arXiv subjects

Mingyi Hong

Publications and source records attributed to Mingyi Hong.

At least 127 records · Page 7Linked to original sources

arXiv2021

Understanding Clipping for Federated Learning: Convergence and Client-Level Differential Privacy

Providing privacy protection has been one of the primary motivations of Federated Learning (FL). Recently, there has been a line of work on incorporating the formal privacy notion of differential privacy with FL. To guarantee the client-level differential privacy in FL algorithms, the clients' transmitted model updates have to be clipped before adding privacy noise. Such clipping operation is substantially different from its counterpart of gradient clipping in the centralized differentially private SGD and has not been well-understood. In this paper, we first empirically demonstrate that the clipped FedAvg can perform surprisingly well even with substantial data heterogeneity when training neural networks, which is partly because the clients' updates become similar for several popular deep architectures. Based on this key observation, we provide the convergence analysis of a differential private (DP) FedAvg algorithm and highlight the relationship between clipping bias and the distribution of the clients' updates. To the best of our knowledge, this is the first work that rigorously investigates theoretical and empirical issues regarding the clipping operation in FL algorithms.

cs.LG↗

arXiv2021

On Lower Iteration Complexity Bounds for the Saddle Point Problems

In this paper, we study the lower iteration complexity bounds for finding the saddle point of a strongly convex and strongly concave saddle point problem: $\min_x\max_yF(x,y)$. We restrict the classes of algorithms in our investigation to be either pure first-order methods or methods using proximal mappings. The existing lower bound result for this type of problems is obtained via the framework of strongly monotone variational inequality problems, which corresponds to the case where the gradient Lipschitz constants ($L_x, L_y$ and $L_{xy}$) and strong convexity/concavity constants ($μ_x$ and $μ_y$) are uniform with respect to variables $x$ and $y$. However, specific to the min-max saddle point problem these parameters are naturally different. Therefore, one is led to finding the best possible lower iteration complexity bounds, specific to the min-max saddle point models. In this paper we present the following results. For the class of pure first-order algorithms, our lower iteration complexity bound is $Ω\left(\sqrt{\frac{L_x}{μ_x}+\frac{L_{xy}^2}{μ_xμ_y}+\frac{L_y}{μ_y}}\cdot\ln\left(\frac{1}ε\right)\right)$, where the term $\frac{L_{xy}^2}{μ_xμ_y}$ explains how the coupling influences the iteration complexity. Under several special parameter regimes, this lower bound has been achieved by corresponding optimal algorithms. However, whether or not the bound under the general parameter regime is optimal remains open. Additionally, for the special case of bilinear coupling problems, given the availability of certain proximal operators, a lower bound of $Ω\left(\sqrt{\frac{L_{xy}^2}{μ_xμ_y}+1}\cdot\ln(\frac{1}ε)\right)$ is established in this paper, and optimal algorithms have already been developed in the literature.

math.OC↗

arXiv2021

STEM: A Stochastic Two-Sided Momentum Algorithm Achieving Near-Optimal Sample and Communication Complexities for Federated Learning

Federated Learning (FL) refers to the paradigm where multiple worker nodes (WNs) build a joint model by using local data. Despite extensive research, for a generic non-convex FL problem, it is not clear, how to choose the WNs' and the server's update directions, the minibatch sizes, and the local update frequency, so that the WNs use the minimum number of samples and communication rounds to achieve the desired solution. This work addresses the above question and considers a class of stochastic algorithms where the WNs perform a few local updates before communication. We show that when both the WN's and the server's directions are chosen based on a stochastic momentum estimator, the algorithm requires $\tilde{\mathcal{O}}(ε^{-3/2})$ samples and $\tilde{\mathcal{O}}(ε^{-1})$ communication rounds to compute an $ε$-stationary solution. To the best of our knowledge, this is the first FL algorithm that achieves such {\it near-optimal} sample and communication complexities simultaneously. Further, we show that there is a trade-off curve between local update frequencies and local minibatch sizes, on which the above sample and communication complexities can be maintained. Finally, we show that for the classical FedAvg (a.k.a. Local SGD, which is a momentum-less special case of the STEM), a similar trade-off curve exists, albeit with worse sample and communication complexities. Our insights on this trade-off provides guidelines for choosing the four important design elements for FL algorithms, the update frequency, directions, and minibatch sizes to achieve the best performance.

