Browsing by Subject "Matrix factorization"

Now showing 1 - 4 of 4

Open Access
Energy-Efficient LSTM networks for online learning
(IEEE, 2020) Ergen, T.; Mirza, Ali H.; Kozat, Süleyman Serdar
We investigate variable-length data regression in an online setting and introduce an energy-efficient regression structure build on long short-term memory (LSTM) networks. 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. To reduce the complexity of this structure, we then replace the regular multiplication operations with an energy-efficient operator, i.e., the ef-operator. To further reduce the complexity, we apply factorizations to the weight matrices in the LSTM network so that the total number of parameters to be trained is significantly reduced. We then introduce online training algorithms based on the stochastic gradient descent (SGD) and exponentiated gradient (EG) algorithms to learn the parameters of the introduced network. Thus, we obtain highly efficient and effective online learning algorithms based on the LSTM network. Thanks to our generic approach, we also provide and simulate an energy-efficient gated recurrent unit (GRU) network in our experiments. Through an extensive set of experiments, we illustrate significant performance gains and complexity reductions achieved by the introduced algorithms with respect to the conventional methods.
Open Access
A highly efficient recurrent neural network architecture for data regression
(IEEE, 2018) Ergen, Tolga; Ceyani, Emir
In this paper, we study online nonlinear data regression and propose a highly efficient long short term memory (LSTM) network based architecture. Here, we also introduce on-line training algorithms to learn the parameters of the introduced architecture. We first propose an LSTM based architecture for data regression. To diminish the complexity of this architecture, we use an energy efficient operator (ef-operator) instead of the multiplication operation. We then factorize the matrices of the LSTM network to reduce the total number of parameters to be learned. In order to train the parameters of this structure, we introduce online learning methods based on the exponentiated gradient (EG) and stochastic gradient descent (SGD) algorithms. Experimental results demonstrate considerable performance and efficiency improvements provided by the introduced architecture.
Open Access
Hybrid parallelization of Stochastic Gradient Descent
(2022-02) Büyükkaya, Kemal
The purpose of this study is to investigate the eﬃcient parallelization of the Stochastic Gradient Descent (SGD) algorithm for solving the matrix comple-tion problem on a high-performance computing (HPC) platform in distributed memory setting. We propose a hybrid parallel decentralized SGD framework with asynchronous communication between processors to show the scalability of parallel SGD up to hundreds of processors. We utilize Message Passing In-terface (MPI) for inter-node communication and POSIX threads for intra-node parallelism. We tested our method by using four diﬀerent real-world benchmark datasets. Experimental results show that the proposed algorithm yields up to 6× better throughput on relatively sparse datasets, and displays comparable perfor-mance to available state-of-the-art algorithms on relatively dense datasets while providing a ﬂexible partitioning scheme and a highly scalable hybrid parallel ar-chitecture.
Open Access
Matrix factorization with stochastic gradient descent for recommender systems
(2019-02) Aktulum, Ömer Faruk
Matrix factorization is an efficient technique used for disclosing latent features of real-world data. It finds its application in areas such as text mining, image analysis, social network and more recently and popularly in recommendation systems. Alternating Least Squares (ALS), Stochastic Gradient Descent (SGD) and Coordinate Descent (CD) are among the methods used commonly while factorizing large matrices. SGD-based factorization has proven to be the most successful among these methods after Netflix and KDDCup competitions where the winners’ algorithms relied on methods based on SGD. Parallelization of SGD then became a hot topic and studied extensively in the literature in recent years. We focus on parallel SGD algorithms developed for shared memory and distributed memory systems. Shared memory parallelizations include works such as HogWild, FPSGD and MLGF-MF, and distributed memory parallelizations include works such as DSGD, GASGD and NOMAD. We design a survey that contains exhaustive analysis of these studies, and then particularly focus on DSGD by implementing it through message-passing paradigm and testing its performance in terms of convergence and speedup. In contrast to the existing works, many real-wold datasets are used in the experiments that we produce using published raw data. We show that DSGD is a robust algorithm for large-scale datasets and achieves near-linear speedup with fast convergence rates.