Qianqian Tong
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Qianqian Tong has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Jinbo Bi
University of Connecticut, USA
7 shared publications - Guannan Liang
Department of Computer Science and Engineering, University of Connecticut, Storrs, CT 06269, USA
6 shared publications - Jiahao Ding
University of Houston
3 shared publications - Chunjiang Zhu
University of Connecticut
2 shared publications - Miao Pan
University of Houston
2 shared publications - Derek Fox
UNCG, Greensboro, North Carolina, USA
1 shared publication
Latest Publications
- Open Access
- 6 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 75-82
Stochastic Variance-Reduced Iterative Hard Thresholding in Graph Sparsity Optimization
- 6 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 75-82
Open AccessStochastic Variance-Reduced Iterative Hard Thresholding in Graph Sparsity Optimization
- 13 October 2022
- Published by Elsevier in Information Sciences
- Vol. 630, 567-585
Stochastic privacy-preserving methods for nonconvex sparse learning
- 13 October 2022
- Published by Elsevier in Information Sciences
- Vol. 630, 567-585
Stochastic privacy-preserving methods for nonconvex sparse learning
- Open Access
- 6 September 2022
- Published by MDPI AG in Algorithms
- Vol. 15 (9) , 319
Federated Optimization of ℓ0-norm Regularized Sparse Learning
Regularized sparse learning with the -norm is important in many areas, including statistical learning and signal processing. Iterative hard thresholding (IHT) methods are the state-of-the-art for nonconvex-constrained sparse learning due to their capability of recovering true support and scalability with large datasets. The current theoretical analysis of IHT assumes the use of centralized IID data. In realistic large-scale scenarios, however, data are distributed, seldom IID, and private to edge computing devices at the local level. Consequently, it is required to study the property of IHT in a federated environment, where local devices update the sparse model individually and communicate with a central server for aggregation infrequently without sharing local data. In this paper, we propose the first group of federated IHT methods: Federated Hard Thresholding (Fed-HT) and Federated Iterative Hard Thresholding (FedIter-HT) with theoretical guarantees. We prove that both algorithms have a linear convergence rate and guarantee for recovering the optimal sparse estimator, which is comparable to classic IHT methods, but with decentralized, non-IID, and unbalanced data. Empirical results demonstrate that the Fed-HT and FedIter-HT outperform their competitor—a distributed IHT, in terms of reducing objective values with fewer communication rounds and bandwidth requirements.- 6 September 2022
- Published by MDPI AG in Algorithms
- Vol. 15 (9) , 319
Open AccessFederated Optimization of ℓ0-norm Regularized Sparse Learning
Regularized sparse learning with the -norm is important in many areas, including statistical learning and signal processing. Iterative hard thresholding (IHT) methods are the state-of-the-art for nonconvex-constrained sparse learning due to their capability of recovering true support and scalability with large datasets. The current theoretical analysis of IHT assumes the use of centralized IID data. In realistic large-scale scenarios, however, data are distributed, seldom IID, and private to edge computing devices at the local level. Consequently, it is required to study the property of IHT in a federated environment, where local devices update the sparse model individually and communicate with a central server for aggregation infrequently without sharing local data. In this paper, we propose the first group of federated IHT methods: Federated Hard Thresholding (Fed-HT) and Federated Iterative Hard Thresholding (FedIter-HT) with theoretical guarantees. We prove that both algorithms have a linear convergence rate and guarantee for recovering the optimal sparse estimator, which is comparable to classic IHT methods, but with decentralized, non-IID, and unbalanced data. Empirical results demonstrate that the Fed-HT and FedIter-HT outperform their competitor—a distributed IHT, in terms of reducing objective values with fewer communication rounds and bandwidth requirements. - Open Access
Escaping Saddle Points with Stochastically Controlled Stochastic Gradient Methods
Stochastically controlled stochastic gradient (SCSG) methods have been proved to converge efficiently to first-order stationary points which, however, can be saddle points in nonconvex optimization. It has been observed that a stochastic gradient descent (SGD) step introduces anistropic noise around saddle points for deep learning and non-convex half space learning problems, which indicates that SGD satisfies the correlated negative curvature (CNC) condition for these problems. Therefore, we propose to use a separate SGD step to help the SCSG method escape from strict saddle points, resulting in the CNC-SCSG method. The SGD step plays a role similar to noise injection but is more stable. We prove that the resultant algorithm converges to a second-order stationary point with a convergence rate of $\tilde{O}( \epsilon^{-2} log( 1/\epsilon))$ where $\epsilon$ is the pre-specified error tolerance. This convergence rate is independent of the problem dimension, and is faster than that of CNC-SGD. A more general framework is further designed to incorporate the proposed CNC-SCSG into any first-order method for the method to escape saddle points. Simulation studies illustrate that the proposed algorithm can escape saddle points in much fewer epochs than the gradient descent methods perturbed by either noise injection or a SGD step.Open AccessEscaping Saddle Points with Stochastically Controlled Stochastic Gradient Methods
