English
Related papers

Related papers: On the Effectiveness of the z-Transform Method in …

200 papers

The Esscher Transform is a tool of broad utility in various domains of applied probability. It provides the solution to a constrained minimum relative entropy optimization problem. In this work, we study the generalization of the Esscher…

Quantum Physics · Physics 2025-04-11 Yixian Qiu , Kelvin Koor , Patrick Rebentrost

We propose an effective and lightweight learning algorithm, Symplectic Taylor Neural Networks (Taylor-nets), to conduct continuous, long-term predictions of a complex Hamiltonian dynamic system based on sparse, short-term observations. At…

Machine Learning · Computer Science 2022-02-22 Yunjin Tong , Shiying Xiong , Xingzhe He , Guanghan Pan , Bo Zhu

Parameter-Efficient Transfer Learning (PETL) aims at efficiently adapting large models pre-trained on massive data to downstream tasks with limited task-specific data. In view of the practicality of PETL, previous works focus on tuning a…

Computer Vision and Pattern Recognition · Computer Science 2023-03-15 Hengyuan Zhao , Hao Luo , Yuyang Zhao , Pichao Wang , Fan Wang , Mike Zheng Shou

Transformers excel at in-context learning (ICL) -- learning from demonstrations without parameter updates -- but how they do so remains a mystery. Recent work suggests that Transformers may internally run Gradient Descent (GD), a…

Machine Learning · Computer Science 2024-11-19 Deqing Fu , Tian-Qi Chen , Robin Jia , Vatsal Sharan

In this article, we study the properties of the nonlinear Fourier spectrum in order to gain better control of the temporal support of the signals synthesized using the inverse nonlinear Fourier transform (NFT). In particular, we provide…

Computational Physics · Physics 2018-09-17 Vishal Vaibhav

Transfer learning using deep neural networks as feature extractors has become increasingly popular over the past few years. It allows to obtain state-of-the-art accuracy on datasets too small to train a deep neural network on its own, and…

Machine Learning · Computer Science 2017-10-25 Vincent Gripon , Ghouthi B. Hacene , Matthias Löwe , Franck Vermet

We consider optimization algorithms that successively minimize simple Taylor-like models of the objective function. Methods of Gauss-Newton type for minimizing the composition of a convex function and a smooth map are common examples. Our…

Optimization and Control · Mathematics 2016-10-12 Dmitriy Drusvyatskiy , Alexander D. Ioffe , Adrian S. Lewis

For a given distribution, learning algorithm, and performance metric, the rate of convergence (or data-scaling law) is the asymptotic behavior of the algorithm's test performance as a function of number of train samples. Many learning…

Machine Learning · Computer Science 2021-11-10 Preetum Nakkiran

This paper studies an intriguing phenomenon related to the good generalization performance of estimators obtained by using large learning rates within gradient descent algorithms. First observed in the deep learning literature, we show that…

Machine Learning · Statistics 2022-06-06 Gaspard Beugnot , Julien Mairal , Alessandro Rudi

Iterative Fast Fourier Transform methods are useful for calculating the fields in composite materials and their macroscopic response. By iterating back and forth until convergence, the differential constraints are satisfied in Fourier…

Numerical Analysis · Mathematics 2018-01-25 Hervé Moulinec , Pierre Suquet , Graeme W. Milton

We consider the asymptotic behavior of a family of gradient methods, which include the steepest descent and minimal gradient methods as special instances. It is proved that each method in the family will asymptotically zigzag between two…

Optimization and Control · Mathematics 2019-08-21 Yakui Huang , Yu-Hong Dai , Xin-Wei Liu , Hongchao Zhang

The use of hyperasymptotics and the Weniger transformation has been proposed, in a joint fashion, for decoding the divergent asymptotic series generated by the steepest descent on a wide class of saddle-point integrals {evaluated across…

Computational Physics · Physics 2009-07-17 Riccardo Borghi

Q-learning has long been one of the most popular reinforcement learning algorithms, and theoretical analysis of Q-learning has been an active research topic for decades. Although researches on asymptotic convergence analysis of Q-learning…

Artificial Intelligence · Computer Science 2022-07-26 Han-Dong Lim , Donghwan Lee

Recursive stochastic algorithms have gained significant attention in the recent past due to data driven applications. Examples include stochastic gradient descent for solving large-scale optimization problems and empirical dynamic…

Machine Learning · Computer Science 2020-07-27 Abhishek Gupta , Hao Chen , Jianzong Pi , Gaurav Tendolkar

Recurrent neural networks are effective models to process sequences. However, they are unable to learn long-term dependencies because of their inherent sequential nature. As a solution, Vaswani et al. introduced the Transformer, a model…

Machine Learning · Computer Science 2023-03-28 Quentin Fournier , Gaétan Marceau Caron , Daniel Aloise

The use of Variational Autoencoders in different Machine Learning tasks has drastically increased in the last years. They have been developed as denoising, clustering and generative tools, highlighting a large potential in a wide range of…

Machine Learning · Computer Science 2019-07-12 Helena Andrés-Terré , Pietro Lió

Recent developments in machine learning and signal processing have resulted in many new techniques that are able to effectively capture the intrinsic yet complex properties of hyperspectral imagery. Tasks ranging from anomaly detection to…

Computer Vision and Pattern Recognition · Computer Science 2020-11-24 Ilya Kavalerov , Weilin Li , Wojciech Czaja , Rama Chellappa

The perturbation technique within the framework of the asymptotic iteration method is used to obtain large-order shifted 1/N expansions, where N is the number of spatial dimensions. This method is contrary to the usual…

Quantum Physics · Physics 2007-08-17 T. Barakat

A linear sequence transformation is defined that accelerates the convergence of the negative binomial series when the terms of the binomial have the same sign. The transformed series can be used to extend the region of applicability of the…

Numerical Analysis · Mathematics 2017-02-07 Liborio I. Costa

A candidate explanation of the good empirical performance of deep neural networks is the implicit regularization effect of first order optimization methods. Inspired by this, we prove a convergence theorem for nonconvex composite…

Machine Learning · Computer Science 2023-02-14 Dávid Terjék , Diego González-Sánchez
‹ Prev 1 4 5 6 7 8 10 Next ›