 |
 A mathematical perspective on TransformersBulletin of the American Mathematical Society (BAMS), 2023 |
 Learning Theory of Distribution Regression with Neural NetworksConstructive approximation (Constr. Approx.), 2023 |
 The Exact Sample Complexity Gain from Invariances for Kernel RegressionNeural Information Processing Systems (NeurIPS), 2023 |
 Efficient anti-symmetrization of a neural network layer by taming the
sign problemJournal of Machine Learning (JML), 2022 |
 Sinkformers: Transformers with Doubly Stochastic AttentionInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2021 |
 On the Universality of Graph Neural Networks on Large Random GraphsNeural Information Processing Systems (NeurIPS), 2021 |
 From Local Structures to Size Generalization in Graph Neural NetworksInternational Conference on Machine Learning (ICML), 2020 |
