Author name cluster

Zhouyuan Huo

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

19 papers

2 author rows

NeurIPS Conference 2023 Conference Paper

Accelerated On-Device Forward Neural Network Training with Module-Wise Descending Asynchronism

Xiaohan Zhao
Hualin Zhang
Zhouyuan Huo
Bin Gu

On-device learning faces memory constraints when optimizing or fine-tuning on edge devices with limited resources. Current techniques for training deep models on edge devices rely heavily on backpropagation. However, its high memory usage calls for a reassessment of its dominance. In this paper, we propose forward gradient descent (FGD) as a potential solution to overcome the memory capacity limitation in on-device learning. However, FGD's dependencies across layers hinder parallel computation and can lead to inefficient resource utilization. To mitigate this limitation, we propose AsyncFGD, an asynchronous framework that decouples dependencies, utilizes module-wise stale parameters, and maximizes parallel computation. We demonstrate its convergence to critical points through rigorous theoretical analysis. Empirical evaluations conducted on NVIDIA's AGX Orin, a popular embedded device, show that AsyncFGD reduces memory consumption and enhances hardware efficiency, offering a novel approach to on-device learning.

AAAI Conference 2021 Conference Paper

Large Batch Optimization for Deep Learning Using New Complete Layer-Wise Adaptive Rate Scaling

Zhouyuan Huo
Bin Gu
Heng Huang

Training deep neural networks using a large batch size has shown promising results and benefits many real-world applications. Warmup is one of nontrivial techniques to stabilize the convergence of large batch training. However, warmup is an empirical method and it is still unknown whether there is a better algorithm with theoretical underpinnings. In this paper, we propose a novel Complete Layer-wise Adaptive Rate Scaling (CLARS) algorithm for large-batch training. We prove the convergence of our algorithm by introducing a new fine-grained analysis of gradient-based methods. Furthermore, the new analysis also helps to understand two other empirical tricks, layer-wise adaptive rate scaling and linear learning rate scaling. We conduct extensive experiments and demonstrate that the proposed algorithm outperforms gradual warmup technique by a large margin and defeats the convergence of the state-of-the-art large-batch optimizer in training advanced deep neural networks (ResNet, DenseNet, MobileNet) on ImageNet dataset.

NeurIPS Conference 2021 Conference Paper

On Large-Cohort Training for Federated Learning

Zachary Charles
Zachary Garrett
Zhouyuan Huo
Sergei Shmulyian
Virginia Smith

Federated learning methods typically learn a model by iteratively sampling updates from a population of clients. In this work, we explore how the number of clients sampled at each round (the cohort size) impacts the quality of the learned model and the training dynamics of federated learning algorithms. Our work poses three fundamental questions. First, what challenges arise when trying to scale federated learning to larger cohorts? Second, what parallels exist between cohort sizes in federated learning, and batch sizes in centralized learning? Last, how can we design federated learning methods that effectively utilize larger cohort sizes? We give partial answers to these questions based on extensive empirical evaluation. Our work highlights a number of challenges stemming from the use of larger cohorts. While some of these (such as generalization issues and diminishing returns) are analogs of large-batch training challenges, others (including catastrophic training failures and fairness concerns) are unique to federated learning.

AAAI Conference 2021 Conference Paper

Step-Ahead Error Feedback for Distributed Training with Compressed Gradient

An Xu
Zhouyuan Huo
Heng Huang

Although the distributed machine learning methods can speed up the training of large deep neural networks, the communication cost has become the non-negligible bottleneck to constrain the performance. To address this challenge, the gradient compression based communication-efficient distributed learning methods were designed to reduce the communication cost, and more recently the local error feedback was incorporated to compensate for the corresponding performance loss. However, in this paper, we will show that a new “gradient mismatch” problem is raised by the local error feedback in centralized distributed training and can lead to degraded performance compared with full-precision training. To solve this critical problem, we propose two novel techniques, 1) step ahead and 2) error averaging, with rigorous theoretical analysis. Both our theoretical and empirical results show that our new methods can handle the “gradient mismatch” problem. The experimental results show that we can even train faster with common gradient compression schemes than both the full-precision training and local error feedback regarding the training epochs and without performance loss.

