StoMPP progressively binarizes BNN layers layerwise from input to output via stochastic masks, delivering depth-scalable accuracy gains in a fully STE-free regime by controlling activation-induced gradient blockades.
Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
abstract
We introduce a method to train Quantized Neural Networks (QNNs) --- neural networks with extremely low precision (e.g., 1-bit) weights and activations, at run-time. At train-time the quantized weights and activations are used for computing the parameter gradients. During the forward pass, QNNs drastically reduce memory size and accesses, and replace most arithmetic operations with bit-wise operations. As a result, power consumption is expected to be drastically reduced. We trained QNNs over the MNIST, CIFAR-10, SVHN and ImageNet datasets. The resulting QNNs achieve prediction accuracy comparable to their 32-bit counterparts. For example, our quantized version of AlexNet with 1-bit weights and 2-bit activations achieves $51\%$ top-1 accuracy. Moreover, we quantize the parameter gradients to 6-bits as well which enables gradients computation using only bit-wise operation. Quantized recurrent neural networks were tested over the Penn Treebank dataset, and achieved comparable accuracy as their 32-bit counterparts using only 4-bits. Last but not least, we programmed a binary matrix multiplication GPU kernel with which it is possible to run our MNIST QNN 7 times faster than with an unoptimized GPU kernel, without suffering any loss in classification accuracy. The QNN code is available online.
citation-role summary
background 3
citation-polarity summary
roles
background 3polarities
background 3representative citing papers
Speculative decoding accelerates exact sampling from large autoregressive models by 2-3x on T5-XXL by running smaller approximation models in parallel to propose token sequences that the large model then verifies in batches while preserving the original output distribution.
Mixed precision training uses FP16 for most computations, FP32 master weights for accumulation, and loss scaling to enable accurate training of large DNNs with halved memory usage.
MobileNets introduce depthwise separable convolutions plus width and resolution multipliers to produce efficient CNNs that trade off latency and accuracy for mobile and embedded vision applications.
Sign-flip perturbations produce π/(π-2) ≈ 2.75 times more transverse output energy than equal-norm sign-preserving perturbations in a ReLU + RMSNorm block because ReLU creates directional asymmetry that RMSNorm's transverse projection exposes.
LoKA enables practical FP8 use in numerically sensitive large recommendation models via online profiling of activations, reusable model modifications for stability, and dynamic kernel dispatching.
EPNAS uses a progressive search policy with REINFORCE performance prediction to search neural architectures in parallel, supporting multiple resource constraints and outperforming ENAS and PNAS on CIFAR-10 and ImageNet in speed and accuracy.
Replacing pointwise convolutions with DWHT yields a model with 79.1% fewer parameters, 48.4% fewer FLOPs, and 1.49% higher accuracy than MobileNet-V1 on CIFAR-100.
citing papers explorer
-
Layerwise Progressive Freezing: A Training Scaffold for Depth-Scalable Binary Networks
StoMPP progressively binarizes BNN layers layerwise from input to output via stochastic masks, delivering depth-scalable accuracy gains in a fully STE-free regime by controlling activation-induced gradient blockades.
-
Fast Inference from Transformers via Speculative Decoding
Speculative decoding accelerates exact sampling from large autoregressive models by 2-3x on T5-XXL by running smaller approximation models in parallel to propose token sequences that the large model then verifies in batches while preserving the original output distribution.
-
Mixed Precision Training
Mixed precision training uses FP16 for most computations, FP32 master weights for accumulation, and loss scaling to enable accurate training of large DNNs with halved memory usage.
-
MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
MobileNets introduce depthwise separable convolutions plus width and resolution multipliers to produce efficient CNNs that trade off latency and accuracy for mobile and embedded vision applications.
-
A Geometric Analysis of Sign-Magnitude Asymmetry in a ReLU + RMSNorm Block under Ternary Quantization
Sign-flip perturbations produce π/(π-2) ≈ 2.75 times more transverse output energy than equal-norm sign-preserving perturbations in a ReLU + RMSNorm block because ReLU creates directional asymmetry that RMSNorm's transverse projection exposes.
-
LoKA: Low-precision Kernel Applications for Recommendation Models At Scale
LoKA enables practical FP8 use in numerically sensitive large recommendation models via online profiling of activations, reusable model modifications for stability, and dynamic kernel dispatching.
-
EPNAS: Efficient Progressive Neural Architecture Search
EPNAS uses a progressive search policy with REINFORCE performance prediction to search neural architectures in parallel, supporting multiple resource constraints and outperforming ENAS and PNAS on CIFAR-10 and ImageNet in speed and accuracy.
-
New pointwise convolution in Deep Neural Networks through Extremely Fast and Non Parametric Transforms
Replacing pointwise convolutions with DWHT yields a model with 79.1% fewer parameters, 48.4% fewer FLOPs, and 1.49% higher accuracy than MobileNet-V1 on CIFAR-100.