conftrace_

over-parameterized neural network

13 papers

Explore in graph

Co-occurring keywords

gradient descent (1144) neural network (6616) relu network (143) over-parameterized network (11) neural network optimization (1293) global convergence (111) neural tangent kernel (205) functional approximation (3) nesterov accelerated gradient (15) heavy ball method (8)

Papers

Provable Acceleration of Nesterov’s Accelerated Gradient Method over Heavy Ball Method in Training Over-Parameterized Neural Networks IJCAI 2024
Efficient Uncertainty Quantification and Reduction for Over-Parameterized Neural Networks NIPS 2023
Over-parameterized Deep Nonparametric Regression for Dependent Data with Its Applications to Reinforcement Learning JMLR 2023
Noise Regularizes Over-parameterized Rank One Matrix Recovery, Provably AISTATS 2022
AdaLoss: A Computationally-Efficient and Provably Convergent Adaptive Gradient Method AAAI 2022
Gradient Starvation: A Learning Proclivity in Neural Networks NIPS 2021
Modeling from Features: a Mean-field Framework for Over-parameterized Deep Neural Networks COLT 2021
The Implicit Bias of Minima Stability: A View from Function Space NIPS 2021
Does Preprocessing Help Training Over-parameterized Neural Networks? NIPS 2021
Global Convergence of Deep Networks with One Wide Layer Followed by Pyramidal Topology NIPS 2020
On Lazy Training in Differentiable Programming NIPS 2019
Fast Convergence of Natural Gradient Descent for Over-Parameterized Neural Networks NIPS 2019
On Learning Over-parameterized Neural Networks: A Functional Approximation Perspective NIPS 2019