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

Embedding Principle of Loss Landscape of Deep Neural Networks NIPS 2021
Analytic Study of Families of Spurious Minima in Two-Layer ReLU Neural Networks: A Tale of Symmetry II NIPS 2021
Characterizing possible failure modes in physics-informed neural networks NIPS 2021
Geometry of the Loss Landscape in Overparameterized Neural Networks: Symmetries and Invariances ICML 2021
Robust Optimization for Multilingual Translation with Imbalanced Data NIPS 2021
A Deeper Look at the Hessian Eigenspectrum of Deep Neural Networks and its Applications to Regularization AAAI 2021
Towards Zero-shot Commonsense Reasoning with Self-supervised Refinement of Language Models EMNLP 2021
When Are Solutions Connected in Deep Networks? NIPS 2021
Towards Better Understanding of Training Certifiably Robust Models against Adversarial Examples NIPS 2021
Taxonomizing local versus global structure in neural network loss landscapes NIPS 2021
Exploring the loss landscape in neural architecture search UAI 2021
Identifying untrustworthy predictions in neural networks by geometric gradient analysis UAI 2021
Deep Neural Networks Are Congestion Games: From Loss Landscape to Wardrop Equilibrium and Beyond AISTATS 2021
How to Characterize The Landscape of Overparameterized Convolutional Neural Networks NIPS 2020
Deep learning versus kernel learning: an empirical study of loss landscape geometry and the time evolution of the Neural Tangent Kernel NIPS 2020
Curriculum Learning by Dynamic Instance Hardness NIPS 2020
Adversarial Weight Perturbation Helps Robust Generalization NIPS 2020
Neural Architecture Search in A Proxy Validation Loss Landscape ICML 2020
Escaping the Gravitational Pull of Softmax NIPS 2020
On the Loss Landscape of Adversarial Training: Identifying Challenges and How to Overcome Them NIPS 2020
Optimizing Mode Connectivity via Neuron Alignment NIPS 2020
Unique Properties of Flat Minima in Deep Networks ICML 2020
What is being transferred in transfer learning? NIPS 2020
Eliminating the Invariance on the Loss Landscape of Linear Autoencoders ICML 2020
Towards a Better Global Loss Landscape of GANs NIPS 2020