All issues

Recently, saddle point problems have received much attention due to their powerful modeling capability for a lot of problems from diverse domains. Applications of these problems occur in many applied areas, such as robust optimization, distributed optimization, game theory, and many applications in machine learning such as empirical risk minimization and generative adversarial networks training. Therefore, many researchers have actively worked on developing numerical methods for solving saddle point problems in many different settings. This paper is devoted to developing a numerical method for solving saddle point problems in the nonconvex uniformly-concave setting. We study a general class of saddle point problems with composite structure and H\"older-continuous higher-order derivatives. To solve the problem under consideration, we propose an approach in which we reduce the problem to a combination of two auxiliary optimization problems separately for each group of variables, the outer minimization problem w.r.t. primal variables, and the inner maximization problem w.r.t the dual variables. For solving the outer minimization problem, we use the Adaptive Gradient Method, which is applicable for nonconvex problems and also works with an inexact oracle that is generated by approximately solving the inner problem. For solving the inner maximization problem, we use the Restarted Unified Acceleration Framework, which is a framework that unifies the high-order acceleration methods for minimizing a convex function that has H\"older-continuous higher-order derivatives. Separate complexity bounds are provided for the number of calls to the first-order oracles for the outer minimization problem and higher-order oracles for the inner maximization problem. Moreover, the complexity of the whole proposed approach is then estimated.

This paper presents the results of experimental validation of some structural issues concerning the practical use of methods to overcome catastrophic forgetting of neural networks. A comparison of current effective methods like EWC (Elastic Weight Consolidation) and WVA (Weight Velocity Attenuation) is made and their advantages and disadvantages are considered. It is shown that EWC is better for tasks where full retention of learned skills is required on all the tasks in the training queue, while WVA is more suitable for sequential tasks with very limited computational resources, or when reuse of representations and acceleration of learning from task to task is required rather than exact retention of the skills. The attenuation of the WVA method must be applied to the optimization step, i. e. to the increments of neural network weights, rather than to the loss function gradient itself, and this is true for any gradient optimization method except the simplest stochastic gradient descent (SGD). The choice of the optimal weights attenuation function between the hyperbolic function and the exponent is considered. It is shown that hyperbolic attenuation is preferable because, despite comparable quality at optimal values of the hyperparameter of the WVA method, it is more robust to hyperparameter deviations from the optimal value (this hyperparameter in the WVA method provides a balance between preservation of old skills and learning a new skill). Empirical observations are presented that support the hypothesis that the optimal value of this hyperparameter does not depend on the number of tasks in the sequential learning queue. And, consequently, this hyperparameter can be picked up on a small number of tasks and used on longer sequences.

In today’s technology-driven world, lite devices like Internet of Things (IoT) devices and microcontrollers (MCUs) are becoming increasingly common. These devices are more energyefficient and affordable, often with reduced features compared to the standard versions such as very limited memory and processing power for typical machine learning models. However, modern machine learning models can have millions of parameters, resulting in a large memory footprint. This complexity not only makes it difficult to deploy these large models on resource constrained devices but also increases the risk of latency and inefficiency in processing, which is crucial in some cases where real-time responses are required such as autonomous driving and medical diagnostics. In recent years, neural networks have seen significant advancements in model optimization techniques that help deployment and inference on these small devices. This narrative review offers a thorough examination of the progression and latest developments in neural network optimization, focusing on key areas such as quantization, pruning, knowledge distillation, and neural architecture search. It examines how these algorithmic solutions have progressed and how new approaches have improved upon the existing techniques making neural networks more efficient. This review is designed for machine learning researchers, practitioners, and engineers who may be unfamiliar with these methods but wish to explore the available techniques. It highlights ongoing research in optimizing networks for achieving better performance, lowering energy consumption, and enabling faster training times, all of which play an important role in the continued scalability of neural networks. Additionally, it identifies gaps in current research and provides a foundation for future studies, aiming to enhance the applicability and effectiveness of existing optimization strategies.

Considered the application of physics-informed neural networks using multi layer perceptrons to solve Cauchy initial value problems in which the right-hand sides of the equation are continuous monotonically increasing, decreasing or oscillating functions. With the use of the computational experiments the influence of the construction of the approximate neural network solution, neural network structure, optimization algorithm and software implementation means on the learning process and the accuracy of the obtained solution is studied. The analysis of the efficiency of the most frequently used machine learning frameworks in software development with the programming languages Python and C# is carried out. It is shown that the use of C# language allows to reduce the time of neural networks training by 20–40%. The choice of different activation functions affects the learning process and the accuracy of the approximate solution. The most effective functions in the considered problems are sigmoid and hyperbolic tangent. The minimum of the loss function is achieved at the certain number of neurons of the hidden layer of a single-layer neural network for a fixed training time of the neural network model. It’s also mentioned that the complication of the network structure increasing the number of neurons does not improve the training results. At the same time, the size of the grid step between the points of the training sample, providing a minimum of the loss function, is almost the same for the considered Cauchy problems. Training single-layer neural networks, the Adam method and its modifications are the most effective to solve the optimization problems. Additionally, the application of twoand three-layer neural networks is considered. It is shown that in these cases it is reasonable to use the LBFGS algorithm, which, in comparison with the Adam method, in some cases requires much shorter training time achieving the same solution accuracy. The specificity of neural network training for Cauchy problems in which the solution is an oscillating function with monotonically decreasing amplitude is also investigated. For these problems, it is necessary to construct a neural network solution with variable weight coefficient rather than with constant one, which improves the solution in the grid cells located near by the end point of the solution interval.

