Graduated optimization is a global optimization technique that is used to minimize a multimodal nonconvex function by smoothing the objective function with noise and gradually refining the solution. This paper experimentally evaluates the performance of the explicit graduated optimization algorithm with an optimal noise scheduling derived from a previous study and discusses its limitations. The evaluation uses traditional benchmark functions and empirical loss functions for modern neural network architectures. In addition, this paper extends the implicit graduated optimization algorithm, which is based on the fact that stochastic noise in the optimization process of SGD implicitly smooths the objective function, to SGD with momentum, analyzes its convergence, and demonstrates its effectiveness through experiments on image classification tasks with ResNet architectures.
论文检索
输入标题、作者或关键词，从 1,712 篇学术成果中精准定位
In performative Reinforcement Learning (RL), an agent faces a policy-dependent environment: the reward and transition functions depend on the agent's policy. Prior work on performative RL has studied the convergence of repeated retraining approaches to a performatively stable policy. In the finite sample regime, these approaches repeatedly solve for a saddle point of a convex-concave objective, which estimates the Lagrangian of a regularized version of the reinforcement learning problem. In this paper, we aim to extend such repeated retraining approaches, enabling them to operate under corrupted data. More specifically, we consider Huber's ε-contamination model, where an ε fraction of data points is corrupted by arbitrary adversarial noise. We propose a repeated retraining approach based on convex-concave optimization under corrupted gradients and a novel problem-specific robust mean estimator for the gradients. We prove that our approach exhibits last-iterate convergence to an approximately stable policy, with the approximation error linear in √ε. We experimentally demonstrate the importance of accounting for corruption in performative reinforcement learning.
This work presents a novel approach to low-rank matrix factorization in a federated learning context, where multiple clients collaboratively solve a matrix decomposition problem without sharing their local data. The algorithm introduces a power initialization technique for the global factorization matrix and combines it with local gradient descent updates to achieve strong theoretical and practical guarantees. Considering this power initialization, we rewrite the previous smooth non-convex problem into a smooth strongly-convex problem that we solve using a parallel Nesterov gradient descent potentially requiring a single step of communication at the initialization step. We provide a linear rate of convergence of the excess loss, our results improve the rates of convergence given in the literature. We provide an upper bound on the Frobenius-norm error of reconstruction under the power initialization strategy. We complete our analysis with experiments on both synthetic and real data.
Federated learning is often used in environments with many unverified participants. Therefore, federated learning under adversarial attacks receives significant attention. This paper proposes an algorithmic framework for list-decodable federated learning, where a central server maintains a list of models, with at least one guaranteed to perform well. The framework has no strict restriction on the fraction of honest clients, extending the applicability of Byzantine federated learning to the scenario with more than half adversaries. Assuming the variance of gradient noise in stochastic gradient descent is bounded, we prove a convergence theorem of our method for strongly convex and smooth losses. Experimental results, including image classification tasks with both convex and non-convex losses, demonstrate that the proposed algorithm can withstand the malicious majority under various attacks.
Backward error analysis allows finding a modified loss function, which the parameter updates really follow under the influence of an optimization method. The additional loss terms included in this modified function is called implicit regularizer. In this paper, we attempt to find the implicit regularizer for various federated learning algorithms on non-IID data distribution, and explain why each method shows different convergence behavior. We first show that the implicit regularizer of FedAvg disperses the gradient of each client from the average gradient, thus increasing the gradient variance. We also empirically show that the implicit regularizer hampers its convergence. Similarly, we compute the implicit regularizers of FedSAM and SCAFFOLD, and explain why they converge better. While existing convergence analyses focus on pointing out the advantages of FedSAM and SCAFFOLD, our approach can explain their limitations in complex non-convex settings. In specific, we demonstrate that FedSAM can partially remove the bias in the first-order term of the implicit regularizer in FedAvg, whereas SCAFFOLD can fully eliminate the bias in the first-order term, but not in the second-order term. Consequently, the implicit regularizer can provide a useful insight on the convergence behavior of federated learning from a different theoretical perspective.
The convergence behavior of Stochastic Gradient Descent (SGD) crucially depends on the stepsize configuration. When using a constant stepsize, the SGD iterates form a Markov chain, enjoying fast convergence during the initial transient phase. However, when reaching stationarity, the iterates oscillate around the optimum without making further progress. In this paper, we study the convergence diagnostics for SGD with constant stepsize, aiming to develop an effective dynamic stepsize scheme. We propose a novel coupling-based convergence diagnostic procedure, which monitors the distance of two coupled SGD iterates for stationarity detection. Our diagnostic statistic is simple and is shown to track the transition from transience stationarity theoretically. We conduct extensive numerical experiments and compare our method against various existing approaches. Our proposed coupling-based stepsize scheme is observed to achieve superior performance across a diverse set of convex and non-convex problems. Moreover, our results demonstrate the robustness of our approach to a wide range of hyperparameters.
