Related papers: Automatic Adjustment of HPA Parameters and Attack …

Parameter-Efficient Fine-Tuning (PEFT), especially Low-Rank Adaptation (LoRA), has emerged as a promising approach to fine-tuning large language models(LLMs) while reducing computational and memory overhead. However, LoRA assumes a uniform…

As machine learning and cybersecurity continue to explode in the context of the digital ecosystem, the complexity of cybersecurity data combined with complicated and evasive machine learning algorithms leads to vast difficulties in…

To leverage data and computation capabilities of mobile devices, machine learning algorithms are deployed at the network edge for training artificial intelligence (AI) models, resulting in the new paradigm of edge learning. In this paper,…

Dynamic Optimization Problems (DOPs) are challenging to address due to their complex nature, i.e., dynamic environment variation. Evolutionary Computation methods are generally advantaged in solving DOPs since they resemble dynamic…

Hadoop MapReduce is a framework for distributed storage and processing of large datasets that is quite popular in big data analytics. It has various configuration parameters (knobs) which play an important role in deciding the performance…

Serverless platforms such as Kubernetes are increasingly adopted in high-performance computing, yet autoscaling remains challenging under highly dynamic and heterogeneous workloads. Existing approaches often rely on uniform reactive…

Data analysis and machine learning have become an integrative part of the modern scientific methodology, providing automated techniques to predict further information based on observations. One of these classification and regression…

The increasing adoption of Artificial Intelligence (AI) in engineering problems calls for the development of calibration methods capable of offering robust statistical reliability guarantees. The calibration of black box AI models is…

An optimization technique based on an adapted combination of simulated annealing (SA) and tabu search (TS) is presented. This method aims at finding near-optimal unequal error protection (UEP) application-layer FEC code configurations. This…

After developer adjustments to a machine learning (ML) algorithm, how can the results of an old hyperparameter optimization (HPO) automatically be used to speedup a new HPO? This question poses a challenging problem, as developer…

In this paper, we review hyperparameter optimization methods for machine learning models, with a particular focus on the Adaptive Tree-Structured Parzen Estimator (ATPE) algorithm. We propose several modifications to ATPE and assess their…

Evolutionary Algorithms (EAs) are being routinely applied for a variety of optimization tasks, and real-parameter optimization in the presence of constraints is one such important area. During constrained optimization EAs often create…

In secure network coding, there is a possibility that the eavesdropper can improve her performance when she changes (contaminates) the information on the attacked edges (active attack) and chooses the attacked edges adaptively (adaptive…

Contextual bandits are widely used in industrial personalization systems. These online learning frameworks learn a treatment assignment policy in the presence of treatment effects that vary with the observed contextual features of the…

This paper presents the Traffic Adaptive Moving-window Patrolling Algorithm (TAMPA), designed to improve real-time incident management during major events like sports tournaments and concerts. Such events significantly stress transportation…

Algorithm selection and hyperparameter tuning are critical steps in both academic and applied machine learning. On the other hand, these steps are becoming ever increasingly delicate due to the extensive rise in the number, diversity, and…

While continual visual instruction tuning (CVIT) has shown promise in adapting multimodal large language models (MLLMs), existing studies predominantly focus on models without safety alignment. This critical oversight ignores the fact that…

Automated hyperparameter optimization (HPO) has gained great popularity and is an important ingredient of most automated machine learning frameworks. The process of designing HPO algorithms, however, is still an unsystematic and manual…

Hybrid planner switching framework (HPSF) for autonomous driving needs to reconcile high-speed driving efficiency with safe maneuvering in dense traffic. Existing HPSF methods often fail to make reliable mode transitions or sustain…

Regulating the importance ratio is critical for the training stability of Group Relative Policy Optimization (GRPO) based frameworks. However, prevailing ratio control methods, such as hard clipping, suffer from non-differentiable…