Stochastic optimization is a current area of research due to significant advances in machine learning and their applications to everyday problems. In this paper, we consider two fundamentally different methods for solving the problem of stochastic optimization — online and offline algorithms. The corresponding algorithms have their qualitative advantages over each other. So, for offline algorithms, it is required to solve an auxiliary problem with high accuracy. However, this can be done in a distributed manner, and this opens up fundamental possibilities such as, for example, the construction of a dual problem. Despite this, both online and offline algorithms pursue a common goal — solving the stochastic optimization problem with a given accuracy. This is reflected in the comparison of the computational complexity of the described algorithms, which is demonstrated in this paper.

The comparison of the described methods is carried out for two types of stochastic problems — convex optimization and saddles. For problems of stochastic convex optimization, the existing solutions make it possible to compare online and offline algorithms in some detail. In particular, for strongly convex problems, the computational complexity of the algorithms is the same, and the condition of strong convexity can be weakened to the condition of $\gamma$-growth of the objective function. From this point of view, saddle point problems are much less studied. Nevertheless, existing solutions allow us to outline the main directions of research. Thus, significant progress has been made for bilinear saddle point problems using online algorithms. Offline algorithms are represented by just one study. In this paper, this example demonstrates the similarity of both algorithms with convex optimization. The issue of the accuracy of solving the auxiliary problem for saddles was also worked out. On the other hand, the saddle point problem of stochastic optimization generalizes the convex one, that is, it is its logical continuation. This is manifested in the fact that existing results from convex optimization can be transferred to saddles. In this paper, such a transfer is carried out for the results of the online algorithm in the convex case, when the objective function satisfies the $\gamma$-growth condition.

Industrial imaging or “machine vision” is currently a key technology in many industries as it can be used to optimize various processes. The purpose of this work is to create a software and hardware complex for measuring the overall and weight characteristics of cargo based on an intelligent system using neural network identification methods that allow one to overcome the technological limitations of similar complexes implemented on ultrasonic and infrared measuring sensors. The complex to be developed will measure cargo without restrictions on the volume and weight characteristics of cargo to be tariffed and sorted within the framework of the warehouse complexes. The system will include an intelligent computer program that determines the volume and weight characteristics of cargo using the machine vision technology and an experimental sample of the stand for measuring the volume and weight of cargo.

We analyzed the solutions to similar problems. We noted that the disadvantages of the studied methods are very high requirements for the location of the camera, as well as the need for manual operations when calculating the dimensions, which cannot be automated without significant modifications. In the course of the work, we investigated various methods of object recognition in images to carry out subject filtering by the presence of cargo and measure its overall dimensions. We obtained satisfactory results when using cameras that combine both an optical method of image capture and infrared sensors. As a result of the work, we developed a computer program allowing one to capture a continuous stream from Intel RealSense video cameras with subsequent extraction of a three-dimensional object from the designated area and to calculate the overall dimensions of the object. At this stage, we analyzed computer vision techniques; developed an algorithm to implement the task of automatic measurement of goods using special cameras and the software allowing one to obtain the overall dimensions of objects in automatic mode.

Upon completion of the work, this development can be used as a ready-made solution for transport companies, logistics centers, warehouses of large industrial and commercial enterprises.

The fast-paced environment of DevSecOps requires integrating security at every stage of software development to ensure secure, compliant applications. Traditional methods of security testing, often performed late in the development cycle, are insufficient to address the unique challenges of continuous integration and continuous deployment (CI/CD) pipelines, particularly in complex, high-stakes sectors such as industrial automation. In this paper, we propose an approach that automates the analysis and testing of security requirements by embedding requirements verification into the CI/CD pipeline. Our method employs the ARQAN tool to map high-level security requirements to Security Technical Implementation Guides (STIGs) using semantic search, and RQCODE to formalize these requirements as code, providing testable and enforceable security guidelines.We implemented ARQAN and RQCODE within a CI/CD framework, integrating them with GitHub Actions for realtime security checks and automated compliance verification. Our approach supports established security standards like IEC 62443 and automates security assessment starting from the planning phase, enhancing the traceability and consistency of security practices throughout the pipeline. Evaluation of this approach in collaboration with an industrial automation company shows that it effectively covers critical security requirements, achieving automated compliance for 66.15% of STIG guidelines relevant to the Windows 10 platform. Feedback from industry practitioners further underscores its practicality, as 85% of security requirements mapped to concrete STIG recommendations, with 62% of these requirements having matching testable implementations in RQCODE. This evaluation highlights the approach’s potential to shift security validation earlier in the development process, contributing to a more resilient and secure DevSecOps lifecycle.

Distributed saddle point problems (SPPs) have numerous applications in optimization, matrix games and machine learning. For example, the training of generated adversarial networks is represented as a min-max optimization problem, and training regularized linear models can be reformulated as an SPP as well. This paper studies distributed nonsmooth SPPs with Lipschitz-continuous objective functions. The objective function is represented as a sum of several components that are distributed between groups of computational nodes. The nodes, or agents, exchange information through some communication network that may be centralized or decentralized. A centralized network has a universal information aggregator (a server, or master node) that directly communicates to each of the agents and therefore can coordinate the optimization process. In a decentralized network, all the nodes are equal, the server node is not present, and each agent only communicates to its immediate neighbors.

We assume that each of the nodes locally holds its objective and can compute its value at given points, i. e. has access to zero-order oracle. Zero-order information is used when the gradient of the function is costly, not possible to compute or when the function is not differentiable. For example, in reinforcement learning one needs to generate a trajectory to evaluate the current policy. This policy evaluation process can be interpreted as the computation of the function value. We propose an approach that uses a smoothing technique, i. e., applies a first-order method to the smoothed version of the initial function. It can be shown that the stochastic gradient of the smoothed function can be viewed as a random two-point gradient approximation of the initial function. Smoothing approaches have been studied for distributed zero-order minimization, and our paper generalizes the smoothing technique on SPPs.