independent component analysis

Causal Disentanglement and Cross-Modal Alignment for Enhanced Few-Shot Learning ICCV 2025 Cross-Entropy Is All You Need To Invert the Data Generating Process ICLR 2025 Feature learning from non-Gaussian inputs: the case of Independent Component Analysis in high dimensions ICML 2025 Heart Rate as a Proxy Measure to Assess Human Confidence in Spoken Speech Interspeech 2025 Investigating the Contextualised Word Embedding Dimensions Specified for Contextual and Temporal Semantic Changes COLING 2025 Nonparametric Factor Analysis and Beyond AISTATS 2025 Revisiting Cosine Similarity via Normalized ICA-transformed Embeddings COLING 2025 S3 - Semantic Signal Separation ACL 2025 An Interventional Perspective on Identifiability in Gaussian LTI Systems with Independent Component Analysis CLeaR 2024 Axis Tour: Word Tour Determines the Order of Axes in ICA-transformed Embeddings EMNLP 2024 Exploring Interpretability of Independent Components of Word Embeddings with Automated Word Intruder Test COLING 2024 Exploring Intra and Inter-language Consistency in Embeddings with ICA EMNLP 2024 Local Causal Discovery with Linear non-Gaussian Cyclic Models AISTATS 2024 Nonparametric Evaluation of Noisy ICA Solutions NeurIPS 2024 Understanding Higher-Order Correlations Among Semantic Components in Embeddings EMNLP 2024 Additive Decoders for Latent Variables Identification and Cartesian-Product Extrapolation NeurIPS 2023 Causal Component Analysis NeurIPS 2023 Causal Discovery with Latent Confounders Based on Higher-Order Cumulants ICML 2023 Cocktail Party Attack: Breaking Aggregation-Based Privacy in Federated Learning Using Independent Component Analysis ICML 2023 Correlative Information Maximization Based Biologically Plausible Neural Networks for Correlated Source Separation ICLR 2023 DCI-ES: An Extended Disentanglement Framework with Connections to Identifiability ICLR 2023 Discovering Universal Geometry in Embeddings with ICA EMNLP 2023 Generalizing Nonlinear ICA Beyond Structural Sparsity NeurIPS 2023 Multi-domain image generation and translation with identifiability guarantees ICLR 2023 Multi-View Independent Component Analysis with Shared and Individual Sources UAI 2023