No article text was recorded for this version.
Gaussian input assumption (input distribution constraints)
Version 1 of 143 papers45 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Recovery Guarantees for One-hidden-layer Neural Networks
- Blog: Efficiently Learning One-Hidden-Layer ReLU Networks via SchurPolynomials
- Blog: Efficiently Learning One Hidden Layer ReLU Networks From Queries
- Blog: Learning ReLUs via Gradient Descent
- Blog: Symmetry-Breaking Convergence Analysis of Certain Two-layered Neural Networks with ReLU nonlinearity
- Blog: An Analytical Formula of Population Gradient for two-layered ReLU network and its Applications in Convergence and Critical Point Analysis
- Blog: Learning with Noise and Regularizers in Multilayer Neural Networks
- Blog: Learning Narrow One-Hidden-Layer ReLU Networks
- Blog: Provable Guarantees for Nonlinear Feature Learning in Three-Layer Neural Networks
- Blog: Guided by the Experts: Provable Feature Learning Dynamic of Soft-Routed Mixture-of-Experts
- Blog: Convergence Analysis of Two-layer Neural Networks with ReLU Activation
- Blog: Convex Relaxations of Convolutional Neural Nets
- Blog: A margin-based multiclass generalization bound via geometric complexity
- Blog: Scaling Laws and Spectra of Shallow Neural Networks in the Feature Learning Regime
- Blog: RedEx: Beyond Fixed Representation Methods via Convex Optimization
- Blog: Efficient Algorithms for Learning Depth-2 Neural Networks with General ReLU Activations
- Blog: Phase diagram of Stochastic Gradient Descent in high-dimensional two-layer neural networks
- Blog: Learning Deep ReLU Networks Is Fixed-Parameter Tractable
- Blog: Fast Escape, Slow Convergence: Learning Dynamics of Phase Retrieval under Power-Law Data
- Blog: Bounds for the smallest eigenvalue of the NTK for arbitrary spherical data of arbitrary dimension
- Blog: On the Impact of Overparameterization on the Training of a Shallow Neural Network in High Dimensions
- Blog: Nonparametric Learning of Two-Layer ReLU Residual Units
- Blog: History-Dependent Attractor Neural Networks
- Blog: Optimal Activation Functions for the Random Features Regression Model
- Blog: Global Convergence Analysis of Local SGD for Two-layer Neural Network without Overparameterization
- Blog: Learning One-hidden-layer Neural Networks under General Input Distributions
- Blog: On the generalization of bayesian deep nets for multi-class classification
- Blog: SGD Learns the Conjugate Kernel Class of the Network
- Blog: Gradient Descent Learns One-hidden-layer CNN: Don't be Afraid of Spurious Local Minima
- Blog: Adding One Neuron Can Eliminate All Bad Local Minima
- Blog: Learning a Single Neuron with Gradient Methods
- Blog: Analytic Study of Families of Spurious Minima in Two-Layer ReLU Neural Networks: A Tale of Symmetry II
- Blog: Transfer Learning in Infinite Width Feature Learning Networks
- Blog: Analytic Characterization of the Hessian in Shallow ReLU Models: A Tale of Symmetry
- Blog: Inference in Multi-Layer Networks with Matrix-Valued Unknowns
- Blog: How Classifier Features Transfer to Downstream: An Asymptotic Analysis in a Two-Layer Model
- Blog: The Surprising Simplicity of the Early-Time Learning Dynamics of Neural Networks
- Blog: On the Hardness of Learning One Hidden Layer Neural Networks
- Blog: Regularization Matters: A Nonparametric Perspective on Overparametrized Neural Network
- Blog: Overparameterized Random Feature Regression with Nearly Orthogonal Data
- Blog: PLUGIn: A simple algorithm for inverting generative models with recovery guarantees
- Blog: Sobolev acceleration for neural networks
- Blog: An analytic theory of generalization dynamics and transfer learning in deep linear networks
History & citation
Current · Permanent link
- This direction split from Gaussian Universality in High Dimensional Neural Network Dynamics (93% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_gaussian_input_assumption_input_distribu_a7aec519,
title = {Gaussian input assumption (input distribution constraints)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/gaussian-input-assumption-input-distribution-constraints/rdr_a7aec519f6ca49b59134d8879a299065},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_gaussian_input_assumption_input_distribu_a7aec519_v1,
title = {Gaussian input assumption (input distribution constraints)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/gaussian-input-assumption-input-distribution-constraints/rdr_a7aec519f6ca49b59134d8879a299065/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}