arXiv subjects

Xidong Wu

Publications and source records attributed to Xidong Wu.

23 records · Page 2Linked to original sources

arXiv2023

Performance and Energy Consumption of Parallel Machine Learning Algorithms

Machine learning models have achieved remarkable success in various real-world applications such as data science, computer vision, and natural language processing. However, model training in machine learning requires large-scale data sets and multiple iterations before it can work properly. Parallelization of training algorithms is a common strategy to speed up the process of training. However, many studies on model training and inference focus only on aspects of performance. Power consumption is also an important metric for any type of computation, especially high-performance applications. Machine learning algorithms that can be used on low-power platforms such as sensors and mobile devices have been researched, but less power optimization is done for algorithms designed for high-performance computing. In this paper, we present a C++ implementation of logistic regression and the genetic algorithm, and a Python implementation of neural networks with stochastic gradient descent (SGD) algorithm on classification tasks. We will show the impact that the complexity of the model and the size of the training data have on the parallel efficiency of the algorithm in terms of both power and performance. We also tested these implementations using shard-memory parallelism, distributed memory parallelism, and GPU acceleration to speed up machine learning model training.

cs.DC↗

arXiv2023

Faster Adaptive Federated Learning

Federated learning has attracted increasing attention with the emergence of distributed data. While extensive federated learning algorithms have been proposed for the non-convex distributed problem, federated learning in practice still faces numerous challenges, such as the large training iterations to converge since the sizes of models and datasets keep increasing, and the lack of adaptivity by SGD-based model updates. Meanwhile, the study of adaptive methods in federated learning is scarce and existing works either lack a complete theoretical convergence guarantee or have slow sample complexity. In this paper, we propose an efficient adaptive algorithm (i.e., FAFED) based on the momentum-based variance-reduced technique in cross-silo FL. We first explore how to design the adaptive algorithm in the FL setting. By providing a counter-example, we prove that a simple combination of FL and adaptive methods could lead to divergence. More importantly, we provide a convergence analysis for our method and prove that our algorithm is the first adaptive FL algorithm to reach the best-known samples $O(ε^{-3})$ and $O(ε^{-2})$ communication rounds to find an $ε$-stationary point without large batches. The experimental results on the language modeling task and image classification task with heterogeneous data demonstrate the efficiency of our algorithms.

cs.LG↗

arXiv2023

AdaGDA: Faster Adaptive Gradient Descent Ascent Methods for Minimax Optimization

In the paper, we propose a class of faster adaptive Gradient Descent Ascent (GDA) methods for solving the nonconvex-strongly-concave minimax problems by using the unified adaptive matrices, which include almost all existing coordinate-wise and global adaptive learning rates. In particular, we provide an effective convergence analysis framework for our adaptive GDA methods. Specifically, we propose a fast Adaptive Gradient Descent Ascent (AdaGDA) method based on the basic momentum technique, which reaches a lower gradient complexity of $\tilde{O}(κ^4ε^{-4})$ for finding an $ε$-stationary point without large batches, which improves the existing results of the adaptive GDA methods by a factor of $O(\sqrtκ)$. Moreover, we propose an accelerated version of AdaGDA (VR-AdaGDA) method based on the momentum-based variance reduced technique, which achieves a lower gradient complexity of $\tilde{O}(κ^{4.5}ε^{-3})$ for finding an $ε$-stationary point without large batches, which improves the existing results of the adaptive GDA methods by a factor of $O(ε^{-1})$. Moreover, we prove that our VR-AdaGDA method can reach the best known gradient complexity of $\tilde{O}(κ^{3}ε^{-3})$ with the mini-batch size $O(κ^3)$. The experiments on policy evaluation and fair classifier learning tasks are conducted to verify the efficiency of our new algorithms.

math.OC↗

arXiv2023

Decentralized Riemannian Algorithm for Nonconvex Minimax Problems

The minimax optimization over Riemannian manifolds (possibly nonconvex constraints) has been actively applied to solve many problems, such as robust dimensionality reduction and deep neural networks with orthogonal weights (Stiefel manifold). Although many optimization algorithms for minimax problems have been developed in the Euclidean setting, it is difficult to convert them into Riemannian cases, and algorithms for nonconvex minimax problems with nonconvex constraints are even rare. On the other hand, to address the big data challenges, decentralized (serverless) training techniques have recently been emerging since they can reduce communications overhead and avoid the bottleneck problem on the server node. Nonetheless, the algorithm for decentralized Riemannian minimax problems has not been studied. In this paper, we study the distributed nonconvex-strongly-concave minimax optimization problem over the Stiefel manifold and propose both deterministic and stochastic minimax methods. The Steifel manifold is a non-convex set. The global function is represented as the finite sum of local functions. For the deterministic setting, we propose DRGDA and prove that our deterministic method achieves a gradient complexity of $O( ε^{-2})$ under mild conditions. For the stochastic setting, we propose DRSGDA and prove that our stochastic method achieves a gradient complexity of $O(ε^{-4})$. The DRGDA and DRSGDA are the first algorithms for distributed minimax optimization with nonconvex constraints with exact convergence. Extensive experimental results on the Deep Neural Networks (DNNs) training over the Stiefel manifold demonstrate the efficiency of our algorithms.

cs.LG↗

arXiv2022

Distributed Dynamic Safe Screening Algorithms for Sparse Regularization

Distributed optimization has been widely used as one of the most efficient approaches for model training with massive samples. However, large-scale learning problems with both massive samples and high-dimensional features widely exist in the era of big data. Safe screening is a popular technique to speed up high-dimensional models by discarding the inactive features with zero coefficients. Nevertheless, existing safe screening methods are limited to the sequential setting. In this paper, we propose a new distributed dynamic safe screening (DDSS) method for sparsity regularized models and apply it on shared-memory and distributed-memory architecture respectively, which can achieve significant speedup without any loss of accuracy by simultaneously enjoying the sparsity of the model and dataset. To the best of our knowledge, this is the first work of distributed safe dynamic screening method. Theoretically, we prove that the proposed method achieves the linear convergence rate with lower overall complexity and can eliminate almost all the inactive features in a finite number of iterations almost surely. Finally, extensive experimental results on benchmark datasets confirm the superiority of our proposed method.

cs.LG↗