Showing results 1 to 13 of 13
Title | Author(s) | Issue Date | |
---|---|---|---|
A generalized neural tangent kernel analysis for two-layer neural networks Proceeding/Conference:Advances in Neural Information Processing Systems 33 (NeurIPS 2020) | 2020 | ||
Agnostic learning of a single neuron with gradient descent Proceeding/Conference:Advances in Neural Information Processing Systems 33 (NeurIPS 2020) | 2020 | ||
Algorithm-dependent generalization bounds for overparameterized deep residual networks Proceeding/Conference:Advances in Neural Information Processing Systems 32 (NeurIPS 2019) | 2019 | ||
Benign Overfitting in Two-layer Convolutional Neural Networks Proceeding/Conference:NeurIPS 2022 (28/11/2022-09/12/2022, New Orleans ) | 9-Dec-2022 | ||
Closing the generalization gap of adaptive gradient methods in training deep neural networks Proceeding/Conference:Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence | 2020 | ||
Generalization bounds of stochastic gradient descent for wide and deep neural networks Proceeding/Conference:Advances in Neural Information Processing Systems 32 (NeurIPS 2019) | 2019 | ||
Generalization error bounds of gradient descent for learning over-parameterized deep relu networks Proceeding/Conference:Proceedings of the AAAI Conference on Artificial Intelligence | 2020 | ||
Gradient descent optimizes over-parameterized deep ReLU networks Journal:Machine Learning | 2020 | ||
The Benefits of Mixup for Feature Learning
Proceeding/Conference:Fortieth International Conference on Machine Learning (ICML) (23/07/2023-29/07/2023, Honolulu, Hawaii, USA) | 23-Jul-2023 | ||
The Implicit Bias of Batch Normalization in Linear Models and Two-layer Linear Convolutional Neural Networks
Proceeding/Conference:36th Annual Conference on Learning Theory (COLT 2023) (12/07/2023-15/07/2023, Bangalore, India) | 15-Jul-2023 | ||
Tight sample complexity of learning one-hidden-layer convolutional neural networks Proceeding/Conference:Advances in Neural Information Processing Systems 32 (NeurIPS 2019) | 2019 | ||
Understanding the Generalization of Adam in Learning Neural Networks with Proper Regularization Proceeding/Conference:International Conference on Learning Representations (ICLR 2023) (01/05/2023-05/05/2023, Kigali, Rwanda) | 5-May-2023 | ||
Understanding Train-Validation Split in Meta-Learning with Neural Networks Proceeding/Conference:The 11th International Conference on Learning Representations (ICLR 2023) (01/05/2023-05/05/2023, Kigali, Rwanda) | 5-May-2023 |