 |
 DASS: Differentiable Architecture Search for Sparse neural networksACM Transactions on Embedded Computing Systems (TECS), 2022 |
 Spartan: Differentiable Sparsity via Regularized TransportationNeural Information Processing Systems (NeurIPS), 2022 |
 Accelerating Attention through Gradient-Based Learned Runtime PruningInternational Symposium on Computer Architecture (ISCA), 2022 |
 SD-Conv: Towards the Parameter-Efficiency of Dynamic ConvolutionIEEE Workshop/Winter Conference on Applications of Computer Vision (WACV), 2022 |
 Learning Pruned Structure and Weights Simultaneously from Scratch: an
Attention based ApproachBigData Congress [Services Society] (BSS), 2021 |
 Efficient and Sparse Neural Networks by Pruning Weights in a
Multiobjective Learning ApproachComputers & Operations Research (Comput. Oper. Res.), 2020 |
 Soft Threshold Weight Reparameterization for Learnable SparsityInternational Conference on Machine Learning (ICML), 2020 |
