Linas Stripinis
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Linas Stripinis has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Remigijus Paulavičius
Institute of Data Science and Digital Technologies, Faculty of Mathematics and Informatics, Vilnius University, Akademijos str. 4, LT-08412 Vilnius, Lithuania
16 shared publications - Ernestas Filatovas
Institute of Data Science and Digital Technologies, Faculty of Mathematics and Informatics, Vilnius University, Akademijos str. 4, LT-08412 Vilnius, Lithuania
4 shared publications - Jakub Kudela
Institute of Automation and Computer Science, Brno University of Technology, 616 69 Brno, Czech Republic
2 shared publications - Dmitrij Kočegarov1 shared publication
- Francisco Orts
Supercomputing‐Algorithms Group, Informatics Department University of Almería Almería Spain
1 shared publication - Francisco Orts
Institute of Data Science and Digital Technologies Vilnius University Akademijos str. 4 LT-08412 Vilnius Lithuania
1 shared publication
Latest Publications
- Open Access
- 22 September 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Mathematical Software
GENDIRECT: a GENeralized DIRECT-type algorithmic framework for derivative-free global optimization
The DIRECT algorithm (DIviding RECTangles) has been a cornerstone of derivative-free global optimization for three decades, inspiring numerous enhancements and adaptations. The recent DIRECTGO toolbox consolidated over fifty of these implementations, providing users with a diverse set of tools. In this paper, we introduce GENDIRECT , a generalized framework that unifies DIRECT -type algorithms under a single approach. GENDIRECT offers a flexible alternative to creating yet another similar algorithm, enabling efficient generation of both known and novel DIRECT -type optimization algorithms through the assembly of different algorithmic components. This approach surpasses the flexibility of both the DIRECTGO toolbox and individual algorithms. GENDIRECT allows the creation of hundreds of thousands of combinations, facilitating customization and incorporation of new components for further advancements. A preliminary experimental study highlights the potential of specific algorithmic components (such as reduced Pareto selection or infinity norm for candidate size calculation) to significantly enhance performance on certain objective functions, emphasizing the importance of tailoring algorithmic choices within the framework to suit specific problem characteristics. The obtained results also facilitate the derivation of practical default configurations for small-, medium-, and large-budget optimization scenarios.
- 22 September 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Mathematical Software
Open AccessGENDIRECT: a GENeralized DIRECT-type algorithmic framework for derivative-free global optimization
The DIRECT algorithm (DIviding RECTangles) has been a cornerstone of derivative-free global optimization for three decades, inspiring numerous enhancements and adaptations. The recent DIRECTGO toolbox consolidated over fifty of these implementations, providing users with a diverse set of tools. In this paper, we introduce GENDIRECT , a generalized framework that unifies DIRECT -type algorithms under a single approach. GENDIRECT offers a flexible alternative to creating yet another similar algorithm, enabling efficient generation of both known and novel DIRECT -type optimization algorithms through the assembly of different algorithmic components. This approach surpasses the flexibility of both the DIRECTGO toolbox and individual algorithms. GENDIRECT allows the creation of hundreds of thousands of combinations, facilitating customization and incorporation of new components for further advancements. A preliminary experimental study highlights the potential of specific algorithmic components (such as reduced Pareto selection or infinity norm for candidate size calculation) to significantly enhance performance on certain objective functions, emphasizing the importance of tailoring algorithmic choices within the framework to suit specific problem characteristics. The obtained results also facilitate the derivation of practical default configurations for small-, medium-, and large-budget optimization scenarios.
- 9 September 2026
- Published by Elsevier in Applied Soft Computing
- Vol. 204
A practical DIRECT-type algorithm for medium-scale black-box global optimization
- 9 September 2026
- Published by Elsevier in Applied Soft Computing
- Vol. 204
A practical DIRECT-type algorithm for medium-scale black-box global optimization
- 3 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cybernetics
- Vol. 56 (3) , 1202-1215
Two Novel Instance Selection Methods Combining Algorithm Performance and Landscape Analysis: A Comparative Study in Continuous Optimization
A reliable benchmark library is essential for advancing research in global optimization by enabling fair comparisons and rigorous testing of optimization algorithms across diverse problem landscapes. In this article, we focus on instance selection methods, which aim to choose representative problems for evaluating algorithm performance. We present a comprehensive review of existing instance selection methods, highlighting their strengths and limitations, particularly in balancing the consideration of algorithm performance and the analysis of problem characteristics using exploratory landscape analysis. Building on these insights, we introduce two novel instance selection methods that leverage both algorithm performance data and landscape analysis information to construct diverse and informative benchmark sets. For evaluation, we benchmark our approaches against four existing instance selection methods on the recently expanded DIRECTGOLib v2.0 library. Our results demonstrate that the proposed methods effectively identify representative instances that capture a wide range of problem characteristics, enabling a more comprehensive evaluation of algorithm performance. These findings have significant implications for the development and assessment of new optimization algorithms, ultimately contributing to more reliable and robust solutions for real-world optimization problems.
