 Temperature Balancing, Layer-wise Weight Analysis, and Neural Network
TrainingNeural Information Processing Systems (NeurIPS), 2023 |
 Approximate Heavy Tails in Offline (Multi-Pass) Stochastic Gradient
DescentNeural Information Processing Systems (NeurIPS), 2023 |
 Uniform-in-Time Wasserstein Stability Bounds for (Noisy) Stochastic
Gradient DescentNeural Information Processing Systems (NeurIPS), 2023 |
 Efficient Sampling of Stochastic Differential Equations with Positive
Semi-Definite ModelsNeural Information Processing Systems (NeurIPS), 2023 |
 Generalisation under gradient descent via deterministic PAC-BayesInternational Conference on Algorithmic Learning Theory (ALT), 2022 |