cs.LG↗

arXiv2021

A Near-Optimal Algorithm for Stochastic Bilevel Optimization via Double-Momentum

This paper proposes a new algorithm -- the \underline{S}ingle-timescale Do\underline{u}ble-momentum \underline{St}ochastic \underline{A}pprox\underline{i}matio\underline{n} (SUSTAIN) -- for tackling stochastic unconstrained bilevel optimization problems. We focus on bilevel problems where the lower level subproblem is strongly-convex and the upper level objective function is smooth. Unlike prior works which rely on \emph{two-timescale} or \emph{double loop} techniques, we design a stochastic momentum-assisted gradient estimator for both the upper and lower level updates. The latter allows us to control the error in the stochastic gradient updates due to inaccurate solution to both subproblems. If the upper objective function is smooth but possibly non-convex, we show that {\aname}~requires $\mathcal{O}(ε^{-3/2})$ iterations (each using ${\cal O}(1)$ samples) to find an $ε$-stationary solution. The $ε$-stationary solution is defined as the point whose squared norm of the gradient of the outer function is less than or equal to $ε$. The total number of stochastic gradient samples required for the upper and lower level objective functions matches the best-known complexity for single-level stochastic gradient algorithms. We also analyze the case when the upper level objective function is strongly-convex.

math.OC↗

arXiv2021

Learning to Continuously Optimize Wireless Resource in a Dynamic Environment: A Bilevel Optimization Perspective

There has been a growing interest in developing data-driven, and in particular deep neural network (DNN) based methods for modern communication tasks. For a few popular tasks such as power control, beamforming, and MIMO detection, these methods achieve state-of-the-art performance while requiring less computational efforts, less resources for acquiring channel state information (CSI), etc. However, it is often challenging for these approaches to learn in a dynamic environment. This work develops a new approach that enables data-driven methods to continuously learn and optimize resource allocation strategies in a dynamic environment. Specifically, we consider an ``episodically dynamic" setting where the environment statistics change in ``episodes", and in each episode the environment is stationary. We propose to build the notion of continual learning (CL) into wireless system design, so that the learning model can incrementally adapt to the new episodes, {\it without forgetting} knowledge learned from the previous episodes. Our design is based on a novel bilevel optimization formulation which ensures certain ``fairness" across different data samples. We demonstrate the effectiveness of the CL approach by integrating it with two popular DNN based models for power control and beamforming, respectively, and testing using both synthetic and ray-tracing based data sets. These numerical results show that the proposed CL approach is not only able to adapt to the new scenarios quickly and seamlessly, but importantly, it also maintains high performance over the previously encountered scenarios as well.

eess.SP↗

arXiv2021

Stochastic Mirror Descent for Low-Rank Tensor Decomposition Under Non-Euclidean Losses

This work considers low-rank canonical polyadic decomposition (CPD) under a class of non-Euclidean loss functions that frequently arise in statistical machine learning and signal processing. These loss functions are often used for certain types of tensor data, e.g., count and binary tensors, where the least squares loss is considered unnatural.Compared to the least squares loss, the non-Euclidean losses are generally more challenging to handle. Non-Euclidean CPD has attracted considerable interests and a number of prior works exist. However, pressing computational and theoretical challenges, such as scalability and convergence issues, still remain. This work offers a unified stochastic algorithmic framework for large-scale CPD decomposition under a variety of non-Euclidean loss functions. Our key contribution lies in a tensor fiber sampling strategy-based flexible stochastic mirror descent framework. Leveraging the sampling scheme and the multilinear algebraic structure of low-rank tensors, the proposed lightweight algorithm ensures global convergence to a stationary point under reasonable conditions. Numerical results show that our framework attains promising non-Euclidean CPD performance. The proposed framework also exhibits substantial computational savings compared to state-of-the-art methods.

