loss landscape

Relating Adversarially Robust Generalization to Flat Minima ICCV 2021 Robust Optimization for Multilingual Translation with Imbalanced Data NeurIPS 2021 Sharpness-aware Minimization for Efficiently Improving Generalization ICLR 2021 Taxonomizing local versus global structure in neural network loss landscapes NeurIPS 2021 Tilting the playing field: Dynamical loss functions for machine learning ICML 2021 Towards Better Understanding of Training Certifiably Robust Models against Adversarial Examples NeurIPS 2021 Towards Zero-shot Commonsense Reasoning with Self-supervised Refinement of Language Models EMNLP 2021 When Are Solutions Connected in Deep Networks? NeurIPS 2021 Adversarial Weight Perturbation Helps Robust Generalization NeurIPS 2020 Bounds on Over-Parameterization for Guaranteed Existence of Descent Paths in Shallow ReLU Networks ICLR 2020 Bridging Mode Connectivity in Loss Landscapes and Adversarial Robustness ICLR 2020 Curriculum Learning by Dynamic Instance Hardness NeurIPS 2020 Deep learning versus kernel learning: an empirical study of loss landscape geometry and the time evolution of the Neural Tangent Kernel NeurIPS 2020 Dynamical mean-field theory for stochastic gradient descent in Gaussian mixture classification NeurIPS 2020 Eliminating the Invariance on the Loss Landscape of Linear Autoencoders ICML 2020 Escaping the Gravitational Pull of Softmax NeurIPS 2020 How to Characterize The Landscape of Overparameterized Convolutional Neural Networks NeurIPS 2020 Is the Skip Connection Provable to Reform the Neural Network Loss Landscape? IJCAI 2020 Neural Architecture Search in A Proxy Validation Loss Landscape ICML 2020 On the Loss Landscape of Adversarial Training: Identifying Challenges and How to Overcome Them NeurIPS 2020 Optimizing Mode Connectivity via Neuron Alignment NeurIPS 2020 Pure and Spurious Critical Points: a Geometric Study of Linear Networks ICLR 2020 Stabilizing Differentiable Architecture Search via Perturbation-based Regularization ICML 2020 The intriguing role of module criticality in the generalization of deep networks ICLR 2020 Towards a Better Global Loss Landscape of GANs NeurIPS 2020