- 3 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cybernetics
- Vol. 56 (3) , 1202-1215
Two Novel Instance Selection Methods Combining Algorithm Performance and Landscape Analysis: A Comparative Study in Continuous Optimization
A reliable benchmark library is essential for advancing research in global optimization by enabling fair comparisons and rigorous testing of optimization algorithms across diverse problem landscapes. In this article, we focus on instance selection methods, which aim to choose representative problems for evaluating algorithm performance. We present a comprehensive review of existing instance selection methods, highlighting their strengths and limitations, particularly in balancing the consideration of algorithm performance and the analysis of problem characteristics using exploratory landscape analysis. Building on these insights, we introduce two novel instance selection methods that leverage both algorithm performance data and landscape analysis information to construct diverse and informative benchmark sets. For evaluation, we benchmark our approaches against four existing instance selection methods on the recently expanded DIRECTGOLib v2.0 library. Our results demonstrate that the proposed methods effectively identify representative instances that capture a wide range of problem characteristics, enabling a more comprehensive evaluation of algorithm performance. These findings have significant implications for the development and assessment of new optimization algorithms, ultimately contributing to more reliable and robust solutions for real-world optimization problems.
- 1 January 2025
- Published by Springer Nature
- p. 278-285
Towards Reproducible Research in Machine Learning via Blockchain
- 1 January 2025
- Published by Springer Nature
- p. 278-285
Towards Reproducible Research in Machine Learning via Blockchain
- Open Access
- 14 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 57-58
Hot Off the Press: Benchmarking Derivative-Free Global Optimization Algorithms under Limited Dimensions and Large Evaluation Budgets
This Hot Off the Press paper provides a brief summary of our recent work "Benchmarking Derivative-Free Global Optimization Algorithms under Limited Dimensions and Large Evaluation Budgets" published in IEEE Transactions on Evolutionary Computation [5]. In the paper, we performed a comprehensive computational comparison between stochastic and deterministic global optimization algorithms with twenty-five representative state-of-the-art methods selected from both classes. The experiments were set up with up to twenty dimensions and relatively large evaluation budgets (105 X n). Benchmarking was carried out in a significantly expanded version of the DIRECTGOLib v2.0 library, which included ten distinct collections of primarily continuous test functions. The evaluation of the methods focused on various aspects, such as solution quality, time complexity, and function evaluation usage. The rankings were determined using statistical tests and performance profiles. Our findings suggest that while state-of-the-art deterministic methods could find reasonable solutions with comparatively fewer function evaluations, most stochastic algorithms require more extensive evaluation budgets to deliver comparable results. However, the performance of stochastic algorithms excelled in more complex and higher-dimensional problems. These research findings offer valuable insights for practitioners and researchers, enabling them to tackle diverse optimization problems effectively.
- 14 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 57-58
Open AccessHot Off the Press: Benchmarking Derivative-Free Global Optimization Algorithms under Limited Dimensions and Large Evaluation Budgets
This Hot Off the Press paper provides a brief summary of our recent work "Benchmarking Derivative-Free Global Optimization Algorithms under Limited Dimensions and Large Evaluation Budgets" published in IEEE Transactions on Evolutionary Computation [5]. In the paper, we performed a comprehensive computational comparison between stochastic and deterministic global optimization algorithms with twenty-five representative state-of-the-art methods selected from both classes. The experiments were set up with up to twenty dimensions and relatively large evaluation budgets (105 X n). Benchmarking was carried out in a significantly expanded version of the DIRECTGOLib v2.0 library, which included ten distinct collections of primarily continuous test functions. The evaluation of the methods focused on various aspects, such as solution quality, time complexity, and function evaluation usage. The rankings were determined using statistical tests and performance profiles. Our findings suggest that while state-of-the-art deterministic methods could find reasonable solutions with comparatively fewer function evaluations, most stochastic algorithms require more extensive evaluation budgets to deliver comparable results. However, the performance of stochastic algorithms excelled in more complex and higher-dimensional problems. These research findings offer valuable insights for practitioners and researchers, enabling them to tackle diverse optimization problems effectively.
