Pairwise learning refers to learning tasks where the loss function depends on a pair of instances. It instantiates many important machine learning tasks such as bipartite ranking and metric learning. A popular approach to handle streaming data in pairwise learning is an online gradient descent (OGD) algorithm, where one needs to pair the current instance with a buffering set of previous instances with a sufficiently large size and therefore suffers from a scalability issue. In this paper, we propose simple stochastic and online gradient descent methods for pairwise learning. A notable difference from the existing studies is that we only pair the current instance with the previous one in building a gradient direction, which is efficient in both the storage and computational complexity. We develop novel stability results, optimization, and generalization error bounds for both convex and nonconvex as well as both smooth and nonsmooth problems. We introduce novel techniques to decouple the dependency of models and the previous instance in both the optimization and generalization analysis. Our study resolves an open question on developing meaningful generalization bounds for OGD using a buffering set with a very small fixed size. We also extend our algorithms and stability analysis to develop differentially private SGD algorithms for pairwise learning which significantly improves the existing results.
In this extended abstract, we will present and discuss opportunities and challenges brought about by a new deep learning method by AUC maximization (aka \underline{\bf D}eep \underline{\bf A}UC \underline{\bf M}aximization or {\bf DAM}) for medical image classification. Since AUC (aka area under ROC curve) is a standard performance measure for medical image classification, hence directly optimizing AUC could achieve a better performance for learning a deep neural network than minimizing a traditional loss function (e.g., cross-entropy loss). Recently, there emerges a trend of using deep AUC maximization for large-scale medical image classification. In this paper, we will discuss these recent results by highlighting (i) the advancements brought by stochastic non-convex optimization algorithms for DAM; (ii) the promising results on various medical image classification problems. Then, we will discuss challenges and opportunities of DAM for medical image classification from three perspectives, feature learning, large-scale optimization, and learning trustworthy AI models.
In this paper, we study stochastic optimization of areas under precision-recall curves (AUPRC), which is widely used for combating imbalanced classification tasks. Although a few methods have been proposed for maximizing AUPRC, stochastic optimization of AUPRC with convergence guarantee remains an undeveloped territory. A recent work [42] has proposed a promising approach towards AUPRC based on maximizing a surrogate loss for the average precision, and proved an $O(1/\epsilon^5)$ complexity for finding an $\epsilon$-stationary solution of the non-convex objective. In this paper, we further improve the stochastic optimization of AURPC by (i) developing novel stochastic momentum methods with a better iteration complexity of $O(1/\epsilon^4)$ for finding an $\epsilon$-stationary solution; and (ii) designing a novel family of stochastic adaptive methods with the same iteration complexity of $O(1/\epsilon^4)$, which enjoy faster convergence in practice. To this end, we propose two innovative techniques that are critical for improving the convergence: (i) the biased estimators for tracking individual ranking scores are updated in a randomized coordinate-wise manner; and (ii) a momentum update is used on top of the stochastic gradient estimator for tracking the gradient of the objective. Extensive experiments on various data sets demonstrate the effectiveness of the proposed algorithms. Of independent interest, the proposed stochastic momentum and adaptive algorithms are also applicable to a class of two-level stochastic dependent compositional optimization problems.
Recently, model-agnostic meta-learning (MAML) has garnered tremendous attention. However, stochastic optimization of MAML is still immature. Existing algorithms for MAML are based on the ``episode" idea by sampling a number of tasks and a number of data points for each sampled task at each iteration for updating the meta-model. However, they either do not necessarily guarantee convergence with a constant mini-batch size or require processing a larger number of tasks at every iteration, which is not viable for continual learning or cross-device federated learning where only a small number of tasks are available per-iteration or per-round. This paper addresses these issues by (i) proposing efficient memory-based stochastic algorithms for MAML with a diminishing convergence error, which only requires sampling a constant number of tasks and a constant number of examples per-task per-iteration; (ii) proposing communication-efficient distributed memory-based MAML algorithms for personalized federated learning in both the cross-device (w/ client sampling) and the cross-silo (w/o client sampling) settings. The key novelty of the proposed algorithms is to maintain an individual personalized model (aka memory) for each task besides the meta-model and only update them for the sampled tasks by a momentum method that incorporates historical updates at each iteration. The theoretical results significantly improve the optimization theory for MAML and the empirical results also corroborate the theory.
