Deep Learning
Position-based Scaled Gradient for Model Quantization and Pruning
We propose the position-based scaled gradient (PSG) that scales the gradient depending on the position of a weight vector to make it more compression-friendly.
Sanity-Checking Pruning Methods: Random Tickets can Win the Jackpot
Network pruning is a method for reducing test-time computational resource requirements with minimal performance degradation.
Sanity-Checking Pruning Methods: Random Tickets can Win the Jackpot
Network pruning is a method for reducing test-time computational resource requirements with minimal performance degradation.
Movement Pruning: Adaptive Sparsity by Fine-Tuning
Magnitude pruning [Han et al., 2015, 2016b], which preserves weights with high absolute values, is
Flamingo: a Visual Language Model for Few-Shot Learning Jean-Baptiste Alayrac *, Jeff Donahue * Pauline Luc * Antoine Miech
They are mainly found in Chile.