Separation Is a Riesz Energy: How Many Environments Does ICA Need?
cs.LG, cs.IT, math.IT, stat.ML
Submitted: 2026-11-04
Updated: 2026-11-07
Terminology
Sources
- Sum-of-squares lower bounds for Non-Gaussian Component Analysis
- Learnability and Competition in High-Dimensional Multi-Component ICA
- A randomized algorithm for simultaneously diagonalizing symmetric matrices by congruence
- Finite-Sample Analysis of Nonlinear Independent Component Analysis:Sample Complexity and Identifiability Bounds
- Relative perturbation bounds with applications to empirical covariance operators
- Beyond identifiability: Learning causal representations with few environments and finite samples
- Computing Truncated Joint Approximate Eigenbases for Model Order Reduction
- Sample Complexity of Causal Identification with Temporal Heterogeneity
- Feature learning from non-Gaussian inputs: the case of Independent Component Analysis in high dimensions
- On joint eigen-decomposition of matrices
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis