English
Related papers

Related papers: Neural Weight Norm = Kolmogorov Complexity

200 papers

Kolmogorov complexity of a finite binary word reflects both algorithmic structure and the empirical distribution of symbols appearing in the word. Words with symbol frequencies far from one half have smaller combinatorial richness and…

Computation · Statistics 2025-12-25 Brani Vidakovic

We introduce canonical weight normalization for convolutional neural networks. Inspired by the canonical tensor decomposition, we express the weight tensors in so-called canonical networks as scaled sums of outer vector products. In…

Machine Learning · Computer Science 2022-06-06 Lokesh Veeramacheneni , Moritz Wolter , Reinhard Klein , Jochen Garcke

We explore the low-rank structure of the weight matrices in neural networks at the stationary points (limiting solutions of optimization algorithms) with $L2$ regularization (also known as weight decay). We show several properties of such…

Machine Learning · Computer Science 2025-08-21 Ilja Kuzborskij , Yasin Abbasi Yadkori

Neural networks have attracted a lot of attention due to its success in applications such as natural language processing and computer vision. For large scale data, due to the tremendous number of parameters in neural networks, overfitting…

Machine Learning · Statistics 2022-07-05 Xiaoxi Shen , Jinghang Lin

Deep learning has been wildly successful in practice and most state-of-the-art machine learning methods are based on neural networks. Lacking, however, is a rigorous mathematical theory that adequately explains the amazing performance of…

Machine Learning · Statistics 2023-10-03 Rahul Parhi , Robert D. Nowak

Universal approximation theory offers a foundational framework to verify neural network expressiveness, enabling principled utilization in real-world applications. However, most existing theoretical constructions are established by…

Machine Learning · Computer Science 2026-01-27 ZeYu Li , ShiJun Zhang , TieYong Zeng , FengLei Fan

Weight decay (WD) is a traditional regularization technique in deep learning, but despite its ubiquity, its behavior is still an area of active research. Golatkar et al. have recently shown that WD only matters at the start of the training…

Machine Learning · Computer Science 2020-12-29 Johan Bjorck , Kilian Weinberger , Carla Gomes

Deep neural networks exhibit a simplicity bias, a well-documented tendency to favor simple functions over complex ones. In this work, we cast new light on this phenomenon through the lens of the Minimum Description Length principle,…

This paper studies the novel concept of weight correlation in deep neural networks and discusses its impact on the networks' generalisation ability. For fully-connected layers, the weight correlation is defined as the average cosine…

Machine Learning · Computer Science 2020-10-20 Gaojie Jin , Xinping Yi , Liang Zhang , Lijun Zhang , Sven Schewe , Xiaowei Huang

In 1974 Kolmogorov proposed a non-probabilistic approach to statistics and model selection. Let data be finite binary strings and models be finite sets of binary strings. Consider model classes consisting of models of given maximal…

Computational Complexity · Computer Science 2007-05-23 Nikolai Vereshchagin , Paul Vitanyi

This paper proposes a novel binarized weight network (BT) for a resource-efficient neural structure. The proposed model estimates a binary representation of weights by taking into account the approximation error with an additional term.…

Computer Vision and Pattern Recognition · Computer Science 2021-05-11 Savas Ozkan , Gozde Bozdagi Akar

Since the Lipschitz properties of convolutional neural networks (CNNs) are widely considered to be related to adversarial robustness, we theoretically characterize the $\ell_1$ norm and $\ell_\infty$ norm of 2D multi-channel convolutional…

Machine Learning · Computer Science 2021-08-17 Youwei Liang , Dong Huang

Predictive Coding Networks (PCNs) aim to learn a generative model of the world. Given observations, this generative model can then be inverted to infer the causes of those observations. However, when training PCNs, a noticeable pathology is…

Artificial Intelligence · Computer Science 2022-09-02 Paul F Kinghorn , Beren Millidge , Christopher L Buckley

We consolidate two widely believed conjectures about tautologies -- no optimal proof system exists, and most require superpolynomial size proofs in any system -- into a $p$-isomorphism-invariant condition satisfied by all paddable…

Computational Complexity · Computer Science 2022-07-21 Hunter Monroe

The advancement of deep learning has led to the development of neural decoders for low latency communications. However, neural decoders can be very complex which can lead to increased computation and latency. We consider iterative pruning…

Machine Learning · Computer Science 2022-11-17 Vikrant Malik , Rohan Ghosh , Mehul Motani

We study the problem of estimating an unknown function from noisy data using shallow ReLU neural networks. The estimators we study minimize the sum of squared data-fitting errors plus a regularization term proportional to the squared…

Machine Learning · Statistics 2023-01-24 Rahul Parhi , Robert D. Nowak

In this paper, we first identify activation shift, a simple but remarkable phenomenon in a neural network in which the preactivation value of a neuron has non-zero mean that depends on the angle between the weight vector of the neuron and…

Neural and Evolutionary Computing · Computer Science 2024-03-22 Takuro Kutsuna

We study the implicit bias towards low-rank weight matrices when training neural networks (NN) with Weight Decay (WD). We prove that when a ReLU NN is sufficiently trained with Stochastic Gradient Descent (SGD) and WD, its weight matrix is…

Machine Learning · Computer Science 2024-10-04 Ke Chen , Chugang Yi , Haizhao Yang

The Lipschitz constant of the map between the input and output space represented by a neural network is a natural metric for assessing the robustness of the model. We present a new method to constrain the Lipschitz constant of dense deep…

Machine Learning · Computer Science 2023-08-22 Ouail Kitouni , Niklas Nolte , Mike Williams

The minimal norm weight perturbations of DNNs required to achieve a specified change in output are derived and the factors determining its size are discussed. These single-layer exact formulae are contrasted with more generic multi-layer…

Machine Learning · Computer Science 2026-05-19 Bethan Evans , Jared Tanner
‹ Prev 1 4 5 6 7 8 10 Next ›