2 papers
cs.LG2024
Robust Training of Neural Networks at Arbitrary Precision and Sparsity
Chengxi Ye, Grace Chu, Yanfeng Liu +5
The discontinuous operations inherent in quantization and sparsification introduce a long-standing obstacle to backpropagation, particularly in ultra-low precision and sparse regim…
cs.LG2024
Custom Gradient Estimators are Straight-Through Estimators in Disguise
Matt Schoenbauer, Daniele Moro, Lukasz Lew +1
Quantization-aware training comes with a fundamental challenge: the derivative of quantization functions such as rounding are zero almost everywhere and nonexistent elsewhere. Vari…