Recently, min-max optimization problems have received increasing attention due to their wide range of applications in machine learning (ML). However, most existing min-max solution techniques are either single-machine or distributed algorithms coordinated by a central server. In this paper, we focus on the decentralized min-max optimization for learning with domain constraints, where multiple agents collectively solve a nonconvex-strongly-concave min-max saddle point problem without coordination from any server. Decentralized min-max optimization problems with domain constraints underpins many important ML applications, including multi-agent ML fairness assurance, and policy evaluations in multi-agent reinforcement learning. We propose an algorithm called PRECISION (proximal gradient-tracking and stochastic recursive variance reduction) that enjoys a convergence rate of $O(1/T)$, where $T$ is the maximum number of iterations. To further reduce sample complexity, we propose PRECISION$^+$ with an adaptive batch size technique. We show that the fast $O(1/T)$ convergence of PRECISION and PRECISION$^+$ to an $\epsilon$-stationary point imply $O(\epsilon^{-2})$ communication complexity and $O(m\sqrt{n}\epsilon^{-2})$ sample complexity, where $m$ is the number of agents and $n$ is the size of dataset at each agent. To our knowledge, this is the first work that achieves $O(\epsilon^{-2})$ in both sample and communication complexities in decentralized min-max learning with domain constraints. Our experiments also corroborate the theoretical results.
Due to the significant computational challenge of training large-scale graph neural networks (GNNs), various sparse learning techniques have been exploited to reduce memory and storage costs. Examples include \textit{graph sparsification} that samples a subgraph to reduce the amount of data aggregation and \textit{model sparsification} that prunes the neural network to reduce the number of trainable weights. Despite the empirical successes in reducing the training cost while maintaining the test accuracy, the theoretical generalization analysis of sparse learning for GNNs remains elusive. To the best of our knowledge, this paper provides the first theoretical characterization of joint edge-model sparse learning from the perspective of sample complexity and convergence rate in achieving zero generalization error. It proves analytically that both sampling important nodes and pruning neurons with the lowest-magnitude can reduce the sample complexity and improve convergence without compromising the test accuracy. Although the analysis is centered on two-layer GNNs with structural constraints on data, the insights are applicable to more general setups and justified by both synthetic and practical citation datasets.
Many real-world problems not only have complicated nonconvex functional constraints but also use a large number of data points. This motivates the design of efficient stochastic methods on finite-sum or expectation constrained problems. In this paper, we design and analyze stochastic inexact augmented Lagrangian methods (Stoc-iALM) to solve problems involving a nonconvex composite (i.e. smooth+nonsmooth) objective and nonconvex smooth functional constraints. We adopt the standard iALM framework and design a subroutine by using the momentum-based variance-reduced proximal stochastic gradient method (PStorm) and a postprocessing step. Under certain regularity conditions (assumed also in existing works), to reach an $\varepsilon$-KKT point in expectation, we establish an oracle complexity result of $O(\varepsilon^{-5})$, which is better than the best-known $O(\varepsilon^{-6})$ result. Numerical experiments on the fairness constrained problem and the Neyman-Pearson classification problem with real data demonstrate that our proposed method outperforms an existing method with the previously best-known complexity result.
The graph neural network (GNN) models have presented impressive achievements in numerous machine learning tasks. However, many existing GNN models are shown to be vulnerable to adversarial attacks, which creates a stringent need to build robust GNN architectures. In this work, we propose a novel interpretable message passing scheme with adaptive structure (ASMP) to defend against adversarial attacks on graph structure. Layers in ASMP are derived based on optimization steps that minimize an objective function that learns the node feature and the graph structure simultaneously. ASMP is adaptive in the sense that the message passing process in different layers is able to be carried out over dynamically adjusted graphs. Such property allows more fine-grained handling of the noisy (or perturbed) graph structure and hence improves the robustness. Convergence properties of the ASMP scheme are theoretically established. Integrating ASMP with neural networks can lead to a new family of GNN models with adaptive structure (ASGNN). Extensive experiments on semi-supervised node classification tasks demonstrate that the proposed ASGNN outperforms the state-of-the-art GNN architectures in terms of classification performance under various adversarial attacks.
In recent years, decentralized bilevel optimization problems have received increasing attention in the networking and machine learning communities thanks to their versatility in modeling decentralized learning problems over peer-to-peer networks (e.g., multi-agent meta-learning, multi-agent reinforcement learning, personalized training, and Byzantine-resilient learning). However, for decentralized bilevel optimization over peer-to-peer networks with limited computation and communication capabilities, how to achieve low sample and communication complexities are two fundamental challenges that remain under-explored so far. In this paper, we make the first attempt to investigate the class of decentralized bilevel optimization problems with nonconvex and strongly-convex structure corresponding to the outer and inner subproblems, respectively. Our main contributions in this paper are two-fold: i) We first propose a deterministic algorithm called INTERACT (inner-gradient-descent-outer-tracked-gradient) that requires the sample complexity of $\mathcal{O}(n \epsilon^{-1})$ and communication complexity of $\mathcal{O}(\epsilon^{-1})$ to solve the bilevel optimization problem, where $n$ and $\epsilon > 0$ are the number of samples at each agent and the desired stationarity gap, respectively. ii) To relax the need for full gradient evaluations in each iteration, we propose a stochastic variance-reduced version of INTERACT (SVR-INTERACT), which improves the sample complexity to $\mathcal{O}(\sqrt{n} \epsilon^{-1})$ while achieving the same communication complexity as the deterministic algorithm. To our knowledge, this work is the first that achieves both low sample and communication complexities for solving decentralized bilevel optimization problems over networks. Our numerical experiments also corroborate our theoretical findings.