JMLR Journal 2020 Journal Article

A Unified q-Memorization Framework for Asynchronous Stochastic Optimization

Bin Gu
Wenhan Xian
Zhouyuan Huo
Cheng Deng
Heng Huang

Asynchronous stochastic algorithms with various variance reduction techniques (such as SVRG, S2GD, SAGA and q-SAGA) are popular in solving large scale learning problems. Recently, Reddi et al. (2015) proposed an unified variance reduction framework (i.e., HSAG) to analyze the asynchronous stochastic gradient optimization. However, the HSAG framework cannot incorporate the S2GD technique, the analysis of the HSAG framework is limited to the SVRG and SAGA techniques on the smooth convex optimization. They did not analyze other important various variance techniques (e.g., S2GD and q-SAGA) and other important optimization problems (e.g., convex optimization with non-smooth regularization and non-convex optimization with cardinality constraint). In this paper, we bridge this gap by using an unified q-memorization framework for various variance reduction techniques (including SVRG, S2GD, SAGA, q-SAGA) to analyze asynchronous stochastic algorithms for three important optimization problems. Specifically, based on the q-memorization framework, 1) we propose an asynchronous stochastic gradient hard thresholding algorithm with q-memorization (AsySGHT-qM) for the non-convex optimization with cardinality constraint, and prove that the convergence rate of AsySGHT-qM before reaching the inherent error induced by gradient hard thresholding methods is geometric. 2) We propose an asynchronous stochastic proximal gradient algorithm (AsySPG-qM) for the convex optimization with non-smooth regularization, and prove that AsySPG-qM can achieve a linear convergence rate. 3) We propose an asynchronous stochastic gradient descent algorithm (AsySGD-qM) for the general non-convex optimization problem, and prove that AsySGD-qM can achieve a sublinear convergence rate to stationary points. The experimental results on various large-scale datasets confirm the fast convergence of our AsySGHT-qM, AsySPG-qM and AsySGD-qM through concrete realizations of SVRG and SAGA. [abs] [ pdf ][ bib ] &copy JMLR 2020. ( edit, beta )

AAAI Conference 2019 Conference Paper

Faster Gradient-Free Proximal Stochastic Methods for Nonconvex Nonsmooth Optimization

Feihu Huang
Bin Gu
Zhouyuan Huo
Songcan Chen
Heng Huang

Proximal gradient method has been playing an important role to solve many machine learning tasks, especially for the nonsmooth problems. However, in some machine learning problems such as the bandit model and the black-box learning problem, proximal gradient method could fail because the explicit gradients of these problems are difficult or infeasible to obtain. The gradient-free (zeroth-order) method can address these problems because only the objective function values are required in the optimization. Recently, the first zeroth-order proximal stochastic algorithm was proposed to solve the nonconvex nonsmooth problems. However, its convergence rate is O( 1 √ T ) for the nonconvex problems, which is significantly slower than the best convergence rate O( 1 T ) of the zerothorder stochastic algorithm, where T is the iteration number. To fill this gap, in the paper, we propose a class of faster zeroth-order proximal stochastic methods with the variance reduction techniques of SVRG and SAGA, which are denoted as ZO-ProxSVRG and ZO-ProxSAGA, respectively. In theoretical analysis, we address the main challenge that an unbiased estimate of the true gradient does not hold in the zerothorder case, which was required in previous theoretical analysis of both SVRG and SAGA. Moreover, we prove that both ZO-ProxSVRG and ZO-ProxSAGA algorithms have O( 1 T ) convergence rates. Finally, the experimental results verify that our algorithms have a faster convergence rate than the existing zeroth-order proximal stochastic algorithm.

NeurIPS Conference 2019 Conference Paper

Ouroboros: On Accelerating Training of Transformer-Based Language Models

Qian Yang
Zhouyuan Huo
Wenlin Wang
Lawrence Carin

Language models are essential for natural language processing (NLP) tasks, such as machine translation and text summarization. Remarkable performance has been demonstrated recently across many NLP domains via a Transformer-based language model with over a billion parameters, verifying the benefits of model size. Model parallelism is required if a model is too large to fit in a single computing device. Current methods for model parallelism either suffer from backward locking in backpropagation or are not applicable to language models. We propose the first model-parallel algorithm that speeds the training of Transformer-based language models. We also prove that our proposed algorithm is guaranteed to converge to critical points for non-convex problems. Extensive experiments on Transformer and Transformer-XL language models demonstrate that the proposed algorithm obtains a much faster speedup beyond data parallelism, with comparable or better accuracy. Code to reproduce experiments is to be found at \url{https: //github. com/LaraQianYang/Ouroboros}.

