Image de couverture de livre

Learning Rate Should Scale Inversely with High-Order Data Moments in High-Dimensional Online Independent Component Analysis

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Gultekin, M. Oguzhan, Demir, Samet, Dogan, Zafer
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Implicitly Normalized Online PCA: A Regularized Algorithm with Exact High-Dimensional Dynamics
par: Demir, Samet, et autres
Publié: (2025)

Learnability and Competition in High-Dimensional Multi-Component ICA
par: Genc, Eser Ilke, et autres
Publié: (2026)

Optimal Attention Temperature Improves the Robustness of In-Context Learning under Distribution Shift in High Dimensions
par: Demir, Samet, et autres
Publié: (2025)

How Data Mixing Shapes In-Context Learning: Asymptotic Equivalence for Transformers with MLPs
par: Demir, Samet, et autres
Publié: (2025)

Asymptotic Analysis of Two-Layer Neural Networks after One Gradient Step under Gaussian Mixtures Data with Structure
par: Demir, Samet, et autres
Publié: (2025)

Asymptotic Study of In-context Learning with Random Transformers through Equivalent Models
par: Demir, Samet, et autres
Publié: (2025)

Learning Beyond the Gaussian Data: Learning Dynamics of Neural Networks on an Expressive and Cumulant-Controllable Data Model
par: Ure, Onat, et autres
Publié: (2026)

Input-Label Correlation Governs a Linear-to-Nonlinear Transition in Random Features under Spiked Covariance
par: Demir, Samet, et autres
Publié: (2024)

Benefits of Online Tilted Empirical Risk Minimization: A Case Study of Outlier Detection and Robust Regression
par: Yildirim, Yigit E., et autres
Publié: (2025)

Exploring the Precise Dynamics of Single-Layer GAN Models: Leveraging Multi-Feature Discriminators for High-Dimensional Subspace Learning
par: Bond, Andrew, et autres
Publié: (2024)

High-dimensional Analysis of Knowledge Distillation: Weak-to-Strong Generalization and Scaling Laws
par: Ildiz, M. Emrullah, et autres
Publié: (2024)

Mollifier Layers: Enabling Efficient High-Order Derivatives in Inverse PDE Learning
par: Bhartari, Ananyae Kumar, et autres
Publié: (2025)

Stochastic Dimension-Free Zeroth-Order Estimator for High-Dimensional and High-Order PINNs
par: Liang, Zhangyong, et autres
Publié: (2026)

Unsupervised Learning: Comparative Analysis of Clustering Techniques on High-Dimensional Data
par: Baligodugula, Vishnu Vardhan, et autres
Publié: (2025)

Implicit High-Order Moment Tensor Estimation and Learning Latent Variable Models
par: Diakonikolas, Ilias, et autres
Publié: (2024)

One-shot Robust Federated Learning of Independent Component Analysis
par: Jin, Dian, et autres
Publié: (2025)

LCIP: Loss-Controlled Inverse Projection of High-Dimensional Image Data
par: Wang, Yu, et autres
Publié: (2026)

High-Dimensional Private Linear Regression with Optimal Rates
par: Bombari, Simone, et autres
Publié: (2025)

Order-Explicit Linearization of High-Dimensional $U$-Statistics
par: Ritzwoller, David M., et autres
Publié: (2024)

Independent Component Discovery in Temporal Count Data
par: Chaussard, Alexandre, et autres
Publié: (2026)

High-Dimensional Independence Testing via Maximum and Average Distance Correlations
par: Shen, Cencheng, et autres
Publié: (2020)

Independent Component Analysis by Robust Distance Correlation
par: Leyder, Sarah, et autres
Publié: (2025)

Enhanced High-Dimensional Data Visualization through Adaptive Multi-Scale Manifold Embedding
par: Ni, Tianhao, et autres
Publié: (2025)

Estimating Treatment Effects with Independent Component Analysis
par: Reizinger, Patrik, et autres
Publié: (2025)

High-Dimensional False Discovery Rate Control for Dependent Variables
par: Machkour, Jasin, et autres
Publié: (2024)

Trading Convergence Rate with Computational Budget in High Dimensional Bayesian Optimization
par: Tran-The, Hung, et autres
Publié: (2019)

How Should LLMs Consume High-Quality Data? Optimal Data Scheduling via Quality-Aware Functional Scaling Laws
par: Zhu, Zhitao, et autres
Publié: (2026)

High-Dimensional BWDM: A Robust Nonparametric Clustering Validation Index for Large-Scale Data
par: Baragilly, Mohammed, et autres
Publié: (2025)

Latent Chain-of-Thought Improves Structured-Data Transformers
par: Dudley, Carson, et autres
Publié: (2026)

The Rashomon Effect for Visualizing High-Dimensional Data
par: Sun, Yiyang, et autres
Publié: (2026)

Efficient Estimation of Unique Components in Independent Component Analysis by Matrix Representation
par: Matsuda, Yoshitatsu, et autres
Publié: (2024)

Orthogonal Subspace Clustering: Enhancing High-Dimensional Data Analysis through Adaptive Dimensionality Reduction and Efficient Clustering
par: Wen, Qing-Yuan, et autres
Publié: (2026)

Accelerating Large-Scale Regularized High-Order Tensor Recovery
par: Qin, Wenjin, et autres
Publié: (2025)

A Multi-Fidelity Methodology for Reduced Order Models with High-Dimensional Inputs
par: Mufti, Bilal, et autres
Publié: (2024)

High-Dimensional Analysis of Bootstrap Ensemble Classifiers
par: Tiomoko, Malik, et autres
Publié: (2025)

Self-sufficient Independent Component Analysis via KL Minimizing Flows
par: Liu, Song
Publié: (2025)

MVICAD2: Multi-View Independent Component Analysis with Delays and Dilations
par: Heurtebise, Ambroise, et autres
Publié: (2025)

Causal Representation Learning on High-Dimensional Data: Benchmarks, Reproducibility, and Evaluation Metrics
par: Sadeghi, Alireza, et autres
Publié: (2026)

LLM Unlearning Should Be Form-Independent
par: Ye, Xiaotian, et autres
Publié: (2025)

Privacy-Preserving Federated Unsupervised Domain Adaptation for Regression on Small-Scale and High-Dimensional Biological Data
par: Baykara, Cem Ata, et autres
Publié: (2024)