Stability and Generalization of Zeroth-Order Decentralized Stochastic Gradient Descent with Changing Topology
PDF ↗Zeroth-order (ZO) optimization as the gradient-free method has become a powerful tool when the first-order gradient is unavailable or expensive to obtain, especially in decentralized learning scenarios where data and computational resources are distributed across multiple clients. There have been many efforts to analyze the optimization convergence rate of zeroth-order decentralized stochastic gradient descent (ZO-DSGD) algorithms. However, the generalization of these methods has not been well studied. In this paper, we provide a generalization analysis of ZO-DSGD with changing topology, where the clients run zeroth-order SGD with local data and communicate with each other according to time-varying topology. We systematically analyze the generalization error in convex, strongly convex, and non-convex cases. The obtained results in the convex and strongly convex cases with zeroth-order oracles recover the results of SGD. Moreover, the generalization bounds derived in non-convex cases align with that of DSGD. To capture the influence of communication topology on the generalization performance, we analyze local generalization bounds concerning local models held at different clients. The obtained results reflect the influence of the number of clients, local sample size, and topology on the generalization error. To the best of our knowledge, this is the first work that provides a generalization analysis of zeroth-order decentralized stochastic gradient descent methods and recovers the results of SGD.
In this study, we consider an optimization problem with uncertainty dependent on decision variables, which has recently attracted attention due to its importance in machine learning and pricing applications. In this problem, the gradient of the objective function cannot be obtained explicitly because the decision-dependent distribution is unknown. Therefore, several zeroth-order methods have been proposed, which obtain noisy objective values by sampling and update the iterates. Although these existing methods have theoretical convergence for optimization problems with decision-dependent uncertainty, they require strong assumptions about the function and distribution or exhibit large variances in their gradient estimators. To overcome these issues, we propose two zeroth-order methods under mild assumptions. First, we develop a zeroth-order method with a new one-point gradient estimator including a variance reduction parameter. The proposed method updates the decision variables while adjusting the variance reduction parameter. Second, we develop a zeroth-order method with a two-point gradient estimator. There are situations where only one-point estimators can be used, but if both one-point and two-point estimators are available, it is more practical to use the two-point estimator. As theoretical results, we show the convergence of our methods to stationary points and provide the worst-case iteration and sample complexity analysis. Our simulation experiments with real data on a retail service application show that our methods output solutions with lower objective values than the conventional zeroth-order methods.
Designing Ambiguity Sets for Distributionally Robust Optimization Using Structural Causal Optimal Transport
PDF ↗Distributionally robust optimization tackles out-of-sample issues like overfitting and distribution shifts by adopting an adversarial approach over a range of possible data distributions, known as the ambiguity set. To balance conservatism and accuracy, these sets must include realistic probability distributions by leveraging information from the nominal distribution. Assuming that nominal distributions arise from a structural causal model with a directed acyclic graph G and structural equations, previous methods such as adapted and G-causal optimal transport have only utilized causal graph information in designing ambiguity sets. In this work, we propose incorporating structural equations, which include causal graph information, to enhance ambiguity sets, resulting in more realistic distributions. We introduce structural causal optimal transport and its associated ambiguity set, demonstrating their advantages and connections to previous methods. A key benefit of our approach is a relaxed version, where a regularization term replaces the complex causal constraints, enabling an efficient algorithm via difference-of-convex programming to solve structural causal optimal transport. We also show that when structural information is absent and must be estimated, our approach remains effective and provides finite sample guarantees. Lastly, we address the radius of ambiguity sets, illustrating how our method overcomes the curse of dimensionality in optimal transport problems, achieving faster shrinkage with dimension-free order.
Error Analysis Affected by Heavy-Tailed Gradients for Non-Convex Pairwise Stochastic Gradient Descent
PDF ↗In recent years, there have been a growing number of works studying the generalization properties of stochastic gradient descent (SGD) from the perspective of algorithmic stability. However, few of them devote to simultaneously studying the generalization and optimization for the non-convex setting, especially pairwise SGD with heavy-tailed gradient noise. This paper considers the impact of the heavy-tailed gradient noise obeying sub-Weibull distribution on the stability-based learning guarantees for non-convex pairwise SGD by investigating its generalization and optimization jointly. Specifically, based on two novel pairwise uniform model stability tools, we firstly bound the generalization error of pairwise SGD in the general non-convex setting after bridging the quantitative relationships between stability and generalization error. Then, we further consider the practical heavy-tailed sub-Weibull gradient noise condition to establish a refined generalization bound without the bounded gradient condition. Finally, sharper error bounds for generalization and optimization are built by introducing the gradient dominance condition. Comparing these results reveals that sub-Weibull gradient noise brings some positive dependencies on the heavy-tailed strength for generalization and optimization. Furthermore, we extend our analysis to the corresponding pairwise minibatch SGD and derive the first stability-based near-optimal generalization and optimization bounds which are consistent with many empirical observations.
