English
Related papers

Related papers: Nonlinear Initialization Methods for Low-Rank Neur…

200 papers

A new initialization method for hidden parameters in a neural network is proposed. Derived from the integral representation of the neural network, a nonparametric probability distribution of hidden parameters is introduced. In this…

Machine Learning · Computer Science 2014-02-20 Sho Sonoda , Noboru Murata

Network initialization is the first and critical step for training neural networks. In this paper, we propose a novel network initialization scheme based on the celebrated Stein's identity. By viewing multi-layer feedforward neural networks…

Machine Learning · Computer Science 2020-06-26 Zebin Yang , Hengtao Zhang , Agus Sudjianto , Aijun Zhang

Neural networks have achieved tremendous success in a large variety of applications. However, their memory footprint and computational demand can render them impractical in application settings with limited hardware or energy resources. In…

Machine Learning · Computer Science 2022-10-19 Steffen Schotthöfer , Emanuele Zangrando , Jonas Kusch , Gianluca Ceruti , Francesco Tudisco

Deep neural networks, particularly those employing Rectified Linear Units (ReLU), are often perceived as complex, high-dimensional, non-linear systems. This complexity poses a significant challenge to understanding their internal learning…

Machine Learning · Computer Science 2025-11-11 Longqing Ye

Let $\Omega = [0,1]^d$ be the unit cube in $\mathbb{R}^d$. We study the problem of how efficiently, in terms of the number of parameters, deep neural networks with the ReLU activation function can approximate functions in the Sobolev spaces…

Machine Learning · Statistics 2024-04-09 Jonathan W. Siegel

Despite the recent success of stochastic gradient descent in deep learning, it is often difficult to train a deep neural network with an inappropriate choice of its initial parameters. Even if training is successful, it has been known that…

Machine Learning · Computer Science 2023-02-10 Cheolhyoung Lee , Kyunghyun Cho

The rapid development of parameter-efficient fine-tuning methods has noticeably improved the efficiency of adapting large language models. Among these, LoRA has gained widespread popularity due to its strong balance of effectiveness and…

Machine Learning · Computer Science 2026-01-15 Yongfu Xue

The development of effective initialization methods requires an understanding of random neural networks. In this work, a rigorous probabilistic analysis of deep unbiased Leaky ReLU networks is provided. We prove a Law of Large Numbers and a…

Machine Learning · Statistics 2026-02-12 Constantin Kogler , Tassilo Schwarz , Samuel Kittle

In neural network compression, most current methods reduce unnecessary parameters by measuring importance and redundancy. To augment already highly optimized existing solutions, we propose linearity-based compression as a novel way to…

Machine Learning · Computer Science 2025-06-27 Silas Dobler , Florian Lemmerich

The overfitting is one of the cursing subjects in the deep learning field. To solve this challenge, many approaches were proposed to regularize the learning models. They add some hyper-parameters to the model to extend the generalization;…

Machine Learning · Computer Science 2020-05-06 Mohammad Mahdi Bejani , Mehdi Ghatee

We develop exact representations of training two-layer neural networks with rectified linear units (ReLUs) in terms of a single convex program with number of variables polynomial in the number of training samples and the number of hidden…

Machine Learning · Computer Science 2020-08-18 Mert Pilanci , Tolga Ergen

This paper presents a nonlinear model reduction method for systems of equations using a structured neural network. The neural network takes the form of a "three-layer" network with the first layer constrained to lie on the Grassmann…

Machine Learning · Computer Science 2020-12-21 Kayla Bollinger , Hayden Schaeffer

Benign overfitting refers to how over-parameterized neural networks can fit training data perfectly and generalize well to unseen data. While this has been widely investigated theoretically, existing works are limited to two-layer networks…

Machine Learning · Computer Science 2024-10-28 Shuning Shang , Xuran Meng , Yuan Cao , Difan Zou

To adapt to real-world data streams, continual learning (CL) systems must rapidly learn new concepts while preserving and utilizing prior knowledge. When it comes to adding new information to continually-trained deep neural networks (DNNs),…

Machine Learning · Computer Science 2025-07-02 Md Yousuf Harun , Christopher Kanan

This paper studies the problem of training a two-layer ReLU network for binary classification using gradient flow with small initialization. We consider a training dataset with well-separated input vectors: Any pair of input data with the…

Machine Learning · Computer Science 2024-03-26 Hancheng Min , Enrique Mallada , René Vidal

State-of-the-art LLMs often rely on scale with high computational costs, which has sparked a research agenda to reduce parameter counts and costs without significantly impacting performance. Our study focuses on Transformer-based LLMs,…

Computation and Language · Computer Science 2024-07-25 Xiuying Wei , Skander Moalla , Razvan Pascanu , Caglar Gulcehre

Optimal parameter initialization remains a crucial problem for neural network training. A poor weight initialization may take longer to train and/or converge to sub-optimal solutions. Here, we propose a method of weight re-initialization by…

Machine Learning · Computer Science 2021-04-21 Norman Mu , Zhewei Yao , Amir Gholami , Kurt Keutzer , Michael Mahoney

Deep neural networks with millions of parameters are at the heart of many state of the art machine learning models today. However, recent works have shown that models with much smaller number of parameters can also perform just as well. In…

Machine Learning · Computer Science 2016-08-03 Suraj Srinivas , R. Venkatesh Babu

Foundation models have achieved remarkable success, yet their growing parameter counts pose significant computational and memory challenges. Low-rank factorization offers a promising route to reduce training and inference costs, but the…

Machine Learning · Computer Science 2026-02-16 Paul Janson , Edouard Oyallon , Eugene Belilovsky

We propose a unified framework for estimating low-rank matrices through nonconvex optimization based on gradient descent algorithm. Our framework is quite general and can be applied to both noisy and noiseless observations. In the general…

Machine Learning · Statistics 2016-10-18 Lingxiao Wang , Xiao Zhang , Quanquan Gu