English
Related papers

Related papers: Beyond Discreteness: Finite-Sample Analysis of Str…

200 papers

Quantized neural network training optimizes a discrete, non-differentiable objective. The straight-through estimator (STE) enables backpropagation through surrogate gradients and is widely used. While previous studies have primarily focused…

Machine Learning · Statistics 2025-10-14 Yuma Ichikawa , Shuhei Kashiwamura , Ayaka Sakata

Training activation quantized neural networks involves minimizing a piecewise constant function whose gradient vanishes almost everywhere, which is undesirable for the standard back-propagation or chain rule. An empirical way around this…

Machine Learning · Computer Science 2019-09-26 Penghang Yin , Jiancheng Lyu , Shuai Zhang , Stanley Osher , Yingyong Qi , Jack Xin

Binarization of neural networks is a dominant paradigm in neural networks compression. The pioneering work BinaryConnect uses Straight Through Estimator (STE) to mimic the gradients of the sign function, but it also causes the crucial…

Computer Vision and Pattern Recognition · Computer Science 2023-08-28 Xiao-Ming Wu , Dian Zheng , Zuhao Liu , Wei-Shi Zheng

Despite the achievements of recent binarization methods on reducing the performance degradation of Binary Neural Networks (BNNs), gradient mismatching caused by the Straight-Through-Estimator (STE) still dominates quantized networks. This…

Computer Vision and Pattern Recognition · Computer Science 2020-09-11 Junjie Liu , Dongchao Wen , Deyu Wang , Wei Tao , Tse-Wei Chen , Kinya Osa , Masami Kato

The discontinuous operations inherent in quantization and sparsification introduce a long-standing obstacle to backpropagation, particularly in ultra-low precision and sparse regimes. While the community has long viewed quantization as…

Machine Learning · Computer Science 2026-03-11 Chengxi Ye , Grace Chu , Yanfeng Liu , Yichi Zhang , Lukasz Lew , Li Zhang , Mark Sandler , Andrew Howard

Neural network quantization aims to reduce the bit-widths of weights and activations, making it a critical technique for deploying deep neural networks on resource-constrained hardware. Most Quantization-Aware Training (QAT) methods rely on…

Machine Learning · Computer Science 2025-09-03 Kaiqi Zhao

Quantization has become a predominant approach for model compression, enabling deployment of large models trained on GPUs onto smaller form-factor devices for inference. Quantization-aware training (QAT) optimizes model parameters with…

Machine Learning · Computer Science 2022-12-13 Zheng Wang , Juncheng B Li , Shuhui Qu , Florian Metze , Emma Strubell

The Straight-Through Estimator (STE) is the dominant method for training neural networks with discrete variables, enabling gradient-based optimisation by routing gradients through a differentiable surrogate. However, existing STE variants…

Machine Learning · Computer Science 2026-02-24 Rushi Shah , Mingyuan Yan , Michael Curtis Mozer , Dianbo Liu

Quantization-aware training comes with a fundamental challenge: the derivative of quantization functions such as rounding are zero almost everywhere and nonexistent elsewhere. Various differentiable approximations of quantization functions…

Machine Learning · Computer Science 2024-05-24 Matt Schoenbauer , Daniele Moro , Lukasz Lew , Andrew Howard

Network quantization aims at reducing bit-widths of weights and/or activations, particularly important for implementing deep neural networks with limited hardware resources. Most methods use the straight-through estimator (STE) to train…

Computer Vision and Pattern Recognition · Computer Science 2021-04-05 Junghyup Lee , Dohyung Kim , Bumsub Ham

The Straight-Through Estimator (STE) is widely used for back-propagating gradients through the quantization function, but the STE technique lacks a complete theoretical understanding. We propose an alternative methodology called…

Machine Learning · Computer Science 2019-05-22 Zhi-Gang Liu , Matthew Mattina

Training neural networks with binary weights and activations is a challenging problem due to the lack of gradients and difficulty of optimization over discrete weights. Many successful experimental results have been achieved with empirical…

Machine Learning · Statistics 2021-10-20 Alexander Shekhovtsov , Viktor Yanush

Quantized or low-bit neural networks are attractive due to their inference efficiency. However, training deep neural networks with quantized activations involves minimizing a discontinuous and piecewise constant loss function. Such a loss…

Machine Learning · Computer Science 2021-06-15 Ziang Long , Penghang Yin , Jack Xin

The {\it straight-through estimator} (STE) is commonly used to optimize quantized neural networks, yet its contexts of effective performance are still unclear despite empirical successes.To make a step forward in this comprehension, we…

Machine Learning · Computer Science 2024-06-26 Mimoun Mohamed , François Malgouyres , Valentin Emiya , Caroline Chaux

We tackle the problem of producing compact models, maximizing their accuracy for a given model size. A standard solution is to train networks with Quantization Aware Training, where the weights are quantized during training and the…

Machine Learning · Computer Science 2021-03-02 Angela Fan , Pierre Stock , Benjamin Graham , Edouard Grave , Remi Gribonval , Herve Jegou , Armand Joulin

Straight-through estimator (STE), which enables the gradient flow over the non-differentiable function via approximation, has been favored in studies related to quantization-aware training (QAT). However, STE incurs unstable convergence…

Machine Learning · Computer Science 2023-07-04 Juncheol Shin , Junhyuk So , Sein Park , Seungyeop Kang , Sungjoo Yoo , Eunhyeok Park

We propose a new algorithm for training deep neural networks (DNNs) with binary weights. In particular, we first cast the problem of training binary neural networks (BiNNs) as a bilevel optimization instance and subsequently construct…

Machine Learning · Computer Science 2021-12-07 Huu Le , Rasmus Kjær Høier , Che-Tsung Lin , Christopher Zach

Quantized neural networks can be viewed as a chain of noisy channels, where rounding in each layer reduces capacity as bit-width shrinks; the floating-point (FP) checkpoint sets the maximum input rate. We track capacity dynamics as the…

Machine Learning · Computer Science 2025-11-12 Sergey Salishev , Ian Akhremchik

Training quantised neural networks (QNNs) is a non-differentiable optimisation problem since weights and features are output by piecewise constant functions. The standard solution is to apply the straight-through estimator (STE), using…

Machine Learning · Computer Science 2022-03-23 Matteo Spallanzani , Gian Paolo Leonardi , Luca Benini

This work examines the challenges of training neural networks using vector quantization using straight-through estimation. We find that a primary cause of training instability is the discrepancy between the model embedding and the…

Machine Learning · Computer Science 2023-05-16 Minyoung Huh , Brian Cheung , Pulkit Agrawal , Phillip Isola
‹ Prev 1 2 3 10 Next ›