Neural Networks Efficiently Learn Low-Dimensional Representations with
SGDInternational Conference on Learning Representations (ICLR), 2022 |
Towards Data-Algorithm Dependent Generalization: a Case Study on
Overparameterized Linear RegressionNeural Information Processing Systems (NeurIPS), 2022 |
Stability & Generalisation of Gradient Descent for Shallow Neural
Networks without the Neural Tangent KernelNeural Information Processing Systems (NeurIPS), 2021 |
On the Role of Optimization in Double Descent: A Least Squares StudyNeural Information Processing Systems (NeurIPS), 2021 |