AAAI Conference 2019 Conference Paper

Scalable and Efficient Pairwise Learning to Achieve Statistical Accuracy

Bin Gu
Zhouyuan Huo
Heng Huang

Pairwise learning is an important learning topic in the machine learning community, where the loss function involves pairs of samples (e. g. , AUC maximization and metric learning). Existing pairwise learning algorithms do not perform well in the generality, scalability and efficiency simultaneously. To address these challenging problems, in this paper, we first analyze the relationship between the statistical accuracy and the regularized empire risk for pairwise loss. Based on the relationship, we propose a scalable and efficient adaptive doubly stochastic gradient algorithm (AdaDSG) for generalized regularized pairwise learning problems. More importantly, we prove that the overall computational cost of AdaDSG is O(n) to achieve the statistical accuracy on the full training set with the size of n, which is the best theoretical result for pairwise learning to the best of our knowledge. The experimental results on a variety of real-world datasets not only confirm the effectiveness of our AdaDSG algorithm, but also show that AdaDSG has significantly better scalability and efficiency than the existing pairwise learning algorithms.

AAAI Conference 2018 Conference Paper

Accelerated Method for Stochastic Composition Optimization With Nonsmooth Regularization

Zhouyuan Huo
Bin Gu
Ji Liu
Heng Huang

Stochastic composition optimization draws much attention recently and has been successful in many emerging applications of machine learning, statistical analysis, and reinforcement learning. In this paper, we focus on the composition problem with nonsmooth regularization penalty. Previous works either have slow convergence rate, or do not provide complete convergence analysis for the general problem. In this paper, we tackle these two issues by proposing a new stochastic composition optimization method for composition problem with nonsmooth regularization penalty. In our method, we apply variance reduction technique to accelerate the speed of convergence. To the best of our knowledge, our method admits the fastest convergence rate for stochastic composition optimization: for strongly convex composition problem, our algorithm is proved to admit linear convergence; for general composition problem, our algorithm signiﬁcantly improves the state-of-theart convergence rate from O(T−1/2 ) to O((n1 +n2)2/3 T−1 ). Finally, we apply our proposed algorithm to portfolio management and policy evaluation in reinforcement learning. Experimental results verify our theoretical analysis.

AAAI Conference 2018 Conference Paper

Asynchronous Doubly Stochastic Sparse Kernel Learning

Bin Gu
Miao Xin
Zhouyuan Huo
Heng Huang

Kernel methods have achieved tremendous success in the past two decades. In the current big data era, data collection has grown tremendously. However, existing kernel methods are not scalable enough both at the training and predicting steps. To address this challenge, in this paper, we ﬁrst introduce a general sparse kernel learning formulation based on the random feature approximation, where the loss functions are possibly non-convex. Then we propose a new asynchronous parallel doubly stochastic algorithm for large scale sparse kernel learning (AsyDSSKL). To the best our knowledge, AsyDSSKL is the ﬁrst algorithm with the techniques of asynchronous parallel computation and doubly stochastic optimization. We also provide a comprehensive convergence guarantee to AsyDSSKL. Importantly, the experimental results on various large-scale real-world datasets show that, our AsyDSSKL method has the signiﬁcant superiority on the computational efﬁciency at the training and predicting steps over the existing kernel methods.

ICML Conference 2018 Conference Paper

Decoupled Parallel Backpropagation with Convergence Guarantee

Zhouyuan Huo
Bin Gu 0001
Qian Yang 0003
Heng Huang 0001

Backpropagation algorithm is indispensable for the training of feedforward neural networks. It requires propagating error gradients sequentially from the output layer all the way back to the input layer. The backward locking in backpropagation algorithm constrains us from updating network layers in parallel and fully leveraging the computing resources. Recently, several algorithms have been proposed for breaking the backward locking. However, their performances degrade seriously when networks are deep. In this paper, we propose decoupled parallel backpropagation algorithm for deep learning optimization with convergence guarantee. Firstly, we decouple the backpropagation algorithm using delayed gradients, and show that the backward locking is removed when we split the networks into multiple modules. Then, we utilize decoupled parallel backpropagation in two stochastic methods and prove that our method guarantees convergence to critical points for the non-convex problem. Finally, we perform experiments for training deep convolutional neural networks on benchmark datasets. The experimental results not only confirm our theoretical analysis, but also demonstrate that the proposed method can achieve significant speedup without loss of accuracy.