Accelerated Methods with Compressed Communications for Distributed Optimization Problems Under Data Similarity
PDF ↗In recent years, as data and problem sizes have increased, distributed learning has become an essential tool for training high-performance models. However, the communication bottleneck, especially for high-dimensional data, is a challenge. Several techniques have been developed to overcome this problem. These include communication compression and implementation of local steps, which work particularly well when there is similarity of local data samples. In this paper, we study the synergy of these approaches for efficient distributed optimization. We propose the first theoretically grounded accelerated algorithms utilizing unbiased and biased compression under data similarity, leveraging variance reduction and error feedback frameworks. In terms of communication time our theory gives ?(1+[M^(-¼)+?^(-½)]√(? /?)) complexity for unbiased compressors and ?(1+β^(¼)√(? /?)) for biased ones, where M is the number of computational nodes, β is the compression power, ? is the similarity measure and ? is the parameter of strong convexity of the objective. Our theoretical results are of record and confirmed by experiments on different average losses and datasets.
We present a significant advancement in the field of Langevin Monte Carlo (LMC) methods by introducing the Inexact Proximal Langevin Algorithm (IPLA). This novel algorithm broadens the scope of problems that LMC can effectively address while maintaining controlled computational costs. IPLA extends LMC's applicability to potentials that are convex, strongly convex in the tails, and exhibit polynomial growth, beyond the conventional L-smoothness assumption. Moreover, we extend LMC's applicability to super-quadratic potentials and offer improved convergence rates over existing algorithms. Additionally, we provide bounds on all moments of the Markov chain generated by IPLA, enhancing its analytical robustness.
EFSkip: A New Error Feedback with Linear Speedup for Compressed Federated Learning with Arbitrary Data Heterogeneity
PDF ↗Due to the communication bottleneck in distributed and decentralized federated learning applications, algorithms using compressed communication have attracted significant attention. The Error Feedback (EF) is a widely-studied compression framework for convergence with biased compressors such as top-k sparsification. Although various improvements have been obtained in recent years, the theoretical guarantee for EF-type framework is still limited. Previous works either 1) rely on strong assumptions such as bounded gradient/dissimilarity assumptions, thus can not deal with arbitrary data heterogeneity and also slow the convergence speed, or 2) can not enjoy linear speedup in the number of clients. In this work, we propose a new EFSkip framework which removes the strong assumptions to allow arbitrary data heterogeneity and enjoys linear speedup for significantly improving upon previous results. In particular, EFSkip achieves a substantially lower computational complexity compared to the previous EF21, i.e., EFSkip enjoys the linear speedup in the number of clients (reducing the result linearly using more clients). We also show that EFSkip enjoys linear speedup and achieves faster convergence for nonconvex problems satisfying Polyak-Lojasiewicz (PL) condition. We believe that the new EFSkip framework will have a large impact on the communication- and computation-efficient distributed and decentralized federated learning.
The independence assumption between random variables is a useful tool to increase the tractability of a modelling framework. However, this assumption can be too simplistic; failing to take dependencies into account can cause models to fail dramatically. The field of multi-axis graphical modelling (also called multi-way modelling, Kronecker-separable modelling) has seen growth over the past decade, but these models require that the data have zero mean. In the multi-axis case, inference is typically done in the single sample scenario, making mean inference impossible. In this paper, we demonstrate how the zero-mean assumption can cause egregious modelling errors for Kronecker-sum-decomposable Gaussian graphical models, as well as propose a relaxation to the zero-mean assumption that allows the avoidance of such errors. Specifically, we propose the "Kronecker-sum-structured mean" assumption, which leads to models with nonconvex-but-unimodal log-likelihoods that can be solved efficiently with coordinate descent.
Metric magnitude of a point cloud is a measure of its ``size." It has been adapted to various mathematical contexts and recent work suggests that it can enhance machine learning and optimization algorithms. But its usability is limited due to the computational cost when the dataset is large or when the computation must be carried out repeatedly (e.g. in model training). In this paper, we study the magnitude computation problem, and show efficient ways of approximating it. We show that it can be cast as a convex optimization problem, but not as a submodular optimization. The paper describes two new algorithms -- an iterative approximation algorithm that converges fast and is accurate in practice, and a subset selection method that makes the computation even faster. It has previously been proposed that the magnitude of model sequences generated during stochastic gradient descent is correlated to the generalization gap. Extension of this result using our more scalable algorithms shows that longer sequences bear higher correlations. We also describe new applications of magnitude in machine learning -- as an effective regularizer for neural network training, and as a novel clustering criterion.
