← Optimization & Theory
Deep Learning › Optimization & Theory ›

Neural Network Optimization

902 directly classified papers

Papers per year

Papers

How SGD Selects the Global Minima in Over-parameterized Learning: A Dynamical Stability Perspective NIPS 2018
Training DNNs with Hybrid Block Floating Point NIPS 2018
L4: Practical loss-based stepsize adaptation for deep learning NIPS 2018
On Neuronal Capacity NIPS 2018
Searching for Efficient Multi-Scale Architectures for Dense Image Prediction NIPS 2018
Kalman Normalization: Normalizing Internal Representations Across Network Layers NIPS 2018
Step Size Matters in Deep Learning NIPS 2018
Algorithmic Regularization in Learning Deep Homogeneous Models: Layers are Automatically Balanced NIPS 2018
Dynamical Isometry and a Mean Field Theory of CNNs: How to Train 10,000-Layer Vanilla Convolutional Neural Networks ICML 2018
Learning Compact Neural Networks with Regularization ICML 2018
Exploring Hidden Dimensions in Accelerating Convolutional Neural Networks ICML 2018
On Acceleration with Noise-Corrupted Gradients ICML 2018
Improving Optimization for Models With Continuous Symmetry Breaking ICML 2018
MorphNet: Fast & Simple Resource-Constrained Structure Learning of Deep Networks CVPR 2018
Learning Time/Memory-Efficient Deep Architectures With Budgeted Super Networks CVPR 2018
A PID Controller Approach for Stochastic Optimization of Deep Networks CVPR 2018
Dissecting Adam: The Sign, Magnitude and Variance of Stochastic Gradients ICML 2018
Densely Connected Networks for Conversational Speech Recognition INTERSPEECH 2018
Efficient Adaptive Online Learning via Frequent Directions IJCAI 2018
On the Convergence Properties of a K-step Averaging Stochastic Gradient Descent Algorithm for Nonconvex Optimization IJCAI 2018
Improving Neural Language Models with Weight Norm Initialization and Regularization EMNLP 2018
Noisy Softmax: Improving the Generalization Ability of DCNN via Postponing the Early Softmax Saturation 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
Gated Recurrent Convolution Neural Network for OCR NIPS 2017
On the Flatness of Loss Surface for Two-layered ReLU Networks ACML 2017