ICML Conference 2018 Conference Paper

Faster Derivative-Free Stochastic Algorithm for Shared Memory Machines

Bin Gu 0001
Zhouyuan Huo
Cheng Deng 0002
Heng Huang 0001

Asynchronous parallel stochastic gradient optimization has been playing a pivotal role to solve large-scale machine learning problems in big data applications. Zeroth-order (derivative-free) methods estimate the gradient only by two function evaluations, thus have been applied to solve the problems where the explicit gradient calculations are computationally expensive or infeasible. Recently, the first asynchronous parallel stochastic zeroth-order algorithm (AsySZO) was proposed. However, its convergence rate is O(1/SQRT{T}) for the smooth, possibly non-convex learning problems, which is significantly slower than O(1/T) the best convergence rate of (asynchronous) stochastic gradient algorithm. To fill this gap, in this paper, we first point out the fundamental reason leading to the slow convergence rate of AsySZO, and then propose a new asynchronous stochastic zerothorder algorithm (AsySZO+). We provide a faster convergence rate O(1/bT) (b is the mini-batch size) for AsySZO+ by the rigorous theoretical analysis, which is a significant improvement over O(1/SQRT{T}). The experimental results on the application of ensemble learning confirm that our AsySZO+ has a faster convergence rate than the existing (asynchronous) stochastic zeroth-order algorithms.

AAAI Conference 2018 Conference Paper

Inexact Proximal Gradient Methods for Non-Convex and Non-Smooth Optimization

Bin Gu
De Wang
Zhouyuan Huo
Heng Huang

In machine learning research, the proximal gradient methods are popular for solving various optimization problems with non-smooth regularization. Inexact proximal gradient methods are extremely important when exactly solving the proximal operator is time-consuming, or the proximal operator does not have an analytic solution. However, existing inexact proximal gradient methods only consider convex problems. The knowledge of inexact proximal gradient methods in the non-convex setting is very limited. To address this challenge, in this paper, we ﬁrst propose three inexact proximal gradient algorithms, including the basic version and Nesterov’s accelerated version. After that, we provide the theoretical analysis to the basic and Nesterov’s accelerated versions. The theoretical results show that our inexact proximal gradient algorithms can have the same convergence rates as the ones of exact proximal gradient algorithms in the non-convex setting. Finally, we show the applications of our inexact proximal gradient algorithms on three representative non-convex learning problems. Empirical results conﬁrm the superiority of our new inexact proximal gradient algorithms.

NeurIPS Conference 2018 Conference Paper

Training Neural Networks Using Features Replay

Zhouyuan Huo
Bin Gu
Heng Huang

Training a neural network using backpropagation algorithm requires passing error gradients sequentially through the network. The backward locking prevents us from updating network layers in parallel and fully leveraging the computing resources. Recently, there are several works trying to decouple and parallelize the backpropagation algorithm. However, all of them suffer from severe accuracy loss or memory explosion when the neural network is deep. To address these challenging issues, we propose a novel parallel-objective formulation for the objective function of the neural network. After that, we introduce features replay algorithm and prove that it is guaranteed to converge to critical points for the non-convex problem under certain conditions. Finally, we apply our method to training deep convolutional neural networks, and the experimental results show that the proposed method achieves {faster} convergence, {lower} memory consumption, and {better} generalization error than compared methods.

AAAI Conference 2017 Conference Paper

Asynchronous Mini-Batch Gradient Descent with Variance Reduction for Non-Convex Optimization

Zhouyuan Huo
Heng Huang

We provide the ﬁrst theoretical analysis on the convergence rate of asynchronous mini-batch gradient descent with variance reduction (AsySVRG) for non-convex optimization. Asynchronous stochastic gradient descent (AsySGD) has been broadly used for deep learning optimization, and it is proved to converge with rate of O(1/ √ T) for non-convex optimization. Recently, variance reduction technique is proposed and it is proved to be able to accelerate the convergence of SGD greatly. It is shown that asynchronous SGD method with variance reduction technique has linear convergence rate when problem is strongly convex. However, there is still no work to analyze the convergence rate of this method for non-convex problem. In this paper, we consider two asynchronous parallel implementations of mini-batch gradient descent method with variance reduction: one is on distributed-memory architecture and the other is on shared-memory architecture. We prove that both methods can converge with a rate of O(1/T) for nonconvex optimization, and linear speedup is accessible when we increase the number of workers. We evaluate our methods by optimizing multi-layer neural networks on two real datasets (MNIST and CIFAR-10), and experimental results demonstrate our theoretical analysis.