- Open Access
- 11 April 2024
- Published by Vilnius University Press in Informatica
- Vol. 35 (2) , 227-253
Advancing Research Reproducibility in Machine Learning through Blockchain Technology
Publisher: Vilnius University Institute of Data Science and Digital Technologies, Journal: Informatica, Title: Advancing Research Reproducibility in Machine Learning through Blockchain Technology, Authors: Ernestas Filatovas, Linas Stripinis, Francisco Orts, Remigijus Paulavičius , Like other disciplines, machine learning is currently facing a reproducibility crisis that hinders the advancement of scientific research. Researchers face difficulties reproducing key results due to the lack of critical details, including the disconnection between publications and associated models, data, parameter settings, and experimental results. To promote transparency and trust in research, solutions that improve the accessibility of models and data, facilitate experiment tracking, and allow audit of experimental results are needed. Blockchain technology, characterized by its decentralization, data immutability, cryptographic hash functions, consensus algorithms, robust security measures, access control mechanisms, and innovative smart contracts, offers a compelling pathway for the development of such solutions. To address the reproducibility challenges in machine learning, we present a novel concept of a blockchain-based platform that operates on a peer-to-peer network. This network comprises organizations and researchers actively engaged in machine learning research, seamlessly integrating various machine learning research and development frameworks. To validate the viability of our proposed concept, we implemented a blockchain network using the Hyperledger Fabric infrastructure and conducted experimental simulations in several scenarios to thoroughly evaluate its effectiveness. By fostering transparency and facilitating collaboration, our proposed platform has the potential to significantly improve reproducible research in machine learning and can be adapted to other domains within artificial intelligence.
- 11 April 2024
- Published by Vilnius University Press in Informatica
- Vol. 35 (2) , 227-253
Open AccessAdvancing Research Reproducibility in Machine Learning through Blockchain Technology
Publisher: Vilnius University Institute of Data Science and Digital Technologies, Journal: Informatica, Title: Advancing Research Reproducibility in Machine Learning through Blockchain Technology, Authors: Ernestas Filatovas, Linas Stripinis, Francisco Orts, Remigijus Paulavičius , Like other disciplines, machine learning is currently facing a reproducibility crisis that hinders the advancement of scientific research. Researchers face difficulties reproducing key results due to the lack of critical details, including the disconnection between publications and associated models, data, parameter settings, and experimental results. To promote transparency and trust in research, solutions that improve the accessibility of models and data, facilitate experiment tracking, and allow audit of experimental results are needed. Blockchain technology, characterized by its decentralization, data immutability, cryptographic hash functions, consensus algorithms, robust security measures, access control mechanisms, and innovative smart contracts, offers a compelling pathway for the development of such solutions. To address the reproducibility challenges in machine learning, we present a novel concept of a blockchain-based platform that operates on a peer-to-peer network. This network comprises organizations and researchers actively engaged in machine learning research, seamlessly integrating various machine learning research and development frameworks. To validate the viability of our proposed concept, we implemented a blockchain network using the Hyperledger Fabric infrastructure and conducted experimental simulations in several scenarios to thoroughly evaluate its effectiveness. By fostering transparency and facilitating collaboration, our proposed platform has the potential to significantly improve reproducible research in machine learning and can be adapted to other domains within artificial intelligence.
- Open Access
- 26 March 2024
- Published by Vilnius University Press in Informatica
- p. 141-174
Review and Computational Study on Practicality of Derivative-Free DIRECT-Type Methods
Derivative-free DIRECT-type global optimization algorithms are increasingly favoured for their simplicity and effectiveness in addressing real-world optimization challenges. This review examines their practical applications through a systematic analysis of scientific journals and computational studies. In particular, significant challenges in reproducibility have been identified with practical problems. To address this, we conducted an experimental study using practical problems from reputable CEC libraries, comparing DIRECT-type techniques against their state-of-the-art counterparts. Therefore, this study sheds light on current gaps, opportunities, and future prospects for advanced research in this domain, laying the foundation for replicating and expanding the research findings presented herein.