stat.ML↗

arXiv2021

Understanding Gradient Clipping in Private SGD: A Geometric Perspective

Deep learning models are increasingly popular in many machine learning applications where the training data may contain sensitive information. To provide formal and rigorous privacy guarantee, many learning systems now incorporate differential privacy by training their models with (differentially) private SGD. A key step in each private SGD update is gradient clipping that shrinks the gradient of an individual example whenever its L2 norm exceeds some threshold. We first demonstrate how gradient clipping can prevent SGD from converging to stationary point. We then provide a theoretical analysis that fully quantifies the clipping bias on convergence with a disparity measure between the gradient distribution and a geometrically symmetric distribution. Our empirical evaluation further suggests that the gradient distributions along the trajectory of private SGD indeed exhibit symmetric structure that favors convergence. Together, our results provide an explanation why private SGD with gradient clipping remains effective in practice despite its potential clipping bias. Finally, we develop a new perturbation-based technique that can provably correct the clipping bias even for instances with highly asymmetric gradient distributions.

cs.LG↗

arXiv2021

Hybrid Block Successive Approximation for One-Sided Non-Convex Min-Max Problems: Algorithms and Applications

The min-max problem, also known as the saddle point problem, is a class of optimization problems which minimizes and maximizes two subsets of variables simultaneously. This class of problems can be used to formulate a wide range of signal processing and communication (SPCOM) problems. Despite its popularity, most existing theory for this class has been mainly developed for problems with certain special convex-concave structure. Therefore, it cannot be used to guide the algorithm design for many interesting problems in SPCOM, where various kinds of non-convexity arise. In this work, we consider a block-wise one-sided non-convex min-max problem, in which the minimization problem consists of multiple blocks and is non-convex, while the maximization problem is (strongly) concave. We propose a class of simple algorithms named Hybrid Block Successive Approximation (HiBSA), which alternatingly perform gradient descent-type steps for the minimization blocks and gradient ascent-type steps for the maximization problem. A key element in the proposed algorithm is the use of certain regularization and penalty sequences, which stabilize the algorithm and ensure convergence. We show that HiBSA converges to some properly defined first-order stationary solutions with quantifiable global rates. To validate the efficiency of the proposed algorithms, we conduct numerical tests on a number of problems, including the robust learning problem, the non-convex min-utility maximization problems, and certain wireless jamming problem arising in interfering channels.

math.OC↗

arXiv2021

On Instabilities of Conventional Multi-Coil MRI Reconstruction to Small Adverserial Perturbations

Although deep learning (DL) has received much attention in accelerated MRI, recent studies suggest small perturbations may lead to instabilities in DL-based reconstructions, leading to concern for their clinical application. However, these works focus on single-coil acquisitions, which is not practical. We investigate instabilities caused by small adversarial attacks for multi-coil acquisitions. Our results suggest that, parallel imaging and multi-coil CS exhibit considerable instabilities against small adversarial perturbations.

eess.IV↗

arXiv2021

Hybrid Federated Learning: Algorithms and Implementation

Federated learning (FL) is a recently proposed distributed machine learning paradigm dealing with distributed and private data sets. Based on the data partition pattern, FL is often categorized into horizontal, vertical, and hybrid settings. Despite the fact that many works have been developed for the first two approaches, the hybrid FL setting (which deals with partially overlapped feature space and sample space) remains less explored, though this setting is extremely important in practice. In this paper, we first set up a new model-matching-based problem formulation for hybrid FL, then propose an efficient algorithm that can collaboratively train the global and local models to deal with full and partial featured data. We conduct numerical experiments on the multi-view ModelNet40 data set to validate the performance of the proposed algorithm. To the best of our knowledge, this is the first formulation and algorithm developed for the hybrid FL.

