No article text was recorded for this version.
spherical harmonic decomposition
Version 1 of 163 papers69 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Bounds for the smallest eigenvalue of the NTK for arbitrary spherical data of arbitrary dimension
- Blog: Regularization with Dot-Product Kernels
- Blog: A spectral-based analysis of the separation between two-layer neural networks and linear methods
- Blog: Spectral Analysis of the Neural Tangent Kernel for Deep Residual Networks
- Blog: Tight Bounds on the Smallest Eigenvalue of the Neural Tangent Kernel for Deep ReLU Networks
- Blog: On the Similarity between the Laplace and Neural Tangent Kernels
- Blog: On the impact of activation and normalization in obtaining isometric embeddings at initialization
- Blog: Deep Networks Learn Deep Hierarchical Models
- Blog: Characterizing the spectrum of the NTK via a power series expansion
- Blog: The spectral norm of random inner-product kernel matrices
- Blog: On the impact of activation and normalization in obtaining isometric embeddings at initialization
- Blog: Polynomial, trigonometric, and tropical activations
- Blog: On the Spectral Bias of Neural Networks
- Blog: Gradient Descent for One-Hidden-Layer Neural Networks: Polynomial Convergence and SQ Lower Bounds
- Blog: Learning single index models via harmonic decomposition
- Blog: Uniform Convergence, Adversarial Spheres and a Simple Remedy
- Blog: Deep Equals Shallow for ReLU Networks in Kernel Regimes
- Blog: Superpolynomial Lower Bounds for Learning One-Layer Neural Networks using Gradient Descent
- Blog: Tight Bounds on the Smallest Eigenvalue of the Neural Tangent Kernel for Deep ReLU Networks
- Blog: Predicting Kernel Regression Learning Curves from Only Raw Data Statistics
- Blog: Learning in the Presence of Low-dimensional Structure: A Spiked Random Matrix Perspective
- Blog: Improved Regret Bounds for Gaussian Process Upper Confidence Bound in Bayesian Optimization
- Blog: Rate of Convergence of Polynomial Networks to Gaussian Processes
- Blog: What can be learnt with wide convolutional neural networks?<sup>*</sup>
- Blog: Beyond ReLU: How Activations Affect Neural Kernels and Random Wide Networks
- Blog: Harmonic Decompositions of Convolutional Networks
- Blog: On the Inductive Bias of Neural Tangent Kernels
- Blog: Diverse Neural Network Learns True Target Functions
- Blog: Spectral Smoothing Unveils Phase Transitions in Hierarchical Variational Autoencoders
- Blog: Emergence of Globally Attracting Fixed Points in Deep Neural Networks With Nonlinear Activations
- Blog: The Interpolation Phase Transition in Neural Networks: Memorization and Generalization under Lazy Training
- Blog: On the Spectral Bias of Convolutional Neural Tangent and Gaussian Process Kernels
- Blog: On the Minimal Degree Bias in Generalization on the Unseen for non-Boolean Functions
- Blog: Fast Neural Kernel Embeddings for General Activations
- Blog: Asymptotic Analysis of Two-Layer Neural Networks after One Gradient Step under Gaussian Mixtures Data with Structure
- Blog: On the Saturation Effects of Spectral Algorithms in Large Dimensions
- Blog: Spherical Inducing Features for Orthogonally-Decoupled Gaussian Processes
- Blog: Learning a Single Neuron for Non-monotonic Activation Functions
- Blog: Depth Separation for Neural Networks
- Blog: Spectral Properties of Kernel Matrices in the Flat Limit
- Blog: A Spectral Analysis of Dot-product Kernels
- Blog: Reproducing Kernel Banach Space Models for Neural Networks with Application to Rademacher Complexity Analysis
- Blog: Reverse Engineering the Neural Tangent Kernel
- Blog: The Convergence Rate of Neural Networks for Learned Functions of Different Frequencies
- Blog: The expressivity and training of deep neural networks: Toward the edge of chaos?
- Blog: Tighter Regret Lower Bound for Gaussian Process Bandits with Squared Exponential Kernel in Hypersphere
- Blog: How Powerful are Shallow Neural Networks with Bandlimited Random Weights?
- Blog: On the Eigenvalue Decay Rates of a Class of Neural-Network Related Kernel Functions Defined on General Domains
- Blog: Learning One-hidden-layer Neural Networks with Landscape Design
- Blog: Generalization Guarantees for Sparse Kernel Approximation with Entropic Optimal Features
- Blog: Reverse Engineering the Neural Tangent Kernel
- Blog: Neural Tangent Kernels Motivate Cross-Covariance Graphs in Neural Networks
- Blog: Tight Bounds on the Smallest Eigenvalue of the Neural Tangent Kernel for Deep ReLU Networks
- Blog: Mercer kernels and integrated variance experimental design: connections between Gaussian process regression and polynomial approximation
- Blog: Time/Accuracy Tradeoffs for Learning a ReLU with respect to Gaussian Marginals
- Blog: Overparameterized Random Feature Regression with Nearly Orthogonal Data
- Blog: Optimal Rates of Approximation by Shallow ReLU$$^k$$ Neural Networks and Applications to Nonparametric Regression
- Blog: A Solvable High-Dimensional Model Where Nonlinear Autoencoders Learn Structure Invisible to PCA While Test Loss Misaligns With Generalization
- Blog: Regularity of matrix coefficients of a compact symmetric pair of Lie groups
- Blog: On the Generalization Power of Overfitted Two-Layer Neural Tangent Kernel Models
Showing 60 of 63 papers.
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_spherical_harmonic_decomposition_4dd672da,
title = {spherical harmonic decomposition},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/spherical-harmonic-decomposition/rdr_4dd672da886e4036832b0ad6c1c2ff2d},
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_spherical_harmonic_decomposition_4dd672da_v1,
title = {spherical harmonic decomposition},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/spherical-harmonic-decomposition/rdr_4dd672da886e4036832b0ad6c1c2ff2d/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}