Suchergebnisse - exponentiated-gradient algorithm

Estimating the spectrum in computed tomography via Kullback–Leibler divergence constrained optimization von Ha, Wooseok, Sidky, Emil Y., Barber, Rina Foygel, Schmidt, Taly Gilat, Pan, Xiaochuan

“… The formulated constrained optimization problem is convex and can be solved efficiently by use of the exponentiated‐gradient (EG) algorithm …”
Volltext

EGRank: An exponentiated gradient algorithm for sparse learning-to-rank von Du, Lei, Pan, Yan, Ding, Jintang, Lai, Hanjiang, Huang, Changqin

“… An exponential gradient algorithm is proposed to learn sparse models for learning-to-rank, which can be formulated as a convex optimization problem with the ℓ1 constraint …”
Volltext

Generalized Exponentiated Gradient Algorithms and Their Application to On-Line Portfolio Selection von Cichocki, Andrzej, Cruces, Sergio, Sarmiento, Auxiliadora, Tanaka, Toshihisa

“… Stochastic gradient descent (SGD) and exponentiated gradient (EG) update methods are widely used in signal processing and machine learning …”
Volltext

Convergence of exponentiated gradient algorithms von Hill, S.I., Williamson, R.C.

“… This paper studies three related algorithms: the (traditional) gradient descent (GD) algorithm, the exponentiated gradient algorithm with positive and negative weights …”
Volltext

A Study of the Exponentiated Gradient +/- Algorithm for Stochastic Optimization of Neural Networks von Parks, David F

“… Exponentiated Gradient +/- (abbr. EG+-) is a gradient update algorithm drawn from work by Manfred Warmuth …”
Volltext

Generalized Exponentiated Gradient Algorithms and Their Application to On-Line Portfolio Selection von Cichocki, Andrzej, Cruces, Sergio, Sarmiento, Auxiliadora, Tanaka, Toshihisa

“… This paper introduces a novel family of generalized exponentiated gradient (EG) updates derived from an Alpha-Beta divergence regularization function …”
Volltext

Kernelization of matrix updates, when and how? von Warmuth, Manfred K., Kotłowski, Wojciech, Zhou, Shuisheng

“… We define what it means for a learning algorithm to be kernelizable in the case when the instances are vectors, asymmetric matrices and symmetric matrices, respectively …”
Volltext

On the Efficient Implementation of the Matrix Exponentiated Gradient Algorithm for Low-Rank Matrix Optimization von Garber, Dan, Kaplan, Atara

“… In particular, the desirable choice is the Matrix Exponentiated Gradient (MEG) method which is based on the Bregman distance induced by the (negative …”
Volltext

Online variance minimization von Warmuth, Manfred K., Kuzmin, Dima

“… . For the first parameter space we apply the Exponentiated Gradient algorithm …”
Volltext

Energy-Efficient LSTM Networks for Online Learning von Ergen, Tolga, Mirza, Ali H., Kozat, Suleyman Serdar

“… For this structure, we also introduce highly effective online training algorithms. We first provide a generic LSTM-based regression structure for variable-length input sequences …”
Volltext

Exponentiated Gradient Exploration for Active Learning von Bouneffouf, Djallel

“… more informative. In this setting, we propose a sequential algorithm named exponentiated gradient (EG)-active that can improve any active learning algorithm by an optimal random exploration …”
Volltext

Efficient online quantum state estimation using a matrix-exponentiated gradient method von Youssry, Akram, Ferrie, Christopher, Tomamichel, Marco

“… In this paper, we explore an efficient online algorithm for quantum state estimation based on a matrix-exponentiated gradient method previously used in the context of machine learning …”
Volltext

An exponentiated gradient adaptive algorithm for blind identification of sparse SIMO systems von Benesty, J., Yiteng Huang, Jingdong Chen

“… Sparse impulse responses are encountered in many acoustic and wireless channels. Recently, a class of exponentiated gradient (EG …”
Volltext

The LMS, PNLMS, and exponentiated gradient algorithms von Benesty, Jacob, Yiteng Huang

“… ). Recently, a class of exponentiated gradient (EG) algorithms has been proposed. One of the algorithms belonging to this class, the so-called EG …”
Volltext

A Comparison of New and Old Algorithms for a Mixture Estimation Problem von Helmbold, David P., Schapire, Robert E., Singer, Yoram, Warmuth, Manfred K.

“… The square distance leads to the gradient projection update, and the relative entropy to a new update which we call the exponentiated gradient update (EG^sub …”
Volltext

An analysis of the exponentiated gradient descent algorithm von Hill, S.I., Williamson, R.C.

“… : the gradient descent (GD) algorithm, the exponentiated gradient algorithm with positive and negative weights …”
Volltext

Sparse Recovery From Multiple Measurement Vectors Using Exponentiated Gradient Updates von Khanna, Saurabh, Murthy, Chandra Ramabhadra

“… For proximal regularization based on Von Neumann Bregman matrix divergence, an exponentiated gradient (EG …”
Volltext

Exponentiated Gradient versus Gradient Descent for Linear Predictors von Kivinen, Jyrki, Warmuth, Manfred K.

“… We consider two algorithms for on-line prediction based on a linear model. The algorithms are the well-known gradient descent (GD …”
Volltext

Exponentiated Gradient LINUCB for Contextual Multi-Armed Bandits von Bouneffouf, Djallel

“… We present Exponentiated Gradient LINUCB, an algorithm for con-textual multi-armed bandits …”
Volltext

Efficient online quantum state estimation using a matrix-exponentiated gradient method von Youssry, Akram, Ferrie, Christopher, Tomamichel, Marco

“… In this paper, we explore an efficient online algorithm for quantum state estimation based on a matrix-exponentiated gradient method previously used in the context of machine learning …”
Volltext