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

Bayesian Network Learning via Topological Order JMLR 2017
A Nonconvex Approach for Phase Retrieval: Reshaped Wirtinger Flow and Incremental Algorithms JMLR 2017
“Convex Until Proven Guilty”: Dimension-Free Acceleration of Gradient Descent on Non-Convex Functions ICML 2017
Globally Optimal Gradient Descent for a ConvNet with Gaussian Inputs ICML 2017
Programming with a Differentiable Forth Interpreter ICML 2017
Sharpness, Restart and Acceleration NIPS 2017
Natasha: Faster Non-Convex Stochastic Optimization via Strongly Non-Convex Parameter ICML 2017
Strongly-Typed Agents are Guaranteed to Interact Safely ICML 2017
Learning to Learn without Gradient Descent by Gradient Descent ICML 2017
How to Escape Saddle Points Efficiently ICML 2017
Gradient Coding: Avoiding Stragglers in Distributed Learning ICML 2017
Efficient Distributed Learning with Sparsity ICML 2017
A Unified Computational and Statistical Framework for Nonconvex Low-rank Matrix Estimation AISTATS 2017
Finite-sum Composition Optimization via Variance Reduced Gradient Descent AISTATS 2017
Efficient Algorithm for Sparse Tensor-variate Gaussian Graphical Models via Gradient Descent AISTATS 2017
Adaptive ADMM with Spectral Penalty Parameter Selection AISTATS 2017
Global Convergence of Non-Convex Gradient Descent for Computing Matrix Squareroot AISTATS 2017
Encrypted Accelerated Least Squares Regression AISTATS 2017
Gradient Methods for Submodular Maximization NIPS 2017
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks ICML 2017
Further and stronger analogy between sampling and optimization: Langevin Monte Carlo and gradient descent COLT 2017
Gradient Descent Can Take Exponential Time to Escape Saddle Points NIPS 2017
The Shattered Gradients Problem: If resnets are the answer, then what is the question? ICML 2017
Failures of Gradient-Based Deep Learning ICML 2017
Algorithms and matching lower bounds for approximately-convex optimization NIPS 2016