Stochastically controlled stochastic gradient (SCSG) methods have been proved to converge efficiently to first-order stationary points which, however, can be saddle points in nonconvex optimization. It has been observed that a stochastic gradient descent (SGD) step introduces anistropic noise around saddle points for deep learning and non-convex half space learning problems, which indicates that SGD satisfies the correlated negative curvature (CNC) condition for these problems. Therefore, we propose to use a separate SGD step to help the SCSG method escape from strict saddle points, resulting in the CNC-SCSG method. The SGD step plays a role similar to noise injection but is more stable. We prove that the resultant algorithm converges to a second-order stationary point with a convergence rate of $\tilde{O}( \epsilon^{-2} log( 1/\epsilon))$ where $\epsilon$ is the pre-specified error tolerance. This convergence rate is independent of the problem dimension, and is faster than that of CNC-SGD. A more general framework is further designed to incorporate the proposed CNC-SCSG into any first-order method for the method to escape saddle points. Simulation studies illustrate that the proposed algorithm can escape saddle points in much fewer epochs than the gradient descent methods perturbed by either noise injection or a SGD step. - Open Access
Effective Federated Adaptive Gradient Methods with Non-IID Decentralized Data
Federated learning allows loads of edge computing devices to collaboratively learn a global model without data sharing. The analysis with partial device participation under non-IID and unbalanced data reflects more reality. In this work, we propose federated learning versions of adaptive gradient methods - Federated AGMs - which employ both the first-order and second-order momenta, to alleviate generalization performance deterioration caused by dissimilarity of data population among devices. To further improve the test performance, we compare several schemes of calibration for the adaptive learning rate, including the standard Adam calibrated by $\epsilon$, $p$-Adam, and one calibrated by an activation function. Our analysis provides the first set of theoretical results that the proposed (calibrated) Federated AGMs converge to a first-order stationary point under non-IID and unbalanced data settings for nonconvex optimization. We perform extensive experiments to compare these federated learning methods with the state-of-the-art FedAvg, FedMomentum and SCAFFOLD and to assess the different calibration schemes and the advantages of AGMs over the current federated learning methods.Open AccessEffective Federated Adaptive Gradient Methods with Non-IID Decentralized Data
Federated learning allows loads of edge computing devices to collaboratively learn a global model without data sharing. The analysis with partial device participation under non-IID and unbalanced data reflects more reality. In this work, we propose federated learning versions of adaptive gradient methods - Federated AGMs - which employ both the first-order and second-order momenta, to alleviate generalization performance deterioration caused by dissimilarity of data population among devices. To further improve the test performance, we compare several schemes of calibration for the adaptive learning rate, including the standard Adam calibrated by $\epsilon$, $p$-Adam, and one calibrated by an activation function. Our analysis provides the first set of theoretical results that the proposed (calibrated) Federated AGMs converge to a first-order stationary point under non-IID and unbalanced data settings for nonconvex optimization. We perform extensive experiments to compare these federated learning methods with the state-of-the-art FedAvg, FedMomentum and SCAFFOLD and to assess the different calibration schemes and the advantages of AGMs over the current federated learning methods. - Open Access
Asynchronous Parallel Stochastic Quasi-Newton Methods
Although first-order stochastic algorithms, such as stochastic gradient descent, have been the main force to scale up machine learning models, such as deep neural nets, the second-order quasi-Newton methods start to draw attention due to their effectiveness in dealing with ill-conditioned optimization problems. The L-BFGS method is one of the most widely used quasi-Newton methods. We propose an asynchronous parallel algorithm for stochastic quasi-Newton (AsySQN) method. Unlike prior attempts, which parallelize only the calculation for gradient or the two-loop recursion of L-BFGS, our algorithm is the first one that truly parallelizes L-BFGS with a convergence guarantee. Adopting the variance reduction technique, a prior stochastic L-BFGS, which has not been designed for parallel computing, reaches a linear convergence rate. We prove that our asynchronous parallel scheme maintains the same linear convergence rate but achieves significant speedup. Empirical evaluations in both simulations and benchmark datasets demonstrate the speedup in comparison with the non-parallel stochastic L-BFGS, as well as the better performance than first-order methods in solving ill-conditioned problems.