Nonconvex constrained optimization problems can be used to model a number of machine learning problems, such as multi-class Neyman-Pearson classification and constrained Markov decision processes. However, such kinds of problems are challenging because both the objective and constraints are possibly nonconvex, so it is difficult to balance the reduction of the loss value and reduction of constraint violation. Although there are a few methods that solve this class of problems, all of them are double-loop or triple-loop algorithms, and they require oracles to solve some subproblems up to certain accuracy by tuning multiple hyperparameters at each iteration. In this paper, we propose a novel gradient descent and perturbed ascent (GDPA) algorithm to solve a class of smooth nonconvex inequality constrained problems. The GDPA is a primal-dual algorithm, which only exploits the first-order information of both the objective and constraint functions to update the primal and dual variables in an alternating way. The key feature of the proposed algorithm is that it is a single-loop algorithm, where only two step-sizes need to be tuned. We show that under a mild regularity condition GDPA is able to find Karush-Kuhn-Tucker (KKT) points of nonconvex functional constrained problems with convergence rate guarantees. To the best of our knowledge, it is the first single-loop algorithm that can solve the general nonconvex smooth problems with nonconvex inequality constraints. Numerical results also showcase the superiority of GDPA compared with the best-known algorithms (in terms of both stationarity measure and feasibility of the obtained solutions).
Meta learning has demonstrated tremendous success in few-shot learning with limited supervised data. In those settings, the meta model is usually overparameterized. While the conventional statistical learning theory suggests that overparameterized models tend to overfit, empirical evidence reveals that overparameterized meta learning methods still work well -- a phenomenon often called ``benign overfitting.'' To understand this phenomenon, we focus on the meta learning settings with a challenging nested structure that we term the nested meta learning, and analyze its generalization performance under an overparameterized meta learning model. While our analysis uses the relatively tractable linear models, our theory contributes to understanding the delicate interplay among data heterogeneity, model adaptation and benign overfitting in nested meta learning tasks. We corroborate our theoretical claims through numerical simulations.
Current deep neural networks (DNNs) are vulnerable to adversarial attacks, where adversarial perturbations to the inputs can change or manipulate classification. To defend against such attacks, an effective and popular approach, known as adversarial training (AT), has been shown to mitigate the negative impact of adversarial attacks by virtue of a min-max robust training method. While effective, it remains unclear whether it can successfully be adapted to the distributed learning context. The power of distributed optimization over multiple machines enables us to scale up robust training over large models and datasets. Spurred by that, we propose distributed adversarial training (DAT), a large-batch adversarial training framework implemented over multiple machines. We show that DAT is general, which supports training over labeled and unlabeled data, multiple types of attack generation methods, and gradient compression operations favored for distributed optimization. Theoretically, we provide, under standard conditions in the optimization theory, the convergence rate of DAT to the first-order stationary points in general non-convex settings. Empirically, we demonstrate that DAT either matches or outperforms state-of-the-art robust accuracies and achieves a graceful training speedup (e.g., on ResNet-50 under ImageNet). Codes are available at https://github.com/dat-2022/dat.
This paper is the first to propose a generic min-max bilevel multi-objective optimization framework, highlighting applications in representation learning and hyperparameter optimization. In many machine learning applications such as meta-learning, multi-task learning, and representation learning, a subset of the parameters are shared by all the tasks, while each specific task has its own set of additional parameters. By leveraging the recent advances of nonconvex min-max optimization, we propose a gradient descent-ascent bilevel optimization (MORBiT) algorithm which is able to extract a set of shared parameters that is robust over all tasks and further overcomes the distributional shift between training and testing tasks. Theoretical analyses show that MORBiT converges to the first-order stationary point at a rate of $\mathcal{O}(\sqrt{n}K^{-2/5})$ for a class of nonconvex problems, where $K$ denotes the total number of iterations and $n$ denotes the number of tasks. Overall, we formulate a min-max bilevel multi-objective optimization problem, provide a single loop two-timescale algorithm with convergence rate guarantees, and show theoretical bounds on the generalization abilities of the optimizer. Experimental results on sinusoid regression and representation learning showcase the superiority of MORBiT over state-of-the-art methods, validating our convergence and generalization results.
In this paper, we investigate the performance of a practical aggregated LiFi-WiFi system with the discrete constellation inputs from a practical view. We derive the achievable rate expressions of the aggregated LiFi-WiFi system for the first time. Then, we study the rate maximization problem via optimizing the constellation distribution and power allocation jointly. Specifically, a multilevel mercy-filling power allocation scheme is proposed by exploiting the relationship between the mutual information and minimum mean-squared error (MMSE) of discrete inputs. Meanwhile, an inexact gradient descent method is proposed for obtaining the optimal probability distributions. To strike a balance between the computational complexity and the transmission performance, we further develop a framework that maximizes the lower bound of the achievable rate where the optimal power allocation can be obtained in closed forms and the constellation distributions problem can be solved efficiently by Frank-Wolfe method. Extensive numerical results show that the optimized strategies are able to provide significant gains over the state-of-the-art schemes in terms of the achievable rate.