3 papers
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…
cs.CV2024
MobileNetV4 -- Universal Models for the Mobile Ecosystem
Danfeng Qin, Chas Leichner, Manolis Delakis +11
We present the latest generation of MobileNets, known as MobileNetV4 (MNv4), featuring universally efficient architecture designs for mobile devices. At its core, we introduce the…
cs.LG2024
PikeLPN: Mitigating Overlooked Inefficiencies of Low-Precision Neural Networks
Marina Neseem, Conor McCullough, Randy Hsin +8
Low-precision quantization is recognized for its efficacy in neural network optimization. Our analysis reveals that non-quantized elementwise operations which are prevalent in laye…