cs.LG↗

arXiv2021

Decentralized Riemannian Gradient Descent on the Stiefel Manifold

We consider a distributed non-convex optimization where a network of agents aims at minimizing a global function over the Stiefel manifold. The global function is represented as a finite sum of smooth local functions, where each local function is associated with one agent and agents communicate with each other over an undirected connected graph. The problem is non-convex as local functions are possibly non-convex (but smooth) and the Steifel manifold is a non-convex set. We present a decentralized Riemannian stochastic gradient method (DRSGD) with the convergence rate of $\mathcal{O}(1/\sqrt{K})$ to a stationary point. To have exact convergence with constant stepsize, we also propose a decentralized Riemannian gradient tracking algorithm (DRGTA) with the convergence rate of $\mathcal{O}(1/K)$ to a stationary point. We use multi-step consensus to preserve the iteration in the local (consensus) region. DRGTA is the first decentralized algorithm with exact convergence for distributed optimization on Stiefel manifold.

math.OC↗

arXiv2021

On the Local Linear Rate of Consensus on the Stiefel Manifold

We study the convergence properties of Riemannian gradient method for solving the consensus problem (for an undirected connected graph) over the Stiefel manifold. The Stiefel manifold is a non-convex set and the standard notion of averaging in the Euclidean space does not work for this problem. We propose Distributed Riemannian Consensus on Stiefel Manifold (DRCS) and prove that it enjoys a local linear convergence rate to global consensus. More importantly, this local rate asymptotically scales with the second largest singular value of the communication matrix, which is on par with the well-known rate in the Euclidean space. To the best of our knowledge, this is the first work showing the equality of the two rates. The main technical challenges include (i) developing a Riemannian restricted secant inequality for convergence analysis, and (ii) to identify the conditions (e.g., suitable step-size and initialization) under which the algorithm always stays in the local region.

math.OC↗

arXiv2021

Online Proximal-ADMM For Time-varying Constrained Convex Optimization

This paper considers a convex optimization problem with cost and constraints that evolve over time. The function to be minimized is strongly convex and possibly non-differentiable, and variables are coupled through linear constraints. In this setting, the paper proposes an online algorithm based on the alternating direction method of multipliers (ADMM), to track the optimal solution trajectory of the time-varying problem; in particular, the proposed algorithm consists of a primal proximal gradient descent step and an appropriately perturbed dual ascent step. The paper derives tracking results, asymptotic bounds, and linear convergence results. The proposed algorithm is then specialized to a multi-area power grid optimization problem, and our numerical results verify the desired properties.

eess.SY↗

arXiv2020

Learning to Continuously Optimize Wireless Resource In Episodically Dynamic Environment

There has been a growing interest in developing data-driven and in particular deep neural network (DNN) based methods for modern communication tasks. For a few popular tasks such as power control, beamforming, and MIMO detection, these methods achieve state-of-the-art performance while requiring less computational efforts, less channel state information (CSI), etc. However, it is often challenging for these approaches to learn in a dynamic environment where parameters such as CSIs keep changing. This work develops a methodology that enables data-driven methods to continuously learn and optimize in a dynamic environment. Specifically, we consider an ``episodically dynamic" setting where the environment changes in ``episodes", and in each episode the environment is stationary. We propose to build the notion of continual learning (CL) into the modeling process of learning wireless systems, so that the learning model can incrementally adapt to the new episodes, {\it without forgetting} knowledge learned from the previous episodes. Our design is based on a novel min-max formulation which ensures certain ``fairness" across different data samples. We demonstrate the effectiveness of the CL approach by customizing it to two popular DNN based models (one for power control and one for beamforming), and testing using both synthetic and real data sets. These numerical results show that the proposed CL approach is not only able to adapt to the new scenarios quickly and seamlessly, but importantly, it maintains high performance over the previously encountered scenarios as well.

