conftrace_

gradient descent

1144 papers

Explore in graph

Also known as

GD

Co-occurring keywords

neural network (6616) neural network optimization (1293) convex optimization (1321) non-convex optimization (547) convergence rate (607) stochastic optimization (1060) convergence analysis (395) stochastic gradient descent (1091) nonconvex optimization (316) implicit bia (107)

Papers

Quantifying the Benefit of Using Differentiable Learning over Tangent Kernels ICML 2021
Tight Bounds on the Smallest Eigenvalue of the Neural Tangent Kernel for Deep ReLU Networks ICML 2021
Online Optimal Control with Affine Constraints AAAI 2021
Learner-Private Convex Optimization ICML 2021
Effects of Parameter Norm Growth During Transformer Training: Inductive Bias from Gradient Descent EMNLP 2021
Early-stopped neural networks are consistent NIPS 2021
Explicit loss asymptotics in the gradient descent training of neural networks NIPS 2021
Limiting fluctuation and trajectorial stability of multilayer neural networks with mean field training NIPS 2021
Continuous vs. Discrete Optimization of Deep Neural Networks NIPS 2021
Score-based Generative Neural Networks for Large-Scale Optimal Transport NIPS 2021
Differentiable Learning Under Triage NIPS 2021
When Expressivity Meets Trainability: Fewer than $n$ Neurons Can Work NIPS 2021
A single gradient step finds adversarial examples on random two-layers neural networks NIPS 2021
Relaxing Local Robustness NIPS 2021
Convergence and Alignment of Gradient Descent with Random Backpropagation Weights NIPS 2021
A Convergence Analysis of Gradient Descent on Graph Neural Networks NIPS 2021
Powerpropagation: A sparsity inducing weight reparameterisation NIPS 2021
On the Role of Optimization in Double Descent: A Least Squares Study NIPS 2021
A Comprehensively Tight Analysis of Gradient Descent for PCA NIPS 2021
The Neural Tangent Link Between CNN Denoisers and Non-Local Filters CVPR 2021
Scalable Rule-Based Representation Learning for Interpretable Classification NIPS 2021
Faster Directional Convergence of Linear Neural Networks under Spherically Symmetric Data NIPS 2021
Differentiable Spike: Rethinking Gradient-Descent for Training Spiking Neural Networks NIPS 2021
Multi-Objective Meta Learning NIPS 2021
Optimization of Graph Neural Networks: Implicit Acceleration by Skip Connections and More Depth ICML 2021