodesically convex archetype combinations via pullback geometry on deformed star distributions.
Starfield uses a traffic-derived Riemannian metric on the satellite shell to select demand-aware ISLs, yielding up to 30% fewer hops and 15% better stretch than grid topologies in Starlink Phase 1 simulations.
Iso-Riemannian descent algorithm with convergence analysis under iso-convexity, iso-monotonicity and iso-Lipschitz conditions for optimization on learned Riemannian manifolds from data.
Retrieval from out-of-domain foundation models enables personalization of a lightweight transformer for stress detection, yielding +3.92% accuracy and +4.76% F1 gains on WESAD without user labels.
Introduces world-task factorization for robot policies using Bayesian evidence and AICON graph plus learned modulator, outperforming baselines with zero-shot generalization in heterogeneous robotics settings.
citing papers explorer
-
Disentanglement Beyond Generative Models with Riemannian ICA
RICA replaces ICA's global generative model with local Riemannian geometry, introducing a disentanglement tensor based on the Hessian of the log-likelihood and Ricci curvature to measure pointwise disentanglement, which recovers sources across manifolds in controlled tests.
-
Recovering the initial condition and physical coefficients in a nonlinear PDE model of cell invasion
Global uniqueness with Lipschitz stability for two reaction coefficients and logarithmic stability for initial condition in a nonlinear cell invasion PDE, plus a decoupled numerical reconstruction method.
-
Riemannian Archetypal Analysis: Interpretable non-linear data analysis on deformed star distributions
Riemannian archetypal analysis projects data onto a manifold of geodesically convex archetype combinations via pullback geometry on deformed star distributions.
-
Starfield: Demand-Aware Satellite Topology Design for Low-Earth Orbit Mega Constellations
Starfield uses a traffic-derived Riemannian metric on the satellite shell to select demand-aware ISLs, yielding up to 30% fewer hops and 15% better stretch than grid topologies in Starlink Phase 1 simulations.
-
Iso-Riemannian Optimization on Learned Data Manifolds
Iso-Riemannian descent algorithm with convergence analysis under iso-convexity, iso-monotonicity and iso-Lipschitz conditions for optimization on learned Riemannian manifolds from data.
-
Retrieval-Augmented Personalization with Foundation Models for Wearable Stress Detection
Retrieval from out-of-domain foundation models enables personalization of a lightweight transformer for stress detection, yielding +3.92% accuracy and +4.76% F1 gains on WESAD without user labels.
-
World-Task Factorization for Robot Learning
Introduces world-task factorization for robot policies using Bayesian evidence and AICON graph plus learned modulator, outperforming baselines with zero-shot generalization in heterogeneous robotics settings.