eess.SP↗

arXiv2020

Learning to Beamform in Heterogeneous Massive MIMO Networks

It is well-known that the problem of finding the optimal beamformers in massive multiple-input multiple-output (MIMO) networks is challenging because of its non-convexity, and conventional optimization based algorithms suffer from high computational costs. While computationally efficient deep learning based methods have been proposed, their complexity heavily relies upon system parameters such as the number of transmit antennas, and therefore these methods typically do not generalize well when deployed in heterogeneous scenarios where the base stations (BSs) are equipped with different numbers of transmit antennas and have different inter-BS distances. This paper proposes a novel deep learning based beamforming algorithm to address the above challenges. Specifically, we consider the weighted sum rate (WSR) maximization problem in multi-input and single-output (MISO) interference channels, and propose a deep neural network architecture by unfolding a parallel gradient projection algorithm. Somewhat surprisingly, by leveraging the low-dimensional structures of the optimal beamforming solution, our constructed neural network can be made independent of the numbers of transmit antennas and BSs. Moreover, such a design can be further extended to a cooperative multicell network. Numerical results based on both synthetic and ray-tracing channel models show that the proposed neural network can achieve high WSRs with significantly reduced runtime, while exhibiting favorable generalization capability with respect to the antenna number, BS number and the inter-BS distance.

cs.IT↗

arXiv2020

Imitation Privacy

In recent years, there have been many cloud-based machine learning services, where well-trained models are provided to users on a pay-per-query scheme through a prediction API. The emergence of these services motivates this work, where we will develop a general notion of model privacy named imitation privacy. We show the broad applicability of imitation privacy in classical query-response MLaaS scenarios and new multi-organizational learning scenarios. We also exemplify the fundamental difference between imitation privacy and the usual data-level privacy.

cs.CR↗

arXiv2020

Joint Channel Assignment and Power Allocation for Multi-UAV Communication

Unmanned aerial vehicle (UAV) swarm has emerged as a promising novel paradigm to achieve better coverage and higher capacity for future wireless network by exploiting the more favorable line-of-sight (LoS) propagation. To reap the potential gains of UAV swarm, the remote control signal sent by ground control unit (GCU) is essential, whereas the control signal quality are susceptible in practice due to the effect of the adjacent channel interference (ACI) and the external interference (EI) from radiation sources distributed across the region. To tackle these challenges, this paper considers priority-aware resource coordination in a multi-UAV communication system, where multiple UAVs are controlled by a GCU to perform certain tasks with a pre-defined trajectory. Specifically, we maximize the minimum signal-to-interference-plus-noise ratio (SINR) among all the UAVs by jointly optimizing channel assignment and power allocation strategy under stringent resource availability constraints. According to the intensity of ACI, we consider the corresponding problem in two scenarios, i.e., Null-ACI and ACI systems. By virtue of the particular problem structure in Null-ACI case, we first recast the formulation into an equivalent yet more tractable form and obtain the global optimal solution via Hungarian algorithm. For general ACI systems, we develop an efficient iterative algorithm for its solution based on the smooth approximation and alternating optimization methods. Extensive simulation results demonstrate that the proposed algorithms can significantly enhance the minimum SINR among all the UAVs and adapt the allocation of communication resources to diverse mission priority.

eess.SP↗

arXiv2020

Non-convex Min-Max Optimization: Applications, Challenges, and Recent Theoretical Advances

The min-max optimization problem, also known as the saddle point problem, is a classical optimization problem which is also studied in the context of zero-sum games. Given a class of objective functions, the goal is to find a value for the argument which leads to a small objective value even for the worst case function in the given class. Min-max optimization problems have recently become very popular in a wide range of signal and data processing applications such as fair beamforming, training generative adversarial networks (GANs), and robust machine learning, to just name a few. The overarching goal of this article is to provide a survey of recent advances for an important subclass of min-max problem, where the minimization and maximization problems can be non-convex and/or non-concave. In particular, we will first present a number of applications to showcase the importance of such min-max problems; then we discuss key theoretical challenges, and provide a selective review of some exciting recent theoretical and algorithmic advances in tackling non-convex min-max problems. Finally, we will point out open questions and future research directions.

math.OC↗