conftrace_

spectral density

13 papers

Explore in graph

Co-occurring keywords

gaussian process (1200) kernel methods (1097) free probability (4) neural network initialization (33) spectral kernel (10) random matrix theory (63) bayesian inference (1907) variational inference (2069) layer-wise pruning (14) residual network (211)

Papers

Linear cost and exponentially convergent approximation of Gaussian Matérn processes on intervals JMLR 2025
AlphaPruning: Using Heavy-Tailed Self Regularization Theory for Improved Layer-wise Pruning of Large Language Models NIPS 2024
Model Balancing Helps Low-data Training and Fine-tuning EMNLP 2024
Free Probability for predicting the performance of feed-forward fully connected neural networks NIPS 2022
Efficient Approximate Inference for Stationary Kernel on Frequency Domain ICML 2022
Investigating and Explaining the Frequency Bias in Image Classification IJCAI 2022
Ridgeless Regression with Random Features IJCAI 2022
Implicit Self-Regularization in Deep Neural Networks: Evidence from Random Matrix Theory and Implications for Learning JMLR 2021
Band-Limited Gaussian Processes: The Sinc Kernel NIPS 2019
Dynamical Isometry is Achieved in Residual Networks in a Universal Way for any Activation Function AISTATS 2019
Function-Space Distributions over Kernels NIPS 2019
Learning Stationary Time Series using Gaussian Processes with Nonparametric Kernels NIPS 2015
Gaussian Process Kernels for Pattern Discovery and Extrapolation ICML 2013