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.
Information theoretical analysis of multivariate correlation
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
verdicts
UNVERDICTED 4roles
background 2polarities
background 2representative citing papers
Multimodal contrastive learning using multilinear products is fragile to single bad modalities, and a gated version improves top-1 retrieval accuracy on synthetic and real trimodal data.
Spectral partitioning on pairwise mutual-information graphs from agent hidden states detects representational coalitions that behavioral measures miss in multi-agent AI.
A pointwise multivariate information-driven sampling method generates reduced datasets that preserve statistical associations among variables for effective feature queries and analysis.
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.
-
Hidden in the Multiplicative Interaction: Uncovering Fragility in Multimodal Contrastive Learning
Multimodal contrastive learning using multilinear products is fragile to single bad modalities, and a gated version improves top-1 retrieval accuracy on synthetic and real trimodal data.
-
Hidden Coalitions in Multi-Agent AI: A Spectral Diagnostic from Internal Representations
Spectral partitioning on pairwise mutual-information graphs from agent hidden states detects representational coalitions that behavioral measures miss in multi-agent AI.
-
Multivariate Pointwise Information-Driven Data Sampling and Visualization
A pointwise multivariate information-driven sampling method generates reduced datasets that preserve statistical associations among variables for effective feature queries and analysis.