conftrace_
← Optimization & Theory
Machine Learning › Optimization & Theory ›

Neural Network Optimization

3,649 papers

Papers per year

2
5
40
414
386
'05
'10
'15
'20
'25

Papers

Accumulated Gradient Normalization ACML 2017
On the Flatness of Loss Surface for Two-layered ReLU Networks ACML 2017
ASAGA: Asynchronous Parallel SAGA AISTATS 2017
Less than a Single Pass: Stochastically Controlled Stochastic Gradient AISTATS 2017
A Modular Analysis of Adaptive (Non-)Convex Optimization: Optimism, Composite Objectives, and Variational Bounds ALT 2017
Depth Separation for Neural Networks COLT 2017
Surprising properties of dropout in deep networks COLT 2017
Unrolling the Shutter: CNN to Correct Motion Distortions CVPR 2017
Fast Video Classification via Adaptive Cascading of Deep Models CVPR 2017
Improving Training of Deep Neural Networks via Singular Value Bounding CVPR 2017
Noisy Softmax: Improving the Generalization Ability of DCNN via Postponing the Early Softmax Saturation CVPR 2017
More Is Less: A More Complicated Network With Less Inference Complexity CVPR 2017
All You Need Is Beyond a Good Init: Exploring Better Solution for Training Extremely Deep Convolutional Neural Networks With Orthonormality and Modulation CVPR 2017
Global Optimality in Neural Network Training CVPR 2017
Gated End-to-End Memory Networks EACL 2017
Why ADAGRAD Fails for Online Topic Modeling EMNLP 2017
Deep Neural Solver for Math Word Problems EMNLP 2017
Trainable Greedy Decoding for Neural Machine Translation EMNLP 2017
Generating High-Quality and Informative Conversation Responses with Sequence-to-Sequence Models EMNLP 2017
The Shattered Gradients Problem: If resnets are the answer, then what is the question? ICML 2017
Neural Optimizer Search with Reinforcement Learning ICML 2017
Programming with a Differentiable Forth Interpreter ICML 2017
Practical Gauss-Newton Optimisation for Deep Learning ICML 2017
Globally Optimal Gradient Descent for a ConvNet with Gaussian Inputs ICML 2017
Learning to Learn without Gradient Descent by Gradient Descent ICML 2017