English
Related papers

Related papers: Free Probability for predicting the performance of…

200 papers

A well-conditioned Jacobian spectrum has a vital role in preventing exploding or vanishing gradients and speeding up learning of deep neural networks. Free probability theory helps us to understand and handle the Jacobian spectrum. We…

Probability · Mathematics 2020-02-13 Tomohiro Hayase

Recent work has shown that tight concentration of the entire spectrum of singular values of a deep network's input-output Jacobian around one at initialization can speed up learning by orders of magnitude. Therefore, to guide important…

Machine Learning · Statistics 2018-02-28 Jeffrey Pennington , Samuel S. Schoenholz , Surya Ganguli

Deep neural networks are known to suffer from exploding or vanishing gradients as depth increases, a phenomenon closely tied to the spectral behavior of the input-output Jacobian. Prior work has identified critical initialization schemes…

Machine Learning · Computer Science 2025-11-25 Benjamin Dadoun , Soufiane Hayou , Hanan Salam , Mohamed El Amine Seddik , Pierre Youssef

Free Probability Theory (FPT) provides rich knowledge for handling mathematical difficulties caused by random matrices that appear in research related to deep neural networks (DNNs), such as the dynamical isometry, Fisher information…

Machine Learning · Statistics 2023-10-25 Benoit Collins , Tomohiro Hayase

Learning expressive probabilistic models correctly describing the data is a ubiquitous problem in machine learning. A popular approach for solving it is mapping the observations into a representation space with a simple joint distribution,…

Machine Learning · Statistics 2020-10-28 Luigi Gresele , Giancarlo Fissore , Adrián Javaloy , Bernhard Schölkopf , Aapo Hyvärinen

Calculating perturbation response properties of materials from first principles provides a vital link between theory and experiment, but is bottlenecked by the high computational cost. Here a general framework is proposed to perform density…

Computational Physics · Physics 2024-03-01 He Li , Zechen Tang , Jingheng Fu , Wen-Han Dong , Nianlong Zou , Xiaoxun Gong , Wenhui Duan , Yong Xu

We revisit the initialization of deep residual networks (ResNets) by introducing a novel analytical tool in free probability to the community of deep learning. This tool deals with non-Hermitian random matrices, rather than their…

Machine Learning · Computer Science 2019-02-26 Zenan Ling , Xing He , Robert C. Qiu

A promising class of generative models maps points from a simple distribution to a complex distribution through an invertible neural network. Likelihood-based training of these models requires restricting their architectures to allow cheap…

Machine Learning · Computer Science 2018-10-23 Will Grathwohl , Ricky T. Q. Chen , Jesse Bettencourt , Ilya Sutskever , David Duvenaud

Recent efforts in applying implicit networks to solve inverse problems in imaging have achieved competitive or even superior results when compared to feedforward networks. These implicit networks only require constant memory during…

Machine Learning · Computer Science 2024-02-06 Linghai Liu , Shuaicheng Tong , Lisa Zhao

In this paper, training a neural network is identified, exactly, as a search through Hamilton--Jacobi initial-value problems: each gradient step selects the initial data of a viscous Hamilton--Jacobi equation whose Hopf--Cole propagator…

Machine Learning · Computer Science 2026-05-29 Jose Marie Antonio Miñoza , Erika Fille T. Legara , Christopher P. Monterola

Modern neural network architectures often generalize well despite containing many more parameters than the size of the training dataset. This paper explores the generalization capabilities of neural networks trained via gradient descent. We…

Machine Learning · Computer Science 2019-07-05 Samet Oymak , Zalan Fabian , Mingchen Li , Mahdi Soltanolkotabi

We examine the geometry of neural network training using the Jacobian of trained network parameters with respect to their initial values. Our analysis reveals low-dimensional structure in the training process which is dependent on the input…

Machine Learning · Computer Science 2024-12-12 Nora Belrose , Adam Scherlis

Model robustness is vital for the reliable deployment of machine learning models in real-world applications. Recent studies have shown that data augmentation can result in model over-relying on features in the low-frequency domain,…

Machine Learning · Computer Science 2022-05-11 Alvin Chan , Yew-Soon Ong , Clement Tan

Deep neural networks are notorious for defying theoretical treatment. However, when the number of parameters in each layer tends to infinity, the network function is a Gaussian process (GP) and quantitatively predictive description is…

Machine Learning · Computer Science 2023-10-09 Darshil Doshi , Tianyu He , Andrey Gromov

We present a mathematical analysis of the effects of Hebbian learning in random recurrent neural networks, with a generic Hebbian learning rule including passive forgetting and different time scales for neuronal activity and learning…

Chaotic Dynamics · Physics 2008-04-07 Benoit Siri , Hugues Berry , Bruno Cessac , Bruno Delord , Mathias Quoy

The free Jacobi process is the radial part of the compression of the free unitary Brownian motion by two free orthogonal projections in a non commutative probability space. In this paper, we derive spectral properties of the free Jacobi…

Probability · Mathematics 2025-03-28 Nizar Demni , Tarek Hamdi

The recent theoretical analysis of deep neural networks in their infinite-width limits has deepened our understanding of initialisation, feature learning, and training of those networks, and brought new practical techniques for finding…

Machine Learning · Computer Science 2024-08-23 Taeyoung Kim , Hongseok Yang

Good initialization is essential for training Deep Neural Networks (DNNs). Oftentimes such initialization is found through a trial and error approach, which has to be applied anew every time an architecture is substantially modified, or…

Machine Learning · Statistics 2022-06-29 Tianyu He , Darshil Doshi , Andrey Gromov

Power grid operators typically solve large-scale, nonconvex optimal power flow (OPF) problems throughout the day to determine optimal setpoints for generators while adhering to physical constraints. Despite being at the heart of many OPF…

Optimization and Control · Mathematics 2020-11-03 Kyri Baker

Multimodal fusion emerges as an appealing technique to improve model performances on many tasks. Nevertheless, the robustness of such fusion methods is rarely involved in the present literature. In this paper, we propose a training-free…

Computer Vision and Pattern Recognition · Computer Science 2022-04-07 Zhengqi Gao , Sucheng Ren , Zihui Xue , Siting Li , Hang Zhao
‹ Prev 1 2 3 10 Next ›