random matrix theory

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 Sparse Quantized Spectral Clustering ICLR 2021 Two-way kernel matrix puncturing: towards resource-efficient PCA and spectral clustering ICML 2021 Context Vectors Are Reflections of Word Vectors in Half the Dimensions (Extended Abstract) IJCAI 2020 Estimating Rank-One Spikes from Heavy-Tailed Noise via Self-Avoiding Walks NeurIPS 2020 Implicit Regularization of Random Feature Models ICML 2020 Optimal Iterative Sketching Methods with the Subsampled Randomized Hadamard Transform NeurIPS 2020 Random Matrix Theory Proves that Deep Learning Representations of GAN-data Behave as Gaussian Mixtures ICML 2020 Spectra of the Conjugate Kernel and Neural Tangent Kernel for linear-width neural networks NeurIPS 2020 A Kernel Random Matrix-Based Approach for Sparse PCA ICLR 2019 Asymptotics for Sketching in Least Squares Regression NeurIPS 2019 Dynamical Isometry is Achieved in Residual Networks in a Universal Way for any Activation Function AISTATS 2019 On the number of variables to use in principal component regression NeurIPS 2019 Random Matrix Improved Covariance Estimation for a Large Class of Metrics ICML 2019 Rotation Invariant Householder Parameterization for Bayesian PCA ICML 2019 The spiked matrix model with generative priors NeurIPS 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 Detection limits in the high-dimensional spiked rectangular model COLT 2018 Dynamical Isometry and a Mean Field Theory of RNNs: Gating Enables Signal Propagation in Recurrent Neural Networks ICML 2018 On the Spectrum of Random Features Maps of High Dimensional Data ICML 2018 The Spectrum of the Fisher Information Matrix of a Single-Hidden-Layer Neural Network NeurIPS 2018 Distributed Sequence Memory of Multidimensional Inputs in Recurrent Networks JMLR 2017 Generalized SURE for optimal shrinkage of singular values in low-rank matrix denoising JMLR 2017