random matrix theory

A Theory of Unsupervised Speech Recognition ACL 2023 Bayesian Extensive-Rank Matrix Factorization with Rotational Invariant Priors NeurIPS 2023 Impact of classification difficulty on the weight matrices spectra in Deep Learning and application to early-stopping JMLR 2023 PCA-based Multi-Task Learning: a Random Matrix Approach ICML 2023 Random Matrix Analysis to Balance between Supervised and Unsupervised Learning under the Low Density Separation Assumption ICML 2023 Sharp Recovery Thresholds of Tensor PCA Spectral Algorithms NeurIPS 2023 SPQR: Controlling Q-ensemble Independence with Spiked Random Model for Reinforcement Learning NeurIPS 2023 Towards Understanding and Reducing Graph Structural Noise for GNNs ICML 2023 A Random Matrix Analysis of Data Stream Clustering: Coping With Limited Memory Resources ICML 2022 A Random Matrix Perspective on Mixtures of Nonlinearities in High Dimensions AISTATS 2022 A Random Matrix Perspective on Random Tensors JMLR 2022 Information bottleneck theory of high-dimensional regression: relevancy, efficiency and optimality NeurIPS 2022 Learning Rates as a Function of Batch Size: A Random Matrix Theory Approach to Neural Network Training JMLR 2022 More Than a Toy: Random Matrix Models Predict How Real-World Neural Representations Generalize ICML 2022 Node Feature Kernels Increase Graph Convolutional Network Robustness AISTATS 2022 On the role of overparameterization in off-policy Temporal Difference learning with linear function approximation NeurIPS 2022 Random matrices in service of ML footprint: ternary random features with no performance loss ICLR 2022 Deciphering and Optimizing Multi-Task Learning: a Random Matrix Approach ICLR 2021 Detection of Signal in the Spiked Rectangular Models ICML 2021 Dynamics of Stochastic Momentum Methods on Large-scale, Quadratic Models NeurIPS 2021 Hessian Eigenspectra of More Realistic Nonlinear Models NeurIPS 2021 Implicit Self-Regularization in Deep Neural Networks: Evidence from Random Matrix Theory and Implications for Learning JMLR 2021 Meta-learning with negative learning rates ICLR 2021 Model, sample, and epoch-wise descents: exact solution of gradient flow in the random feature model NeurIPS 2021 On the Random Conjugate Kernel and Neural Tangent Kernel ICML 2021