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.
hub
IEEE Transactions on Pattern Analysis and Machine Intelligence 35(8), 1798–1828 (2013)
16 Pith papers cite this work. Polarity classification is still indexing.
16
Pith papers citing it
hub tools
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 16roles
background 1polarities
background 1representative citing papers
A new framework shows concept subspaces are not unique, estimator choice affects containment and disentanglement, LEACE works well but generalizes poorly, and HuBERT encodes phone info as contained and disentangled from speaker info while speaker info resists compact containment.
LHSD uses spectral filtering on the log-density Hessian to isolate tangent directions from noise and estimate local intrinsic dimension scalably via Stochastic Lanczos Quadrature.
Applies gentlest ascent dynamics and stable manifold methods to compute domain of attraction boundaries for stable equilibria in synchronous-generator power system models.
Task-aligned supervised geometric stability predicts linear steerability with high accuracy while unsupervised stability detects representational drift earlier and with lower false alarms than CKA or Procrustes.
A GAN framework is trained on EAGLE simulation merger trees to generate new realistic trees for semi-analytic galaxy models at modest computational cost.
Derives an asymptotic equivalent for the Representation Gap in equivariant diffusion models, showing it depends primarily on the intrinsic dimension of the task.
DAR replaces GAP with an attention-based aggregation module retrained jointly with the classifier head to disentangle core from spurious features and outperforms DFR on multiple datasets.
Soft Learning optimally combines heterogeneous ML specialists via cross-validated non-negative least squares, achieving top performance on 70% of 37 datasets with formal guarantees and 72-435x CPU speedups over deep networks.
Disease trajectory embeddings from longitudinal EHR data serve as structural priors to enhance multi-organ IDP representation learning, improving AUC and MAE for disease prediction across 159 conditions in UK Biobank.
In one Parkinson patient, higher occlusion produced the smallest longitudinal shift in PCA gait latent space over 11 weeks while immediate performance stayed comparable, supporting a viability level focused on sustained organization.
Bayesian-ARGOS is a hybrid frequentist-Bayesian method that discovers equations from limited noisy observations more efficiently than SINDy or bootstrap-ARGOS while adding uncertainty quantification.
In one Parkinsonian subject, a neural network approximates the observed shift in PCA gait latent space between two sessions across six occlusal conditions.
A transition graph model with utility and evidence counts learns behaviors from state history and feedback, showing performance comparable to neural networks on Atari Breakout.
A rank reduction autoencoder combined with classification predicts numerical dispersion in automotive crash simulations more effectively than random forests when using wavelet or slope signal inputs.
In a single Parkinson's patient, gait conditions with comparable linear performance metrics showed different temporal organizations in dynamical state space and unsupervised latent embeddings when vertical occlusion dimension was varied.
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.
-
A framework for analyzing concept representations in neural models
A new framework shows concept subspaces are not unique, estimator choice affects containment and disentanglement, LEACE works well but generalizes poorly, and HuBERT encodes phone info as contained and disentangled from speaker info while speaker info resists compact containment.
-
Local Hessian Spectral Filtering for Robust Intrinsic Dimension Estimation
LHSD uses spectral filtering on the log-density Hessian to isolate tangent directions from noise and estimate local intrinsic dimension scalably via Stochastic Lanczos Quadrature.
-
Calculating Domain of Attraction Boundary of Power Systems Based on the Gentlest Ascent Dynamics
Applies gentlest ascent dynamics and stable manifold methods to compute domain of attraction boundaries for stable equilibria in synchronous-generator power system models.
-
The Geometric Canary: Predicting Steerability and Detecting Drift via Representational Stability
Task-aligned supervised geometric stability predicts linear steerability with high accuracy while unsupervised stability detects representational drift earlier and with lower false alarms than CKA or Procrustes.
-
A Halo Merger Tree Generation and Evaluation Framework
A GAN framework is trained on EAGLE simulation merger trees to generate new realistic trees for semi-analytic galaxy models at modest computational cost.
-
Representation Gap: Explaining the Unreasonable Effectiveness of Neural Networks from a Geometric Perspective
Derives an asymptotic equivalent for the Representation Gap in equivariant diffusion models, showing it depends primarily on the intrinsic dimension of the task.
-
Deep Attention Reweighting: Post-Hoc Attention-Based Feature Aggregation in CNNs for Disentangling Core and Spurious Features under Spurious Correlations
DAR replaces GAP with an attention-based aggregation module retrained jointly with the classifier head to disentangle core from spurious features and outperforms DFR on multiple datasets.
-
Soft Learning
Soft Learning optimally combines heterogeneous ML specialists via cross-validated non-negative least squares, achieving top performance on 70% of 37 datasets with formal guarantees and 72-435x CPU speedups over deep networks.
-
From Trajectories to Phenotypes: Disease Progression as Structural Priors for Multi-organ Imaging Representation Learning
Disease trajectory embeddings from longitudinal EHR data serve as structural priors to enhance multi-organ IDP representation learning, improving AUC and MAE for disease prediction across 159 conditions in UK Biobank.
-
From Organization to Viability: A Multi-Level Analysis of Gait Dynamics Under Occlusal Constraint
In one Parkinson patient, higher occlusion produced the smallest longitudinal shift in PCA gait latent space over 11 weeks while immediate performance stayed comparable, supporting a viability level focused on sustained organization.
-
Fast and principled equation discovery from chaos to climate
Bayesian-ARGOS is a hybrid frequentist-Bayesian method that discovers equations from limited noisy observations more efficiently than SINDy or bootstrap-ARGOS while adding uncertainty quantification.
-
From Observed Viability to Internal Predictive Approximation: A Single-Subject Latent-Space Analysis of Gait Dynamics Under Occlusal Constraint
In one Parkinsonian subject, a neural network approximates the observed shift in PCA gait latent space between two sessions across six occlusal conditions.
-
Interpretable experiential learning based on state history and global feedback
A transition graph model with utility and evidence counts learns behaviors from state history and feedback, showing performance comparable to neural networks on Atari Breakout.
-
CRADIPOR: Crash Dispersion Predictor
A rank reduction autoencoder combined with classification predicts numerical dispersion in automotive crash simulations more effectively than random forests when using wavelet or slope signal inputs.
-
Observable Performance Does Not Fully Reflect System Organization: A Multi-Level Analysis of Gait Dynamics Under Occlusal Constraint
In a single Parkinson's patient, gait conditions with comparable linear performance metrics showed different temporal organizations in dynamical state space and unsupervised latent embeddings when vertical occlusion dimension was varied.