Open AccessAsynchronous Parallel Stochastic Quasi-Newton Methods
Although first-order stochastic algorithms, such as stochastic gradient descent, have been the main force to scale up machine learning models, such as deep neural nets, the second-order quasi-Newton methods start to draw attention due to their effectiveness in dealing with ill-conditioned optimization problems. The L-BFGS method is one of the most widely used quasi-Newton methods. We propose an asynchronous parallel algorithm for stochastic quasi-Newton (AsySQN) method. Unlike prior attempts, which parallelize only the calculation for gradient or the two-loop recursion of L-BFGS, our algorithm is the first one that truly parallelizes L-BFGS with a convergence guarantee. Adopting the variance reduction technique, a prior stochastic L-BFGS, which has not been designed for parallel computing, reaches a linear convergence rate. We prove that our asynchronous parallel scheme maintains the same linear convergence rate but achieves significant speedup. Empirical evaluations in both simulations and benchmark datasets demonstrate the speedup in comparison with the non-parallel stochastic L-BFGS, as well as the better performance than first-order methods in solving ill-conditioned problems.
- Open Access
Effective Proximal Methods for Non-convex Non-smooth Regularized Learning
Sparse learning is a very important tool for mining useful information and patterns from high dimensional data. Non-convex non-smooth regularized learning problems play essential roles in sparse learning, and have drawn extensive attentions recently. We design a family of stochastic proximal gradient methods by applying arbitrary sampling to solve the empirical risk minimization problem with a non-convex and non-smooth regularizer. These methods draw mini-batches of training examples according to an arbitrary probability distribution when computing stochastic gradients. A unified analytic approach is developed to examine the convergence and computational complexity of these methods, allowing us to compare the different sampling schemes. We show that the independent sampling scheme tends to improve performance over the commonly-used uniform sampling scheme. Our new analysis also derives a tighter bound on convergence speed for the uniform sampling than the best one available so far. Empirical evaluations demonstrate that the proposed algorithms converge faster than the state of the art.
Open AccessEffective Proximal Methods for Non-convex Non-smooth Regularized Learning
Sparse learning is a very important tool for mining useful information and patterns from high dimensional data. Non-convex non-smooth regularized learning problems play essential roles in sparse learning, and have drawn extensive attentions recently. We design a family of stochastic proximal gradient methods by applying arbitrary sampling to solve the empirical risk minimization problem with a non-convex and non-smooth regularizer. These methods draw mini-batches of training examples according to an arbitrary probability distribution when computing stochastic gradients. A unified analytic approach is developed to examine the convergence and computational complexity of these methods, allowing us to compare the different sampling schemes. We show that the independent sampling scheme tends to improve performance over the commonly-used uniform sampling scheme. Our new analysis also derives a tighter bound on convergence speed for the uniform sampling than the best one available so far. Empirical evaluations demonstrate that the proposed algorithms converge faster than the state of the art.
- Open Access
Calibrating the Adaptive Learning Rate to Improve Convergence of ADAM
Adaptive gradient methods (AGMs) have become popular in optimizing the nonconvex problems in deep learning area. We revisit AGMs and identify that the adaptive learning rate (A-LR) used by AGMs varies significantly across the dimensions of the problem over epochs (i.e., anisotropic scale), which may lead to issues in convergence and generalization. All existing modified AGMs actually represent efforts in revising the A-LR. Theoretically, we provide a new way to analyze the convergence of AGMs and prove that the convergence rate of \textsc{Adam} also depends on its hyper-parameter $\epsilon$, which has been overlooked previously. Based on these two facts, we propose a new AGM by calibrating the A-LR with an activation ({\em softplus}) function, resulting in the \textsc{Sadam} and \textsc{SAMSGrad} methods \footnote{Code is available at https://github.com/neilliang90/Sadam.git.}. We further prove that these algorithms enjoy better convergence speed under nonconvex, non-strongly convex, and Polyak-{\L}ojasiewicz conditions compared with \textsc{Adam}. Empirical studies support our observation of the anisotropic A-LR and show that the proposed methods outperform existing AGMs and generalize even better than S-Momentum in multiple deep learning tasks.Open AccessCalibrating the Adaptive Learning Rate to Improve Convergence of ADAM
Adaptive gradient methods (AGMs) have become popular in optimizing the nonconvex problems in deep learning area. We revisit AGMs and identify that the adaptive learning rate (A-LR) used by AGMs varies significantly across the dimensions of the problem over epochs (i.e., anisotropic scale), which may lead to issues in convergence and generalization. All existing modified AGMs actually represent efforts in revising the A-LR. Theoretically, we provide a new way to analyze the convergence of AGMs and prove that the convergence rate of \textsc{Adam} also depends on its hyper-parameter $\epsilon$, which has been overlooked previously. Based on these two facts, we propose a new AGM by calibrating the A-LR with an activation ({\em softplus}) function, resulting in the \textsc{Sadam} and \textsc{SAMSGrad} methods \footnote{Code is available at https://github.com/neilliang90/Sadam.git.}. We further prove that these algorithms enjoy better convergence speed under nonconvex, non-strongly convex, and Polyak-{\L}ojasiewicz conditions compared with \textsc{Adam}. Empirical studies support our observation of the anisotropic A-LR and show that the proposed methods outperform existing AGMs and generalize even better than S-Momentum in multiple deep learning tasks.