English
Related papers

Related papers: Revisiting Recursive Least Squares for Training De…

200 papers

In scanning microscopy based imaging techniques, there is a need to develop novel data acquisition schemes that can reduce the time for data acquisition and minimize sample exposure to the probing radiation. Sparse sampling schemes are…

Signal Processing · Electrical Eng. & Systems 2018-03-09 Yan Zhang , G. M. Dilshan Godaliyadda , Nicola Ferrier , Emine B. Gulsoy , Charles A. Bouman , Charudatta Phatak

The slow convergence rate and pathological curvature issues of first-order gradient methods for training deep neural networks, initiated an ongoing effort for developing faster $\mathit{second}$-$\mathit{order}$ optimization algorithms…

Machine Learning · Computer Science 2020-12-10 Jan van den Brand , Binghui Peng , Zhao Song , Omri Weinstein

We propose RSO (random search optimization), a gradient free Markov Chain Monte Carlo search based approach for training deep neural networks. To this end, RSO adds a perturbation to a weight in a deep neural network and tests if it reduces…

Machine Learning · Computer Science 2020-05-13 Rohun Tripathi , Bharat Singh

Iteratively Re-weighted Least Squares (IRLS) is a method for solving minimization problems involving non-quadratic cost functions, perhaps non-convex and non-smooth, which however can be described as the infimum over a family of quadratic…

Numerical Analysis · Mathematics 2016-02-24 Massimo Fornasier , Steffen Peter , Holger Rauhut , Stephan Worm

Training deep neural networks (DNNs) efficiently is a challenge due to the associated highly nonconvex optimization. The backpropagation (backprop) algorithm has long been the most widely used algorithm for gradient computation of…

Machine Learning · Statistics 2018-03-28 Tim Tsz-Kit Lau , Jinshan Zeng , Baoyuan Wu , Yuan Yao

Partial least squares regression (PLSR) has been a popular technique to explore the linear relationship between two datasets. However, most of algorithm implementations of PLSR may only achieve a suboptimal solution through an optimization…

Computer Vision and Pattern Recognition · Computer Science 2016-09-22 Haoran Chen , Yanfeng Sun , Junbin Gao , Yongli Hu , Baocai Yin

Deep neural networks have exhibited promising performance in image super-resolution (SR) by learning a nonlinear mapping function from low-resolution (LR) images to high-resolution (HR) images. However, there are two underlying limitations…

Computer Vision and Pattern Recognition · Computer Science 2020-05-25 Yong Guo , Jian Chen , Jingdong Wang , Qi Chen , Jiezhang Cao , Zeshuai Deng , Yanwu Xu , Mingkui Tan

Over the past years, there has been significant interest in understanding the implicit bias of gradient descent optimization and its connection to the generalization properties of overparametrized neural networks. Several works observed…

Optimization and Control · Mathematics 2025-03-11 Hung-Hsu Chou , Johannes Maly , Claudio Mayrink Verdun , Bernardo Freitas Paulo da Costa , Heudson Mirandola

Recurrent Neural Networks (RNNs) offer fast inference on long sequences but are hard to optimize and slow to train. Deep state-space models (SSMs) have recently been shown to perform remarkably well on long sequence modeling tasks, and have…

Machine Learning · Computer Science 2023-03-14 Antonio Orvieto , Samuel L Smith , Albert Gu , Anushan Fernando , Caglar Gulcehre , Razvan Pascanu , Soham De

This work presents a new algorithm for training recurrent neural networks (although ideas are applicable to feedforward networks as well). The algorithm is derived from a theory in nonconvex optimization related to the diffusion equation.…

Machine Learning · Computer Science 2016-02-08 Hossein Mobahi

We consider learning deep neural networks (DNNs) that consist of low-precision weights and activations for efficient inference of fixed-point operations. In training low-precision networks, gradient descent in the backward pass is performed…

Computer Vision and Pattern Recognition · Computer Science 2020-05-26 Yoojin Choi , Mostafa El-Khamy , Jungwon Lee

Stochastic gradient descent (SGD) is the main approach for training deep networks: it moves towards the optimum of the cost function by iteratively updating the parameters of a model in the direction of the gradient of the loss evaluated on…

Machine Learning · Computer Science 2021-03-30 Loris Nanni , Gianluca Maguolo , Alessandra Lumini

We develop a recursive total least-squares (RTLS) algorithm for errors-in-variables system identification utilizing the inverse power method and the dichotomous coordinate-descent (DCD) iterations. The proposed algorithm, called DCD-RTLS,…

Systems and Control · Computer Science 2015-06-22 Reza Arablouei , Kutluyıl Doğançay , Stefan Werner

We address the problem of sparse recovery in an online setting, where random linear measurements of a sparse signal are revealed sequentially and the objective is to recover the underlying signal. We propose a reweighted least squares (RLS)…

Machine Learning · Computer Science 2017-06-30 Subhadip Mukherjee , Deepak R. , Huaijin Chen , Ashok Veeraraghavan , Chandra Sekhar Seelamantula

In many application of noise cancellation, the changes in signal characteristics could be quite fast. This requires the utilization of adaptive algorithms, which converge rapidly. Least Mean Squares (LMS) and Normalized Least Mean Squares…

Sound · Computer Science 2011-06-07 Sayed. A. Hadei , M. lotfizad

Latest least squares regression (LSR) methods mainly try to learn slack regression targets to replace strict zero-one labels. However, the difference of intra-class targets can also be highlighted when enlarging the distance between…

Computer Vision and Pattern Recognition · Computer Science 2019-10-09 Zhe Chen , Xiao-Jun Wu , Josef Kittler

Due to the non-convex nature of training Deep Neural Network (DNN) models, their effectiveness relies on the use of non-convex optimization heuristics. Traditional methods for training DNNs often require costly empirical methods to produce…

Machine Learning · Computer Science 2023-12-21 Tolga Ergen , Mert Pilanci

We propose a new deep recurrent neural network (RNN) architecture for sequential signal reconstruction. Our network is designed by unfolding the iterations of the proximal gradient method that solves the l1-l1 minimization problem. As such,…

Machine Learning · Computer Science 2019-02-19 Hung Duy Le , Huynh Van Luong , Nikos Deligiannis

We develop a Recursive $\mathcal{L}_1$-Regularized Least Squares (SPARLS) algorithm for the estimation of a sparse tap-weight vector in the adaptive filtering setting. The SPARLS algorithm exploits noisy observations of the tap-weight…

Information Theory · Computer Science 2009-01-08 Behtash Babadi , Nicholas Kalouptsidis , Vahid Tarokh

We propose a new iteratively reweighted least squares (IRLS) algorithm for the recovery of a matrix $X \in \mathbb{C}^{d_1\times d_2}$ of rank $r \ll\min(d_1,d_2)$ from incomplete linear observations, solving a sequence of low complexity…

Numerical Analysis · Mathematics 2018-02-28 Christian Kümmerle , Juliane Sigl
‹ Prev 1 4 5 6 7 8 10 Next ›