El houcine Bergou

LEGACY: A Lightweight Dynamic Gradient Compression Strategy for Distributed Deep Learning

When Less Is More: Uncovering the Robustness Advantage of Model Pruning

Unveiling the Hidden Structure: Tight Bounds for Matrix Multiplication Approximation via Convex Optimization

LoRA: The Past, Present, and Future

SSProNet: Secondary Structure aware Graph Neural Network for Protein Representation Learning

LEGACY: A Lightweight Adaptive Gradient Compression Strategy for Distributed Deep Learning