Many well-known first-order gradient methods have been extended to cope with large-scale composite problems, which often arise as a regularized empirical risk minimization in machine learning. However, their optimal convergence is attained only in terms of the weighted average of past iterative solutions. How to make the individual convergence of stochastic gradient descent (SGD) optimal, especially for strongly convex problems has now become a challenging problem in the machine learning community. On the other hand, Nesterov's recent weighted averaging strategy succeeds in achieving the optimal individual convergence of dual averaging (DA) but it fails in the basic mirror descent (MD). In this paper, a new primal averaging (PA) gradient operation step is presented, in which the gradient evaluation is imposed on the weighted average of all past iterative solutions. We prove that simply modifying the gradient operation step in MD by PA strategy suffices to recover the optimal individual rate for general convex problems. Along this line, the optimal individual rate of convergence for strongly convex problems can also be achieved by imposing the strong convexity on the gradient operation step. Furthermore, we extend PA-MD to solve regularized nonsmooth learning problems in the stochastic setting, which reveals that PA strategy is a simple yet effective extra step toward the optimal individual convergence of SGD. Several real experiments on sparse learning and SVM problems verify the correctness of our theoretical analysis.

The extrapolation strategy raised by Nesterov, which can accelerate the convergence rate of gradient descent methods by orders of magnitude when dealing with smooth convex objective, has led to tremendous success in training machine learning tasks. In this article, the convergence of individual iterates of projected subgradient (PSG) methods for nonsmooth convex optimization problems is theoretically studied based on Nesterov's extrapolation, which we name individual convergence. We prove that Nesterov's extrapolation has the strength to make the individual convergence of PSG optimal for nonsmooth problems. In light of this consideration, a direct modification of the subgradient evaluation suffices to achieve optimal individual convergence for strongly convex problems, which can be regarded as making an interesting step toward the open question about stochastic gradient descent (SGD) posed by Shamir. Furthermore, we give an extension of the derived algorithms to solve regularized learning tasks with nonsmooth losses in stochastic settings. Compared with other state-of-the-art nonsmooth methods, the derived algorithms can serve as an alternative to the basic SGD especially in coping with machine learning problems, where an individual output is needed to guarantee the regularization structure while keeping an optimal rate of convergence. Typically, our method is applicable as an efficient tool for solving large-scale l₁-regularized hinge-loss learning problems. Several comparison experiments demonstrate that our individual output not only achieves an optimal convergence rate but also guarantees better sparsity than the averaged solution.

Tea disease detection is crucial for improving the agricultural circular economy. Deep learning-based methods have been widely applied to this task, and the main idea of these methods is to extract multiscale coarse features of diseases using the backbone network and fuse these features through the neck for accurate disease detection. This paper proposes a novel tea disease detection method that enhances feature expression of the backbone network and the feature fusion capability of the neck: (1) constructing an inverted residual self-attention module as a backbone plugin to capture the long-distance dependencies of disease spots on the leaves; and (2) developing a channel–spatial attention module with residual connection in the neck network to enhance the contextual semantic information of fused features in disease images and eliminate complex background noise. For the second step, the proposed channel–spatial attention module uses Residual Channel Attention (RCA) to enhance inter-channel interactions, facilitating discrimination between disease spots and normal leaf regions, and employs spatial attention (SA) to enhance essential areas of tea diseases. Experimental results demonstrate that the proposed method achieved accuracy and mAP scores of 92.9% and 94.6%, respectively. In particular, this method demonstrated improvements of 6.4% in accuracy and 6.2% in mAP compared to the SSD model.

The truncated regular L₁-loss support vector machine can eliminate the excessive number of support vectors (SVs); thus, it has significant advantages in robustness and scalability. However, in this paper, we discover that the associated state-of-the-art solvers, such as difference convex algorithm and concave-convex procedure, not only have limited sparsity promoting property for general truncated losses especially the L₂-loss but also have poor scalability for large-scale problems. To circumvent these drawbacks, we present a general multistage scheme with explicit interpretation regarding SVs as well as outliers. In particular, we solve the general nonconvex truncated loss minimization through a sequence of associated convex subproblems, in which the outliers are removed in advance. The proposed algorithm can be regarded as a structural optimization attempt carefully considering sparsity imposed by the nonconvex truncated losses. We show that this general multistage algorithm offers sufficient sparsity especially for the truncated L₂-loss. To further improve the scalability, we propose a linear multistep algorithm by employing a single iteration of coordinate descent to monotonically decrease the objective function at each stage and a kernel algorithm by using the Karush-Kuhn-Tucker conditions to cheaply find most part of the outliers for the next stage. Comparison experiments demonstrate that our methods have superiority in sparsity as well as efficiency in scalability.

Learning adversarial examples can be formulated as an optimization problem of maximizing the loss function with some box-constraints. However, for solving this induced optimization problem, the state-of-the-art gradient-based methods such as FGSM, I-FGSM and MI-FGSM look different from their original methods especially in updating the direction, which makes it difficult to understand them and then leaves some theoretical issues to be addressed in viewpoint of optimization. In this paper, from the perspective of adapting step-size, we provide a unified theoretical interpretation of these gradient-based adversarial learning methods. We show that each of these algorithms is in fact a specific reformulation of their original gradient methods but using the step-size rules with only current gradient information. Motivated by such analysis, we present a broad class of adaptive gradient-based algorithms based on the regular gradient methods, in which the step-size strategy utilizing information of the accumulated gradients is integrated. Such adaptive step-size strategies directly normalize the scale of the gradients rather than use some empirical operations. The important benefit is that convergence for the iterative algorithms is guaranteed and then the whole optimization process can be stabilized. The experiments demonstrate that our AdaI-FGM consistently outperforms I-FGSM and AdaMI-FGM remains competitive with MI-FGSM for black-box attacks.