We present theory of synaptic neural balance and we show experimentally that synaptic neural balance can improve deep learning speed, and accuracy, even in data-scarce environments. Given an additive cost function (regularizer) of the synaptic weights, a neuron is said to be in balance if the total cost of its incoming weights is equal to the total cost of its outgoing weights. For large classes of networks, activation functions, and regularizers, neurons can be balanced fully or partially using scaling operations that do not change their functionality. Furthermore, these balancing operations are associated with a strictly convex optimization problem with a single optimum and can be carried out in any order. In our simulations, we systematically observe that: (1) Fully balancing before training results in better performance as compared to several other training approaches; (2) Interleaving partial (layer-wise) balancing and stochastic gradient descent steps during training results in faster learning convergence and better overall accuracy (with L1 balancing converging faster than L2 balancing); and (3) When given limited training data, neural balanced models outperform plain or regularized models; and this is observed in both feedforward and recurrent networks. In short, the evidence supports that neural balancing operations could be added to the arsenal of methods used to regularize and train neural networks. Furthermore, balancing operations are entirely local and can be carried out asynchronously, making them plausible for biological or neuromorphic systems.
Collaborative machine learning (CML) provides a promising paradigm for democratizing advanced technologies by enabling cost-sharing among participants. However, the potential for rent-seeking behaviors among parties can undermine such collaborations. Contract theory presents a viable solution by rewarding participants with models of varying accuracy based on their contributions. However, unlike monetary compensation, using models as rewards introduces unique challenges, particularly due to the stochastic nature of these rewards when contribution costs are privately held information. This paper formalizes the optimal contracting problem within CML and proposes a transformation that simplifies the non-convex optimization problem into one that can be solved through convex optimization algorithms. We conduct a detailed analysis of the properties that an optimal contract must satisfy when models serve as the rewards, and we explore the potential benefits and welfare implications of these contract-driven CML schemes through numerical experiments.
Tâtonnement is a simple, intuitive market process where prices are iteratively adjusted based on the difference between demand and supply. Many variants under different market assumptions have been studied and shown to converge to a market equilibrium, in some cases at a fast rate. However, the classical case of linear Fisher markets have long eluded the analyses, and it remains unclear whether tâtonnement converges in this case. We show that, for a sufficiently small stepsize, the prices given by the tâtonnement process are guaranteed to converge to equilibrium prices, up to a small approximation radius that depends on the stepsize. To achieve this, we consider the dual Eisenberg-Gale convex program in the price space, view tâtonnement as subgradient descent on this convex program, and utilize novel last-iterate convergence results for subgradient descent under error bound conditions. In doing so, we show that the convex program satisfies a particular error bound condition, the quadratic growth condition, and that the price sequence generated by tâtonnement is bounded above and away from zero. We also show that a similar convergence result holds for tâtonnement in quasi-linear Fisher markets. Numerical experiments are conducted to demonstrate that the theoretical linear convergence aligns with empirical observations.
To model complex real-world systems, such as traders in stock markets, or the dissemination of contagious diseases, graphon mean-field games (GMFG) have been proposed to model many agents. Despite the empirical success, our understanding of GMFG is limited. Popular algorithms such as mirror descent are deployed but remain unknown for their convergence properties. In this work, we give the first last-iterate convergence rate of mirror descent in regularized monotone GMFG. In tabular monotone GMFG with finite state and action spaces and under bandit feedback, we show a last-iterate convergence rate of O(T^{-1/4}). Moreover, when exact knowledge of costs and transitions is available, we improve this convergence rate to O(T^{-1}), matching the existing convergence rate observed in strongly convex games. In linear GMFG, our algorithm achieves a last-iterate convergence rate of O(T^{-1/5}). Finally, we verify the performance of the studied algorithms by empirically testing them against fictitious play in a variety of tasks.
Given an unweighted, undirected, and simple graph, the Densest k-Subgraph (DkS) problem aims to find a subgraph of k vertices that has the maximum average induced degree. In this paper, we consider an equivalent reformulation of the DkS problem via diagonal loading. On relaxing the combinatorial constraint of the reformulated problem, we show that the resulting non-convex, continuous relaxation is tight under certain conditions by leveraging an extension of the Motzkin-Straus theorem. We utilize two projection-free approaches to solve the relaxed problem: one based on the Frank-Wolfe algorithm and the other on explicit constraint parameterization. We compare their performance to state-of-the-art baselines across various benchmarks. Our empirical results show that the Frank-Wolfe-based algorithm proposed in this paper outperforms existing baselines in terms of subgraph density and computational complexity.