conftrace_

random matrix theory

63 papers

Explore in graph

Also known as

RMT

Co-occurring keywords

neural network (6616) random matrix (28) principal component analysis (316) gaussian mixture model (389) spectral analysis (239) asymptotic analysis (86) tensor decomposition (375) neural tangent kernel (205) spectral method (204) implicit regularization (93)

Papers

On the role of overparameterization in off-policy Temporal Difference learning with linear function approximation NIPS 2022
A Random Matrix Perspective on Random Tensors JMLR 2022
Model, sample, and epoch-wise descents: exact solution of gradient flow in the random feature model NIPS 2021
Dynamics of Stochastic Momentum Methods on Large-scale, Quadratic Models NIPS 2021
On the Random Conjugate Kernel and Neural Tangent Kernel ICML 2021
Two-way kernel matrix puncturing: towards resource-efficient PCA and spectral clustering ICML 2021
Detection of Signal in the Spiked Rectangular Models ICML 2021
Rank-one matrix estimation: analytic time evolution of gradient descent dynamics COLT 2021
SGD in the Large: Average-case Analysis, Asymptotics, and Stepsize Criticality COLT 2021
Hessian Eigenspectra of More Realistic Nonlinear Models NIPS 2021
Implicit Self-Regularization in Deep Neural Networks: Evidence from Random Matrix Theory and Implications for Learning JMLR 2021
Context Vectors Are Reflections of Word Vectors in Half the Dimensions (Extended Abstract) IJCAI 2020
Random Matrix Theory Proves that Deep Learning Representations of GAN-data Behave as Gaussian Mixtures ICML 2020
Optimal Iterative Sketching Methods with the Subsampled Randomized Hadamard Transform NIPS 2020
Estimating Rank-One Spikes from Heavy-Tailed Noise via Self-Avoiding Walks NIPS 2020
Spectra of the Conjugate Kernel and Neural Tangent Kernel for linear-width neural networks NIPS 2020
Implicit Regularization of Random Feature Models ICML 2020
Rotation Invariant Householder Parameterization for Bayesian PCA ICML 2019
Random Matrix Improved Covariance Estimation for a Large Class of Metrics ICML 2019
The spiked matrix model with generative priors NIPS 2019
On the number of variables to use in principal component regression NIPS 2019
Dynamical Isometry is Achieved in Residual Networks in a Universal Way for any Activation Function AISTATS 2019
Asymptotics for Sketching in Least Squares Regression NIPS 2019
Traditional and Heavy Tailed Self Regularization in Neural Network Models ICML 2019
A Random Matrix Analysis and Improvement of Semi-Supervised Learning for Large Dimensional Data JMLR 2018