 Lite it fly: An All-Deformable-Butterfly NetworkIEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2023 |
 Does a sparse ReLU network training problem always admit an optimum?Neural Information Processing Systems (NeurIPS), 2023 |
 Simple Hardware-Efficient Long Convolutions for Sequence ModelingInternational Conference on Machine Learning (ICML), 2023 |
 Monarch: Expressive Structured Matrices for Efficient and Accurate
TrainingInternational Conference on Machine Learning (ICML), 2022 |
