English
Related papers

Related papers: Initializing Models with Larger Ones

200 papers

As a neural network's depth increases, it can improve generalization performance. However, training deep networks is challenging due to gradient and signal propagation issues. To address these challenges, extensive theoretical research and…

Machine Learning · Computer Science 2025-03-04 Hyunwoo Lee , Hayoung Choi , Hyunju Kim

Transformer-based Large Language Models (LLMs) have revolutionized Natural Language Processing by demonstrating exceptional performance across diverse tasks. This study investigates the impact of the parameter initialization scale on the…

Computation and Language · Computer Science 2025-05-22 Junjie Yao , Zhongwang Zhang , Zhi-Qin John Xu

In this article, we introduce a novel normalization technique for neural network weight matrices, which we term weight conditioning. This approach aims to narrow the gap between the smallest and largest singular values of the weight…

Computer Vision and Pattern Recognition · Computer Science 2026-03-16 Hemanth Saratchandran , Thomas X. Wang , Simon Lucey

When training data is scarce, the incorporation of additional prior knowledge can assist the learning process. While it is common to initialize neural networks with weights that have been pre-trained on other large data sets, pre-training…

Machine Learning · Computer Science 2022-05-24 Laura von Rueden , Sebastian Houben , Kostadin Cvejoski , Christian Bauckhage , Nico Piatkowski

Neural networks based on metric recognition methods have a strictly determined architecture. Number of neurons, connections, as well as weights and thresholds values are calculated analytically, based on the initial conditions of tasks:…

Neural and Evolutionary Computing · Computer Science 2025-06-10 Polad Geidarov

Artificial neural networks can acquire many aspects of human knowledge from data, making them promising as models of human learning. But what those networks can learn depends upon their inductive biases -- the factors other than the data…

Machine Learning · Computer Science 2025-02-28 Gianluca Bencomo , Max Gupta , Ioana Marinescu , R. Thomas McCoy , Thomas L. Griffiths

This paper addresses how a recursive neural network model can automatically leave out useless information and emphasize important evidence, in other words, to perform "weight tuning" for higher-level representation acquisition. We propose…

Neural and Evolutionary Computing · Computer Science 2014-12-16 Jiwei Li

This paper proposes a novel, efficient transfer learning method, called Scalable Weight Reparametrization (SWR) that is efficient and effective for multiple downstream tasks. Efficient transfer learning involves utilizing a pre-trained…

Machine Learning · Computer Science 2023-02-28 Byeonggeun Kim , Jun-Tae Lee , Seunghan yang , Simyung Chang

Deep learning models have become increasingly large and complex, resulting in higher memory consumption and computational demands. Consequently, model loading times and initial inference latency have increased, posing significant challenges…

Machine Learning · Computer Science 2025-10-02 Hyunwoo Kim , Junha Lee , Mincheol Choi , Jeonghwan Lee , Jaeshin Cho

Many pre-trained models (PTMs) are available in modern applications. Because different PTMs are often trained on different datasets, their performances can vary substantially for different new tasks, and the ranking of the candidates may…

Methodology · Statistics 2026-05-14 Ziwen Gao , Baihua He , Yuhong Yang

Loss of plasticity is a phenomenon in which a neural network loses its ability to learn when trained for an extended time on non-stationary data. It is a crucial problem to overcome when designing systems that learn continually. An…

Neural and Evolutionary Computing · Computer Science 2025-08-21 J. Fernando Hernandez-Garcia , Shibhansh Dohare , Jun Luo , Rich S. Sutton

Automated machine learning (AutoML) methods improve upon existing models by optimizing various aspects of their design. While present methods focus on hyperparameters and neural network topologies, other aspects of neural network design can…

Machine Learning · Computer Science 2023-04-10 Garrett Bingham

The huge size of deep networks hinders their use in small computing devices. In this paper, we consider compressing the network by weight quantization. We extend a recently proposed loss-aware weight binarization scheme to ternarization,…

Machine Learning · Computer Science 2018-05-11 Lu Hou , James T. Kwok

Deep neural networks produce state-of-the-art results when trained on a large number of labeled examples but tend to overfit when small amounts of labeled examples are used for training. Creating a large number of labeled examples requires…

Computer Vision and Pattern Recognition · Computer Science 2021-09-13 Attaullah Sahito , Eibe Frank , Bernhard Pfahringer

The ability to train randomly initialised deep neural networks is known to depend strongly on the variance of the weight matrices and biases as well as the choice of nonlinear activation. Here we complement the existing geometric analysis…

Information Theory · Computer Science 2021-02-09 Jared Tanner , Giuseppe Ughi

1-bit LLM quantization offers significant advantages in reducing storage and computational costs. However, existing methods typically train 1-bit LLMs from scratch, failing to fully leverage pre-trained models. This results in high training…

Computation and Language · Computer Science 2026-05-19 Zhijun Tu , Jian Li , Yuanyuan Xi , Siqi Liu , Chuanjian Liu , Hanting Chen , Jie Hu , Yunhe Wang

Training deep neural networks results in strong learned representations that show good generalization capabilities. In most cases, training involves iterative modification of all weights inside the network via back-propagation. In Extreme…

Machine Learning · Computer Science 2018-02-06 Amir Rosenfeld , John K. Tsotsos

Pretrained models are the standard starting point for training. This approach consistently outperforms the use of a random initialization. However, pretraining is a costly endeavour that few can undertake. In this paper, we create better…

Computation and Language · Computer Science 2022-04-08 Leshem Choshen , Elad Venezian , Noam Slonim , Yoav Katz

Foundation models are pre-trained on large-scale datasets and subsequently fine-tuned on small-scale datasets using parameter-efficient fine-tuning (PEFT) techniques like low-rank adapters (LoRA). In most previous works, LoRA weight…

Computer Vision and Pattern Recognition · Computer Science 2025-07-14 Debasmit Das , Hyoungwoo Park , Munawar Hayat , Seokeon Choi , Sungrack Yun , Fatih Porikli

Weights initialization in deep neural networks have a strong impact on the speed of converge of the learning map. Recent studies have shown that in the case of random initializations, a chaos/order phase transition occur in the space of…

Machine Learning · Computer Science 2023-06-28 Carlos Cardona