English
Related papers

Related papers: A Johnson--Lindenstrauss Framework for Randomly In…

200 papers

In this paper, we consider parameter recovery for non-overlapping convolutional neural networks (CNNs) with multiple kernels. We show that when the inputs follow Gaussian distribution and the sample size is sufficiently large, the squared…

Machine Learning · Computer Science 2017-11-10 Kai Zhong , Zhao Song , Inderjit S. Dhillon

Despite remarkable performance on a variety of tasks, many properties of deep neural networks are not yet theoretically understood. One such mystery is the depth degeneracy phenomenon: the deeper you make your network, the closer your…

Machine Learning · Statistics 2025-11-18 Cameron Jakub , Mihai Nica

This work attempts to address two fundamental questions about the structure of the convolutional neural networks (CNN): 1) why a non-linear activation function is essential at the filter output of every convolutional layer? 2) what is the…

Computer Vision and Pattern Recognition · Computer Science 2016-11-04 C. -C. Jay Kuo

The efficiency of recurrent neural networks (RNNs) in dealing with sequential data has long been established. However, unlike deep, and convolution networks where we can attribute the recognition of a certain feature to every layer, it is…

Machine Learning · Computer Science 2020-01-15 Stefan Horoi , Guillaume Lajoie , Guy Wolf

Recent work in the literature has shown experimentally that one can use the lower layers of a trained convolutional neural network (CNN) to model natural textures. More interestingly, it has also been experimentally shown that only one…

Computer Vision and Pattern Recognition · Computer Science 2016-12-20 Mihir Mongia , Kundan Kumar , Akram Erraqabi , Yoshua Bengio

Embeddings play a pivotal role across various disciplines, offering compact representations of complex data structures. Randomized methods like Johnson-Lindenstrauss (JL) provide state-of-the-art and essentially unimprovable theoretical…

Machine Learning · Statistics 2024-12-11 Nikos Tsikouras , Constantine Caramanis , Christos Tzamos

The utility of a learned neural representation depends on how well its geometry supports performance in downstream tasks. This geometry depends on the structure of the inputs, the structure of the target outputs, and the architecture of the…

Machine Learning · Computer Science 2024-01-25 Matteo Alleman , Jack W Lindsey , Stefano Fusi

Neural networks are playing a crucial role in everyday life, with the most modern generative models able to achieve impressive results. Nonetheless, their functioning is still not very clear, and several strategies have been adopted to…

Differential Geometry · Mathematics 2024-04-10 Alessandro Benfenati , Alessio Marta

Ensuring proper generalization is a critical challenge in applying data-driven methods for solving inverse problems in imaging, as neural networks reconstructing an image must perform well across varied datasets and acquisition geometries.…

Image and Video Processing · Electrical Eng. & Systems 2025-11-18 Emilien Valat , Ozan Öktem

Recent findings suggest that the consecutive layers of ReLU neural networks can be understood geometrically as space folding transformations of the input space, revealing patterns of self-similarity. In this paper, we present the first…

Machine Learning · Computer Science 2025-02-17 Michal Lewandowski , Hamid Eghbalzadeh , Bernhard Heinzl , Raphael Pisoni , Bernhard A. Moser

Recurrent Neural Networks (RNNs) have found widespread applications in machine learning for time series prediction and dynamical systems reconstruction, and experienced a recent renaissance with improved training algorithms and…

Machine Learning · Computer Science 2026-04-14 Lukas Eisenmann , Alena Brändle , Zahra Monfared , Daniel Durstewitz

For a set $X$ of $N$ points in $\mathbb{R}^D$, the Johnson-Lindenstrauss lemma provides random linear maps that approximately preserve all pairwise distances in $X$ -- up to multiplicative error $(1\pm \epsilon)$ with high probability --…

Probability · Mathematics 2023-07-18 Michael P. Casey

Convex functions and their gradients play a critical role in mathematical imaging, from proximal optimization to Optimal Transport. The successes of deep learning has led many to use learning-based methods, where fixed functions or…

Machine Learning · Computer Science 2025-04-09 Anne Gagneux , Mathurin Massias , Emmanuel Soubies , Rémi Gribonval

Substantial work indicates that the dynamics of neural networks (NNs) is closely related to their initialization of parameters. Inspired by the phase diagram for two-layer ReLU NNs with infinite width (Luo et al., 2021), we make a step…

Machine Learning · Computer Science 2022-10-20 Hanxu Zhou , Qixuan Zhou , Zhenyuan Jin , Tao Luo , Yaoyu Zhang , Zhi-Qin John Xu

One of the mysteries in the success of neural networks is randomly initialized first order methods like gradient descent can achieve zero training loss even though the objective function is non-convex and non-smooth. This paper demystifies…

Machine Learning · Computer Science 2019-02-06 Simon S. Du , Xiyu Zhai , Barnabas Poczos , Aarti Singh

How neural network behaves during the training over different choices of hyperparameters is an important question in the study of neural networks. In this work, inspired by the phase diagram in statistical mechanics, we draw the phase…

Machine Learning · Computer Science 2020-10-14 Tao Luo , Zhi-Qin John Xu , Zheng Ma , Yaoyu Zhang

Neural networks with a large number of parameters often do not overfit, owing to implicit regularization that favors \lq good\rq{} networks. Other related and puzzling phenomena include properties of flat minima, saddle-to-saddle dynamics,…

Artificial Intelligence · Computer Science 2026-01-06 Joachim Bona-Pellissier , François Malgouyres , François Bachoc

We consider Convolutional Neural Networks (CNNs) with 2D structured features that are symmetric in the spatial dimensions. Such networks arise in modeling pairwise relationships for a sequential recommendation problem, as well as secondary…

Machine Learning · Statistics 2022-03-07 Kehelwala Dewage Gayan Maduranga , Vasily Zadorozhnyy , Qiang Ye

Neural models learn representations of high-dimensional data on low-dimensional manifolds. Multiple factors, including stochasticities in the training process, model architectures, and additional inductive biases, may induce different…

Machine Learning · Computer Science 2025-12-02 Hanlin Yu , Berfin Inal , Georgios Arvanitidis , Soren Hauberg , Francesco Locatello , Marco Fumero

In the past decade, significant strides in deep learning have led to numerous groundbreaking applications. Despite these advancements, the understanding of the high generalizability of deep learning, especially in such an over-parametrized…

Disordered Systems and Neural Networks · Physics 2024-09-17 Hao Liao , Wei Zhang , Zhanyi Huang , Zexiao Long , Mingyang Zhou , Xiaoqun Wu , Rui Mao , Chi Ho Yeung
‹ Prev 1 2 3 10 Next ›