TUNG QUOC LE

2 accepted papers

2025

Fast Inference with Kronecker-Sparse Matrices

Antoine Gonon, Léon Zheng, Pascal Carrivain, TUNG QUOC LE

ICML 2025poster

Kronecker-sparse (KS) matrices—whose supports are Kronecker products of identity and all-ones blocks—underpin the structure of Butterfly and Monarch matrices and offer the promise of more efficient models. However, existing GPU kernels for KS matrix multiplication suffer from high data movement cost…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2023

Does a sparse ReLU network training problem always admit an optimum ?

TUNG QUOC LE, Rémi Gribonval, Elisa Riccietti

NeurIPS 2023poster

Given a training set, a loss function, and a neural network architecture, it is often taken for granted that optimal network parameters exist, and a common practice is to apply available optimization algorithms to search for them. In this work, we show that the existence of an optimal solution is no…

Cited by 6 Source ↗PDF ↗Scholar ↗