 Uniform convergence may be unable to explain generalization in deep
learningNeural Information Processing Systems (NeurIPS), 2019 Vaishnavh Nagarajan J. Zico Kolter |
 Asymmetric Valleys: Beyond Sharp and Flat Local MinimaNeural Information Processing Systems (NeurIPS), 2019 |
 Compressing Gradient Optimizers via Count-SketchesInternational Conference on Machine Learning (ICML), 2019 |
 Deep Frank-Wolfe For Neural Network OptimizationInternational Conference on Learning Representations (ICLR), 2018 |
 Measuring the Effects of Data Parallelism on Neural Network TrainingJournal of machine learning research (JMLR), 2018 |
 The jamming transition as a paradigm to understand the loss landscape of
deep neural networksPhysical Review E (PRE), 2018 |
 A New Benchmark and Progress Toward Improved Weakly Supervised LearningBritish Machine Vision Conference (BMVC), 2018 |
