No article text was recorded for this version.
Gaussian input assumption (Gaussian feature assumption)
Version 1 of 154 papers54 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Phase transitions for high-dimensional joint support recovery
- Blog: How Much is a Noisy Image Worth? Data Scaling Laws for Ambient Diffusion.
- Blog: The Computational Advantage of Depth in Learning High-Dimensional Hierarchical Targets
- Blog: Estimating Generalization Performance Along the Trajectory of Proximal SGD in Robust Regression
- Blog: Learning curves for the multi-class teacher-student perceptron
- Blog: A Feature Normalisation Technique for PLLR Based Language Identification Systems
- Blog: Precise Tradeoffs in Adversarial Training for Linear Regression
- Blog: Local Linear Convergence of Douglas-Rachford for Linear Programming: a Probabilistic Analysis
- Blog: Bias in Motion: Theoretical Insights into the Dynamics of Bias in SGD Training
- Blog: Tight bounds for maximum ℓ1-margin classifiers
- Blog: Universality laws for Gaussian mixtures in generalized linear models*
- Blog: Bayes-optimal Learning of Deep Random Networks of Extensive-width
- Blog: Classifying high-dimensional Gaussian mixtures: Where kernel methods fail and neural networks succeed
- Blog: Solvable Model for Inheriting the Regularization through Knowledge Distillation
- Blog: Dynamics of Training
- Blog: Error Analysis of Spherically Constrained Least Squares Reformulation in Solving the Stackelberg Prediction Game
- Blog: The Reliability of OKRidge Method in Solving Sparse Ridge Regression Problems
- Blog: On Single-Index Models beyond Gaussian Data
- Blog: A Framework for Probability Density Estimation
- Blog: Pruning is Optimal for Learning Sparse Features in High-Dimensions
- Blog: Universality in Transfer Learning for Linear Models
- Blog: Feature learning from non-Gaussian inputs: the case of Independent Component Analysis in high dimensions
- Blog: Characterizing Overfitting in Kernel Ridgeless Regression Through the Eigenspectrum
- Blog: On the Connection Between Learning Two-Layer Neural Networks and Tensor Decomposition
- Blog: Large deviations in the perceptron model and consequences for active learning
- Blog: Approximate Leave-one-out Cross Validation for Regression with ℓ1 Regularizers
- Blog: On the Existence of Consistent Adversarial Attacks in High-Dimensional Linear Classification
- Blog: A Non-Asymptotic Moreau Envelope Theory for High-Dimensional Generalized Linear Models
- Blog: LoD: Loss-difference OOD Detection by Intentionally Label-Noisifying Unlabeled Wild Data
- Blog: Dynamics of stochastic gradient descent for two-layer neural networks in the teacher-student setup
- Blog: An Effective Theory of Bias Amplification
- Blog: Neural Networks Efficiently Learn Low-Dimensional Representations with SGD
- Blog: Towards Understanding the Importance of Shortcut Connections in Residual Networks
- Blog: Phase Transitions in Transfer Learning for High-Dimensional Perceptrons
- Blog: Learning One-hidden-layer Neural Networks with Landscape Design
- Blog: Deciphering Lasso-based Classification Through a Large Dimensional Analysis of the Iterative Soft-Thresholding Algorithm
- Blog: On Class Distributions Induced by Nearest Neighbor Graphs for Node Classification of Tabular Data
- Blog: Learning Hierarchical Polynomials with Three-Layer Neural Networks
- Blog: Generalized Dantzig Selector: Application to the k-support norm
- Blog: A Derandomization Framework for Structure Discovery: Applications in Neural Networks and Beyond
- Blog: Optimal Nonlinearities Improve Generalization Performance of Random Features
- Blog: Block Regularized Lasso for Multivariate Multi-Response Linear Regression
- Blog: On the Interaction between Norm and Dimensionality: Multiple Regimes in Learning
- Blog: Deep Learning of Compositional Targets with Hierarchical Spectral Methods
- Blog: Learning One-hidden-layer ReLU Networks via Gradient Descent
- Blog: Double Descent Meets Out-of-Distribution Detection: Theoretical Insights and Empirical Analysis on the Role of Model Complexity
- Blog: Bayes-optimal Learning of Deep Random Networks of Extensive-width
- Blog: How unlabeled data improve generalization in self-training? A one-hidden-layer theoretical analysis
- Blog: A random matrix analysis of random Fourier features: beyond the Gaussian kernel, a precise phase transition, and the corresponding double descent
- Blog: Sharp Asymptotics and Optimal Performance for Inference in Binary Models
- Blog: Learning quadratic neural networks in high dimensions: SGD dynamics and scaling laws
- Blog: Generalization for multiclass classification with overparameterized linear models
- Blog: Accuracy on the Line: on the Strong Correlation Between Out-of-Distribution and In-Distribution Generalization
- Blog: The Performance Analysis of Generalized Margin Maximizers on Separable Data
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_gaussian_input_assumption_gaussian_featu_9739b4b7,
title = {Gaussian input assumption (Gaussian feature assumption)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/gaussian-input-assumption-gaussian-feature-assumption/rdr_9739b4b79f1e489eaf35351aea87dcc4},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-19},
}This exact version (version 1, frozen text):
@misc{lacuna_gaussian_input_assumption_gaussian_featu_9739b4b7_v1,
title = {Gaussian input assumption (Gaussian feature assumption)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/gaussian-input-assumption-gaussian-feature-assumption/rdr_9739b4b79f1e489eaf35351aea87dcc4/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-19},
}