 |
 |
 On the insufficiency of existing momentum schemes for Stochastic
OptimizationInformation Theory and Applications Workshop (ITA), 2018 |
 Averaging Weights Leads to Wider Optima and Better GeneralizationConference on Uncertainty in Artificial Intelligence (UAI), 2018 |
 Essentially No Barriers in Neural Network Energy LandscapeInternational Conference on Machine Learning (ICML), 2018 |
 Neural Inverse Rendering for General Reflectance Photometric StereoInternational Conference on Machine Learning (ICML), 2018 Tatsunori Taniai Takanori Maehara |
 Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNsNeural Information Processing Systems (NeurIPS), 2018 |
 Solving Inverse Computational Imaging Problems using Deep Pixel-level
PriorIEEE Transactions on Computational Imaging (TCI), 2018 |
 |
