English
Related papers

Related papers: A Sober Look at Neural Network Initializations

200 papers

We draw connections between simple neural networks and under-determined linear systems to comprehensively explore several interesting theoretical questions in the study of neural networks. First, we emphatically show that it is unsurprising…

Numerical Analysis · Mathematics 2020-11-02 Austin R. Benson , Anil Damle , Alex Townsend

Before training a neural net, a classic rule of thumb is to randomly initialize the weights so the variance of activations is preserved across layers. This is traditionally interpreted using the total variance due to randomness in both…

Machine Learning · Computer Science 2019-08-07 Kyle Luther , H. Sebastian Seung

In this short note, we propose a new method for quantizing the weights of a fully trained neural network. A simple deterministic pre-processing step allows us to quantize network layers via memoryless scalar quantization while preserving…

Machine Learning · Computer Science 2023-04-06 Johannes Maly , Rayan Saab

In past few years, various initialization schemes have been proposed. These schemes are glorot initialization, He initialization, initialization using orthogonal matrix, random walk method for initialization. Some of these methods stress on…

Machine Learning · Computer Science 2025-09-08 Vijay Pandey

Recent works have cast some light on the mystery of why deep nets fit any data and generalize despite being very overparametrized. This paper analyzes training and generalization for a simple 2-layer ReLU net with random initialization, and…

Machine Learning · Computer Science 2019-05-28 Sanjeev Arora , Simon S. Du , Wei Hu , Zhiyuan Li , Ruosong Wang

Regularization is typically understood as improving generalization by altering the landscape of local extrema to which the model eventually converges. Deep neural networks (DNNs), however, challenge this view: We show that removing…

Machine Learning · Computer Science 2019-06-03 Aditya Golatkar , Alessandro Achille , Stefano Soatto

We study the role of depth in training randomly initialized overparameterized neural networks. We give a general result showing that depth improves trainability of neural networks by improving the conditioning of certain kernel matrices of…

Machine Learning · Computer Science 2021-02-18 Naman Agarwal , Pranjal Awasthi , Satyen Kale

Despite recent algorithmic advances, we still lack principled ways to leverage the well-documented rescaling symmetries in ReLU neural network parameters. While two properly rescaled weights implement the same function, the training…

Machine Learning · Statistics 2026-02-24 Arthur Lebeurrier , Titouan Vayer , Rémi Gribonval

Neural networks trained via gradient descent with random initialization and without any regularization enjoy good generalization performance in practice despite being highly overparametrized. A promising direction to explain this phenomenon…

Machine Learning · Computer Science 2022-05-17 Hancheng Min , Salma Tarmoun , Rene Vidal , Enrique Mallada

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

Generalization of deep neural networks remains one of the main open problems in machine learning. Previous theoretical works focused on deriving tight bounds of model complexity, while empirical works revealed that neural networks exhibit…

Machine Learning · Computer Science 2022-01-31 James Wang , Cheng-Lin Yang

Binary Neural Network (BNN) shows its predominance in reducing the complexity of deep neural networks. However, it suffers severe performance degradation. One of the major impediments is the large quantization error between the…

Computer Vision and Pattern Recognition · Computer Science 2020-10-23 Mingbao Lin , Rongrong Ji , Zihan Xu , Baochang Zhang , Yan Wang , Yongjian Wu , Feiyue Huang , Chia-Wen Lin

The selection of initial parameter values for gradient-based optimization of deep neural networks is one of the most impactful hyperparameter choices in deep learning systems, affecting both convergence times and model performance. Yet…

Machine Learning · Computer Science 2020-01-17 Wei Hu , Lechao Xiao , Jeffrey Pennington

Understanding and controlling biasing effects in neural networks is crucial for ensuring accurate and fair model performance. In the context of classification problems, we provide a theoretical analysis demonstrating that the structure of a…

Machine Learning · Computer Science 2024-11-11 Emanuele Francazi , Aurelien Lucchi , Marco Baity-Jesi

In this work, we propose a data-driven scheme to initialize the parameters of a deep neural network. This is in contrast to traditional approaches which randomly initialize parameters by sampling from transformed standard distributions.…

Neural and Evolutionary Computing · Computer Science 2021-05-24 Debasmit Das , Yash Bhalgat , Fatih Porikli

Inducing and leveraging sparse activations during training and inference is a promising avenue for improving the computational efficiency of deep networks, which is increasingly important as network sizes continue to grow and their…

Machine Learning · Computer Science 2024-02-27 Ilan Price , Nicholas Daultry Ball , Samuel C. H. Lam , Adam C. Jones , Jared Tanner

Deep neural networks (DNNs) are often trained on the premise that the complete training data set is provided ahead of time. However, in real-world scenarios, data often arrive in chunks over time. This leads to important considerations…

Machine Learning · Computer Science 2023-03-21 Vijaya Raghavan T. Ramkumar , Elahe Arani , Bahram Zonooz

Traditional initialisation methods, e.g. He and Xavier, have been effective in avoiding the problem of vanishing or exploding gradients in neural networks. However, they only use simple pointwise distributions, which model one-dimensional…

Computer Vision and Pattern Recognition · Computer Science 2023-10-26 Christian Harder , Moritz Fuchs , Yuri Tolkach , Anirban Mukhopadhyay

In recurrent neural networks, learning long-term dependency is the main difficulty due to the vanishing and exploding gradient problem. Many researchers are dedicated to solving this issue and they proposed many algorithms. Although these…

Machine Learning · Computer Science 2023-07-31 Ran Dou , Jose Principe

We propose a simple, data-driven approach to help guide hyperparameter selection for neural network initialization. We leverage the relationship between neural network and Gaussian process models having corresponding activation and…

Machine Learning · Statistics 2020-12-21 Anthony S. Tai , Chunfeng Huang