- 26 March 2024
- Published by Vilnius University Press in Informatica
- p. 141-174
Open AccessReview and Computational Study on Practicality of Derivative-Free DIRECT-Type Methods
Derivative-free DIRECT-type global optimization algorithms are increasingly favoured for their simplicity and effectiveness in addressing real-world optimization challenges. This review examines their practical applications through a systematic analysis of scientific journals and computational studies. In particular, significant challenges in reproducibility have been identified with practical problems. To address this, we conducted an experimental study using practical problems from reputable CEC libraries, comparing DIRECT-type techniques against their state-of-the-art counterparts. Therefore, this study sheds light on current gaps, opportunities, and future prospects for advanced research in this domain, laying the foundation for replicating and expanding the research findings presented herein.
- Open Access
- 9 January 2024
- Published by MDPI AG in Mathematics
- Vol. 12 (2) , 221
Data-Driven Consensus Protocol Classification Using Machine Learning
The consensus protocol plays a vital role in the performance and security of a specific Distributed Ledger Technology (DLT) solution. Currently, the traditional classification of consensus algorithms relies on subjective criteria, such as protocol families (Proof of Work, Proof of Stake, etc.) or other protocol features. However, such classifications often result in representatives with strongly different characteristics belonging to the same category. To address this challenge, a quantitative data-driven classification methodology that leverages machine learning—specifically, clustering—is introduced here to achieve unbiased grouping of analyzed consensus protocols implemented in various platforms. When different clustering techniques were used on the analyzed DLT dataset, an average consistency of was achieved, while some instances exhibited a match of , and the lowest consistency observed was .- 9 January 2024
- Published by MDPI AG in Mathematics
- Vol. 12 (2) , 221
Open AccessData-Driven Consensus Protocol Classification Using Machine Learning
The consensus protocol plays a vital role in the performance and security of a specific Distributed Ledger Technology (DLT) solution. Currently, the traditional classification of consensus algorithms relies on subjective criteria, such as protocol families (Proof of Work, Proof of Stake, etc.) or other protocol features. However, such classifications often result in representatives with strongly different characteristics belonging to the same category. To address this challenge, a quantitative data-driven classification methodology that leverages machine learning—specifically, clustering—is introduced here to achieve unbiased grouping of analyzed consensus protocols implemented in various platforms. When different clustering techniques were used on the analyzed DLT dataset, an average consistency of was achieved, while some instances exhibited a match of , and the lowest consistency observed was . - Open Access
- 29 June 2023
- Published by MDPI AG in Mathematics
- Vol. 11 (13) , 2920
Novel Algorithm for Linearly Constrained Derivative Free Global Optimization of Lipschitz Functions
This paper introduces an innovative extension of the DIRECT algorithm specifically designed to solve global optimization problems that involve Lipschitz continuous functions subject to linear constraints. Our approach builds upon recent advancements in DIRECT-type algorithms, incorporating novel techniques for partitioning and selecting potential optimal hyper-rectangles. A key contribution lies in applying a new mapping technique to eliminate the infeasible region efficiently. This allows calculations to be performed only within the feasible region defined by linear constraints. We perform extensive tests using a diverse set of benchmark problems to evaluate the effectiveness and performance of the proposed algorithm compared to existing DIRECT solvers. Statistical analyses using Friedman and Wilcoxon tests demonstrate the superiority of a new algorithm in solving such problems.
- 29 June 2023
- Published by MDPI AG in Mathematics
- Vol. 11 (13) , 2920
Open AccessNovel Algorithm for Linearly Constrained Derivative Free Global Optimization of Lipschitz Functions
This paper introduces an innovative extension of the DIRECT algorithm specifically designed to solve global optimization problems that involve Lipschitz continuous functions subject to linear constraints. Our approach builds upon recent advancements in DIRECT-type algorithms, incorporating novel techniques for partitioning and selecting potential optimal hyper-rectangles. A key contribution lies in applying a new mapping technique to eliminate the infeasible region efficiently. This allows calculations to be performed only within the feasible region defined by linear constraints. We perform extensive tests using a diverse set of benchmark problems to evaluate the effectiveness and performance of the proposed algorithm compared to existing DIRECT solvers. Statistical analyses using Friedman and Wilcoxon tests demonstrate the superiority of a new algorithm in solving such problems.
- 3 June 2023
- Published by Elsevier in Expert Systems with Applications
- Vol. 230
A novel greedy genetic algorithm-based personalized travel recommendation system
- 3 June 2023
- Published by Elsevier in Expert Systems with Applications
- Vol. 230
A novel greedy genetic algorithm-based personalized travel recommendation system