English
Related papers

Related papers: Weight decay induces low-rank attention layers

200 papers

Overfitting is one of the critical problems in deep neural networks. Many regularization schemes try to prevent overfitting blindly. However, they decrease the convergence speed of training algorithms. Adaptive regularization schemes can…

Machine Learning · Computer Science 2021-06-18 Mohammad Mahdi Bejani , Mehdi Ghatee

Large-batch training has become a cornerstone in accelerating the training of deep neural networks, yet it poses challenges in optimization and generalization. Existing optimizers like AdamW present performance degradation during language…

Machine Learning · Computer Science 2025-08-29 Yang Luo , Zangwei Zheng , Ziheng Qin , Zirui Zhu , Yong Liu , Yang You

Over the past few years, Batch-Normalization has been commonly used in deep networks, allowing faster training and high performance for a wide variety of applications. However, the reasons behind its merits remained unanswered, with several…

Machine Learning · Statistics 2019-02-08 Elad Hoffer , Ron Banner , Itay Golan , Daniel Soudry

Factorized layers--operations parameterized by products of two or more matrices--occur in a variety of deep learning contexts, including compressed model training, certain types of knowledge distillation, and multi-head self-attention…

Machine Learning · Statistics 2022-10-07 Mikhail Khodak , Neil Tenenholtz , Lester Mackey , Nicolò Fusi

In low-latency or mobile applications, lower computation complexity, lower memory footprint and better energy efficiency are desired. Many prior works address this need by removing redundant parameters. Parameter quantization replaces…

Machine Learning · Computer Science 2021-11-16 Cheng-Chou Lan

The prevailing paradigm in large language model (LLM) development is to pretrain a base model, then perform further training to improve performance and model behavior. However, hyperparameter optimization and scaling laws have been studied…

Machine Learning · Computer Science 2026-02-12 Tessa Han , Sebastian Bordt , Hanlin Zhang , Sham Kakade

Weight decay is a broadly used technique for training state-of-the-art deep networks from image classification to large language models. Despite its widespread usage and being extensively studied in the classical literature, its role…

Machine Learning · Computer Science 2024-11-06 Francesco D'Angelo , Maksym Andriushchenko , Aditya Varre , Nicolas Flammarion

Deep learning regularization techniques, such as dropout, layer normalization, or weight decay, are widely adopted in the construction of modern artificial neural networks, often resulting in more robust training processes and improved…

Machine Learning · Computer Science 2024-11-22 Denis Tarasov , Anja Surina , Caglar Gulcehre

Improving the efficiency of inference in Large Language Models (LLMs) is a critical area of research. Post-training Quantization (PTQ) is a popular technique, but it often faces challenges at low-bit levels, particularly in downstream…

Computer Vision and Pattern Recognition · Computer Science 2025-04-15 Wenjin Ke , Zhe Li , Dong Li , Lu Tian , Emad Barsoum

Regularization is a fundamental technique to prevent over-fitting and to improve generalization performances by constraining a model's complexity. Current Deep Networks heavily rely on regularizers such as Data-Augmentation (DA) or…

Machine Learning · Computer Science 2022-04-12 Randall Balestriero , Leon Bottou , Yann LeCun

The weight decay regularization term is widely used during training to constrain expressivity, avoid overfitting, and improve generalization. Historically, this concept was borrowed from the SVM maximum margin principle and extended to…

Machine Learning · Computer Science 2021-10-12 Berry Weinstein , Shai Fine , Yacov Hel-Or

Deep neural networks exploiting millions of parameters are nowadays the norm in deep learning applications. This is a potential issue because of the great amount of computational resources needed for training, and of the possible loss of…

Computation and Language · Computer Science 2022-10-31 Giovanni Bonetta , Matteo Ribero , Rossella Cancelliere

With the commercialization of large language models (LLMs), weight-activation quantization has emerged to compress and accelerate LLMs, achieving high throughput while reducing inference costs. However, existing post-training quantization…

Machine Learning · Computer Science 2025-02-11 Jung Hyun Lee , Jeonghoon Kim , June Yong Yang , Se Jung Kwon , Eunho Yang , Kang Min Yoo , Dongsoo Lee

We present weight normalization: a reparameterization of the weight vectors in a neural network that decouples the length of those weight vectors from their direction. By reparameterizing the weights in this way we improve the conditioning…

Machine Learning · Computer Science 2016-06-07 Tim Salimans , Diederik P. Kingma

The success of deep neural networks is in part due to the use of normalization layers. Normalization layers like Batch Normalization, Layer Normalization and Weight Normalization are ubiquitous in practice, as they improve generalization…

Machine Learning · Computer Science 2020-06-15 Yonatan Dukler , Quanquan Gu , Guido Montúfar

We propose a novel regularization method, called \textit{volumization}, for neural networks. Inspired by physics, we define a physical volume for the weight parameters in neural networks, and we show that this method is an effective way of…

Machine Learning · Computer Science 2020-04-02 Liu Ziyin , Zihao Wang , Makoto Yamada , Masahito Ueda

This paper investigates low-rank structure in the gradients of the training loss for two-layer neural networks while relaxing the usual isotropy assumptions on the training data and parameters. We consider a spiked data model in which the…

Machine Learning · Computer Science 2025-10-03 Rishi Sonthalia , Michael Murray , Guido Montúfar

Post-training quantization is widely employed to reduce the computational demands of neural networks. Typically, individual substructures, such as layers or blocks of layers, are quantized with the objective of minimizing quantization…

Machine Learning · Computer Science 2024-11-07 Khasmamad Shabanovi , Lukas Wiest , Vladimir Golkov , Daniel Cremers , Thomas Pfeil

Recent results suggest that reinitializing a subset of the parameters of a neural network during training can improve generalization, particularly for small training sets. We study the impact of different reinitialization methods in several…

Machine Learning · Computer Science 2021-09-02 Ibrahim Alabdulmohsin , Hartmut Maennel , Daniel Keysers

Transformers trained on modular arithmetic exhibit sharp transitions between memorization, generalization, and collapse. We show that weight decay acts as a scalar empirical control parameter for these regimes, and introduce two cheap…

Machine Learning · Computer Science 2026-05-21 Lucky Verma