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

Sobolev Independence Criterion NIPS 2019
Memory Efficient Adaptive Optimization NIPS 2019
Sever: A Robust Meta-Algorithm for Stochastic Optimization ICML 2019
Efficient Dictionary Learning with Gradient Descent ICML 2019
Learning Deep Priors for Image Dehazing ICCV 2019
The implicit bias of gradient descent on nonseparable data COLT 2019
Gradient Descent for One-Hidden-Layer Neural Networks: Polynomial Convergence and SQ Lower Bounds COLT 2019
On the Power and Limitations of Random Features for Understanding Neural Networks NIPS 2019
Global Guarantees for Blind Demodulation with Generative Priors NIPS 2019
Neural 3D Mesh Renderer CVPR 2018
Connecting Optimization and Regularization Paths NIPS 2018
Gradient Hard Thresholding Pursuit JMLR 2018
Convergence of Unregularized Online Learning Algorithms JMLR 2018
The Physical Systems Behind Optimization Algorithms NIPS 2018
Decoupled Parallel Backpropagation with Convergence Guarantee ICML 2018
On the Global Convergence of Gradient Descent for Over-parameterized Models using Optimal Transport NIPS 2018
Extreme Learning to Rank via Low Rank Assumption ICML 2018
Catalyst Acceleration for First-order Convex Optimization: from Theory to Practice JMLR 2018
Step Size Matters in Deep Learning NIPS 2018
Learning to Reweight Examples for Robust Deep Learning ICML 2018
Orthogonal Recurrent Neural Networks with Scaled Cayley Transform ICML 2018
Bilevel Programming for Hyperparameter Optimization and Meta-Learning ICML 2018
On the Optimization of Deep Networks: Implicit Acceleration by Overparameterization ICML 2018
The Implicit Bias of Gradient Descent on Separable Data JMLR 2018
Gradient descent with identity initialization efficiently learns positive definite linear transformations by deep residual networks ICML 2018