Recently, several universal methods have been proposed for online convex optimization, and attain minimax rates for multiple types of convex functions simultaneously. However, they need to design and optimize one surrogate loss for each type of functions, which makes it difficult to exploit the structure of the problem and utilize the vast amount of existing algorithms. In this paper, we propose a simple strategy for universal online convex optimization, which avoids these limitations. The key idea is to construct a set of experts to process the original online functions, and deploy a meta-algorithm over the \emph{linearized} losses to aggregate predictions from experts. Specifically, we choose Adapt-ML-Prod to track the best expert, because it has a second-order bound and can be used to leverage strong convexity and exponential concavity. In this way, we can plug in off-the-shelf online solvers as black-box experts to deliver problem-dependent regret bounds. Furthermore, our strategy inherits the theoretical guarantee of any expert designed for strongly convex functions and exponentially concave functions, up to a double logarithmic factor. For general convex functions, it maintains the minimax optimality and also achieves a small-loss bound.
Many machine learning problems can be formulated as minimax problems such as Generative Adversarial Networks (GANs), AUC maximization and robust estimation, to mention but a few. A substantial amount of studies are devoted to studying the convergence behavior of their stochastic gradient-type algorithms. In contrast, there is relatively little work on their generalization, i.e., how the learning models built from training examples would behave on test examples. In this paper, we provide a comprehensive generalization analysis of stochastic gradient methods for minimax problems under both convex-concave and nonconvex-nonconcave cases through the lens of algorithmic stability. We establish a quantitative connection between stability and several generalization measures both in expectation and with high probability. For the convex-concave setting, our stability analysis shows that stochastic gradient descent ascent attains optimal generalization bounds for both smooth and nonsmooth minimax problems. We also establish generalization bounds for both weakly-convex-weakly-concave and gradient-dominated problems.
In this paper, we consider non-convex stochastic bilevel optimization (SBO) problems that have many applications in machine learning. Although numerous studies have proposed stochastic algorithms for solving these problems, they are limited in two perspectives: (i) their sample complexities are high, which do not match the state-of-the-art result for non-convex stochastic optimization; (ii) their algorithms are tailored to problems with only one lower-level problem. When there are many lower-level problems, it could be prohibitive to process all these lower-level problems at each iteration. To address these limitations, this paper proposes fast randomized stochastic algorithms for non-convex SBO problems. First, we present a stochastic method for non-convex SBO with only one lower problem and establish its sample complexity of $O(1/\epsilon^3)$ for finding an $\epsilon$-stationary point under appropriate conditions, matching the lower bound for stochastic smooth non-convex optimization. Second, we present a randomized stochastic method for non-convex SBO with $m>1$ lower level problems by processing only one lower problem at each iteration, and establish its sample complexity no worse than $O(m/\epsilon^3)$, which could have a better complexity than simply processing all $m$ lower problems at each iteration. To the best of our knowledge, this is the first work considering SBO with many lower level problems and establishing state-of-the-art sample complexity.
In this paper, we demonstrate the power of a widely used stochastic estimator based on moving average (SEMA) on a range of stochastic non-convex optimization problems, which only requires {\bf a general unbiased stochastic oracle}. We analyze various stochastic methods (existing or newly proposed) based on the {\bf variance recursion property} of SEMA for three families of non-convex optimization, namely standard stochastic non-convex minimization, stochastic non-convex strongly-concave min-max optimization, and stochastic bilevel optimization. Our contributions include: (i) for standard stochastic non-convex minimization, we present a simple and intuitive proof of convergence for a family Adam-style methods (including Adam) with an increasing or large "momentum" parameter for the first-order moment, which gives an alternative yet more natural way to guarantee Adam converge; (ii) for stochastic non-convex strongly-concave min-max optimization, we present a single-loop stochastic gradient descent ascent method based on the moving average estimators and establish its oracle complexity of $O(1/\epsilon^4)$ without using a large mini-batch size, addressing a gap in the literature; (iii) for stochastic bilevel optimization, we present a single-loop stochastic method based on the moving average estimators and establish its oracle complexity of $\widetilde O(1/\epsilon^4)$ without computing the inverse or SVD of the Hessian matrix, improving state-of-the-art results. For all these problems, we also establish a variance diminishing result for the used stochastic gradient estimators.
Areas under ROC (AUROC) and precision-recall curves (AUPRC) are common metrics for evaluating classification performance for imbalanced problems. Compared with AUROC, AUPRC is a more appropriate metric for highly imbalanced datasets. While direct optimization of AUROC has been studied extensively, optimization of AUPRC has been rarely explored. In this work, we propose a principled technical method to optimize AUPRC for deep learning. Our approach is based on maximizing the averaged precision (AP), which is an unbiased point estimator of AUPRC. We show that the surrogate loss function for AP is highly non-convex and more complicated than that of AUROC. We cast the objective into a sum of dependent compositional functions with inner functions dependent on random variables of the outer level. We propose efficient adaptive and non-adaptive stochastic algorithms with provable convergence guarantee under mild conditions by using recent advances in stochastic compositional optimization. Extensive experimental results on graphs and image datasets demonstrate that our proposed method outperforms prior methods on imbalanced problems. To the best of our knowledge, our work represents the first attempt to optimize AUPRC with provable convergence.