English
Related papers

Related papers: Mutual Information of Neural Network Initialisatio…

200 papers

We examine the relationship between the mutual information between the output model and the empirical sample and the generalization of the algorithm in the context of stochastic convex optimization. Despite increasing interest in…

Machine Learning · Computer Science 2024-01-17 Roi Livni

Each year, deep learning demonstrates new and improved empirical results with deeper and wider neural networks. Meanwhile, with existing theoretical frameworks, it is difficult to analyze networks deeper than two layers without resorting to…

Machine Learning · Computer Science 2023-03-28 Hong Jun Jeon , Yifan Zhu , Benjamin Van Roy

Neural networks with random hidden nodes have gained increasing interest from researchers and practical applications. This is due to their unique features such as very fast training and universal approximation property. In these networks…

Neural and Evolutionary Computing · Computer Science 2017-10-16 Grzegorz Dudek

Meta-learning leverages related source tasks to learn an initialization that can be quickly fine-tuned to a target task with limited labeled examples. However, many popular meta-learning algorithms, such as model-agnostic meta-learning…

Machine Learning · Statistics 2020-03-24 Diana Cai , Rishit Sheth , Lester Mackey , Nicolo Fusi

A common method in training neural networks is to initialize all the weights to be independent Gaussian vectors. We observe that by instead initializing the weights into independent pairs, where each pair consists of two identical Gaussian…

Machine Learning · Computer Science 2022-06-28 Alexander Munteanu , Simon Omlor , Zhao Song , David P. Woodruff

Weight initialization plays a crucial role in the optimization behavior and convergence efficiency of neural networks. Most existing initialization methods, such as Xavier and Kaiming initializations, rely on random sampling and do not…

Machine Learning · Computer Science 2026-02-09 Shaowen Wang , Tariq Alkhalifah

Weight initialization plays an important role in neural network training. Widely used initialization methods are proposed and evaluated for networks that are trained from scratch. However, the growing number of pretrained models now offers…

Machine Learning · Computer Science 2023-12-01 Zhiqiu Xu , Yanjie Chen , Kirill Vishniakov , Yida Yin , Zhiqiang Shen , Trevor Darrell , Lingjie Liu , Zhuang Liu

We carry out an information-theoretical analysis of a two-layer neural network trained from input-output pairs generated by a teacher network with matching architecture, in overparametrized regimes. Our results come in the form of bounds…

Machine Learning · Computer Science 2023-07-13 Francesco Camilli , Daria Tieplova , Jean Barbier

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

We present a novel approach for training deep neural networks in a Bayesian way. Classical, i.e. non-Bayesian, deep learning has two major drawbacks both originating from the fact that network parameters are considered to be deterministic.…

Machine Learning · Statistics 2019-03-11 Konstantin Posch , Jan Steinbrener , Jürgen Pilz

Small neural networks with a constrained number of trainable parameters, can be suitable resource-efficient candidates for many simple tasks, where now excessively large models are used. However, such models face several problems during the…

Machine Learning · Computer Science 2021-09-21 Alexander Kovalenko , Pavel Kordík , Magda Friedjungová

Evaluation of generative models is mostly based on the comparison between the estimated distribution and the ground truth distribution in a certain feature space. To embed samples into informative features, previous works often use…

Machine Learning · Computer Science 2022-12-15 Junghyuk Lee , Jun-Hyuk Kim , Jong-Seok Lee

Estimating the Generalization Error (GE) of Deep Neural Networks (DNNs) is an important task that often relies on availability of held-out data. The ability to better predict GE based on a single training set may yield overarching DNN…

Machine Learning · Computer Science 2022-07-20 Angus Galloway , Anna Golubeva , Mahmoud Salem , Mihai Nica , Yani Ioannou , Graham W. Taylor

The key distinguishing property of a Bayesian approach is marginalization instead of optimization, not the prior, or Bayes rule. Bayesian inference is especially compelling for deep neural networks. (1) Neural networks are typically…

Machine Learning · Computer Science 2020-01-30 Andrew Gordon Wilson

Given any deep fully connected neural network, initialized with random Gaussian parameters, we bound from above the quadratic Wasserstein distance between its output distribution and a suitable Gaussian process. Our explicit inequalities…

Machine Learning · Computer Science 2023-09-25 Andrea Basteri , Dario Trevisan

The activation function deployed in a deep neural network has great influence on the performance of the network at initialisation, which in turn has implications for training. In this paper we study how to avoid two problems at…

Machine Learning · Computer Science 2021-05-18 Michael Murray , Vinayak Abrol , Jared Tanner

Existing generalization bounds for deep neural networks require data to be independent and identically distributed (iid). This assumption may not hold in real-life applications such as evolutionary biology, infectious disease epidemiology,…

Machine Learning · Statistics 2023-10-10 Quan Huu Do , Binh T. Nguyen , Lam Si Tung Ho

Training feedforward neural networks with standard logistic activations is considered difficult because of the intrinsic properties of these sigmoidal functions. This work aims at showing that these networks can be trained to achieve…

Neural and Evolutionary Computing · Computer Science 2017-10-04 Emanuele Sansone , Francesco G. B. De Natale

Neural networks with sinusoidal activations have been proposed as an alternative to networks with traditional activation functions. Despite their promise, particularly for learning implicit models, their training behavior is not yet fully…

Machine Learning · Computer Science 2022-11-29 Filipe de Avila Belbute-Peres , J. Zico Kolter

The edge-of-chaos dynamics of wide randomly initialized low-rank feedforward networks are analyzed. Formulae for the optimal weight and bias variances are extended from the full-rank to low-rank setting and are shown to follow from…

Machine Learning · Statistics 2023-02-01 Thiziri Nait Saada , Jared Tanner
‹ Prev 1 3 4 5 6 7 10 Next ›