conftrace_

loss landscape

149 papers

Explore in graph

Co-occurring keywords

neural network optimization (1293) gradient descent (1144) neural network (6616) sharpness-aware minimization (81) stochastic gradient descent (1091) flat minima (50) deep neural network (1803) mode connectivity (17) transfer learning (5449) neural network training (309)

Papers

Dynamical mean-field theory for stochastic gradient descent in Gaussian mixture classification NIPS 2020
Stabilizing Differentiable Architecture Search via Perturbation-based Regularization ICML 2020
Is the Skip Connection Provable to Reform the Neural Network Loss Landscape? IJCAI 2020
Finding the Needle in the Haystack with Convolutions: on the benefits of architectural bias NIPS 2019
The Normalization Method for Alleviating Pathological Sharpness in Wide Neural Networks NIPS 2019
Addressing the Loss-Metric Mismatch with Adaptive Loss Alignment ICML 2019
Semi-flat minima and saddle points by embedding neural networks to overparameterization NIPS 2019
Explaining Landscape Connectivity of Low-cost Solutions for Multilayer Nets NIPS 2019
The Goldilocks Zone: Towards Better Understanding of Neural Network Loss Landscapes AAAI 2019
Exponential convergence rates for Batch Normalization: The power of length-direction decoupling in non-convex optimization AISTATS 2019
Learning One-hidden-layer Neural Networks under General Input Distributions AISTATS 2019
Large Scale Structure of Neural Network Loss Landscapes NIPS 2019
Interpreting and Evaluating Neural Network Robustness IJCAI 2019
Visualizing and Understanding the Effectiveness of BERT IJCNLP 2019
Spurious Valleys in One-hidden-layer Neural Network Optimization Landscapes JMLR 2019
Robustness via Curvature Regularization, and Vice Versa CVPR 2019
On Connected Sublevel Sets in Deep Learning ICML 2019
Visualizing and Understanding the Effectiveness of BERT EMNLP 2019
Visualizing the Loss Landscape of Neural Nets NIPS 2018
Comparing Dynamics: Deep Neural Networks versus Glassy Systems ICML 2018
Optimization Landscape and Expressivity of Deep CNNs ICML 2018
Adding One Neuron Can Eliminate All Bad Local Minima NIPS 2018
On the Flatness of Loss Surface for Two-layered ReLU Networks ACML 2017
On the Quality of the Initial Basin in Overspecified Neural Networks ICML 2016