STAFF
HOME
ACTIVITIES
PROJECTS
PUBLICATIONS
STAFF
CONTACT
Ana Nikolikj
About
Activities
Publications
Projects
Ana Nikolikj,
Building A, Floor 2, Room S6a
+386 1 477 3616
ana.nikolikj@ijs.si
About
Activities
Academic
Research
Publications
Journal articles
show more
A Survey of Features Used for Representing Black-box Single-Objective Continuous Optimization
Benchmarking Footprints of Continuous Black-Box Optimization Algorithms: Explainable Insights into Algorithm Success and Failure
A Learning Search Algorithm for the Restricted Longest Common Subsequence Problem
Exploring Module Interactions in Modular CMA-ES across Problem Classes
User-Defined Trade-Offs in LLM Benchmarking: Balancing Accuracy, Scale, and Sustainability
Conference papers
show more
Tracing the Interactions of Modular CMA-ES Configurations Across Problem Landscapes
Customized Exploration of Landscape Features Driving Multi-Objective Combinatorial Optimization Performance
Quantifying Module Interactions in the PSO-X Framework
Generalization Ability of Feature-based Performance Prediction Models: A Statistical Analysis across Benchmarks
Quantifying Individual and Joint Module Impact in Modular Optimization Frameworks
Comparing Solvability Patterns of Algorithms across Diverse Problem Landscapes
RF+clust for Leave-One-Problem-Out Performance Prediction
Algorithm Instance Footprint: Separating Easily Solvable and Challenging Problem Instances
Assessing the Generalizability of a Performance Predictive Model
Sensitivity Analysis of RF+clust for Leave-one-problem-out Performance Prediction
PS-AAS: Portfolio Selection for Automated Algorithm Selection in Black-Box Optimization
Identifying minimal set of Exploratory Landscape Analysis features for reliable algorithm performance prediction
Improving Nevergrad’s Algorithm Selection Wizard NGOpt Through Automated Algorithm Configuration
Explaining Differential Evolution Performance Through Problem Landscape Characteristics
Books & Chapters
show more
Explainable Landscape Analysis
Projects
Research
show more
Leveraging Benchmarking Data for Automated Machine Learning and Optimization
From Big Data to Good Data: Smart-sized Benchmarking for Trustworthy Artificial Intelligence
Slovenian AI Factory
Refined estimation of environmental exposure in vulnerable population groups and its biological and health impact
Artificial Intelligence for Science
Auto-OPT: Automated selection and configuration of single-objective continuous optimization algorithms
Theoretical and computational aspects of some graph problems with applications on network information spreading
Representation Learning of Landscape Spaces for Explainable Performance of Stochastic Optimization Algorithms
Automated Configuration, Selection, and Design of Iterative Optimization Heuristics
Fair Benchmarking for Dynamic Algorithm Configuration
Applied
show more