IJCAI Conference 2017 Conference Paper

Joint Capped Norms Minimization for Robust Matrix Recovery

Feiping Nie
Zhouyuan Huo
Heng Huang

The low-rank matrix recovery is an important machine learning research topic with various scientific applications. Most existing low-rank matrix recovery methods relax the rank minimization problem via the trace norm minimization. However, such a relaxation makes the solution seriously deviate from the original one. Meanwhile, most matrix recovery methods minimize the squared prediction errors on the observed entries, which is sensitive to outliers. In this paper, we propose a new robust matrix recovery model to address the above two challenges. The joint capped trace norm and capped $\ell_1$-norm are used to tightly approximate the rank minimization and enhance the robustness to outliers. The evaluation experiments are performed on both synthetic data and real world applications in collaborative filtering and social network link prediction. All empirical results show our new method outperforms the existing matrix recovery methods.

IJCAI Conference 2017 Conference Paper

Multi-Class Support Vector Machine via Maximizing Multi-Class Margins

Jie Xu
Xianglong Liu
Zhouyuan Huo
Cheng Deng
Feiping Nie
Heng Huang

Support Vector Machine (SVM) is originally proposed as a binary classification model, and it has already achieved great success in different applications. In reality, it is more often to solve a problem which has more than two classes. So, it is natural to extend SVM to a multi-class classifier. There have been many works proposed to construct a multi-class classifier based on binary SVM, such as one versus all strategy, one versus one strategy and Weston's multi-class SVM. One versus all strategy and one versus one strategy split the multi-class problem to multiple binary classification subproblems, and we need to train multiple binary classifiers. Weston's multi-class SVM is formed by ensuring risk constraints and imposing a specific regularization, like Frobenius norm. It is not derived by maximizing the margin between hyperplane and training data which is the motivation in SVM. In this paper, we propose a multi-class SVM model from the perspective of maximizing margin between training points and hyperplane, and analyze the relation between our model and other related methods. In the experiment, it shows that our model can get better or compared results when comparing with other related methods.

AAAI Conference 2017 Conference Paper

Video Recovery via Learning Variation and Consistency of Images

Zhouyuan Huo
Shangqian Gao
Weidong Cai
Heng Huang

Matrix completion algorithms have been popularly used to recover images with missing entries, and they are proved to be very effective. Recent works utilized tensor completion models in video recovery assuming that all video frames are homogeneous and correlated. However, real videos are made up of different episodes or scenes, i. e. heterogeneous. Therefore, a video recovery model which utilizes both video spatiotemporal consistency and variation is necessary. To solve this problem, we propose a new video recovery method Sectional Trace Norm with Variation and Consistency Constraints (STN-VCC). In our model, capped 1-norm regularization is utilized to learn the spatial-temporal consistency and variation between consecutive frames in video clips. Meanwhile, we introduce a new low-rank model to capture the low-rank structure in video frames with a better approximation of rank minimization than traditional trace norm. An efﬁcient optimization algorithm is proposed, and we also provide a proof of convergence in the paper. We evaluate the proposed method via several video recovery tasks and experiment results show that our new method consistently outperforms other related approaches.

AAAI Conference 2016 Conference Paper

Optimal Discrete Matrix Completion

Zhouyuan Huo
Ji Liu
Heng Huang

In recent years, matrix completion methods have been successfully applied to solve recommender system applications. Most of them focus on the matrix completion problem in real number domain, and produce continuous prediction values. However, these methods are not appropriate in some occasions where the entries of matrix are discrete values, such as movie ratings prediction, social network relation and interaction prediction, because their continuous outputs are not probabilities and uninterpretable. In this case, an additional step to process the continuous results with either heuristic threshold parameters or complicated mapping is necessary, while it is inefﬁcient and may diverge from the optimal solution. There are a few matrix completion methods working on discrete number domain, however, they are not applicable to sparse and large-scale data set. In this paper, we propose a novel optimal discrete matrix completion model, which is able to learn optimal thresholds automatically and also guarantees an exact low-rank structure of the target matrix. We use stochastic gradient descent algorithm with momentum method to optimize the new objective function and speed up optimization. In the experiments, it is proved that our method can predict discrete values with high accuracy, very close to or even better than these values obtained by carefully tuned thresholds on Movielens and YouTube data sets. Meanwhile, our model is able to handle online data and easy to parallelize.