Aims and Scope

The field of optimization is confronting escalating challenges amid the growing scale, complexity, and dynamic nature of problems spanning scientific and industrial domains. Conventional methods—including evolutionary algorithms, swarm intelligence, and mathematical programming—often grapple with high computational overheads, limited scalability in high-dimensional spaces, and an inability to adapt to problem-specific structures.

Recent advances in machine learning (ML) are reshaping this landscape. Deep learning, reinforcement learning, Bayesian optimization, and related techniques enable the extraction of latent patterns, the modeling of complex mappings, and the construction of data-driven surrogate models. This synergy is fostering a new generation of intelligent optimizers that are more efficient, adaptive, and autonomous.

A paradigm shift is underway, moving from traditional optimization strategies to learning-aware frameworks. Central to this evolution is the transition from random exploration to guided search, where ML models uncover and exploit structural properties of the problem space to steer optimization efficiently. For instance, ML-based surrogates effectively approximate computationally expensive evaluations—such as those in computational fluid dynamics (CFD) or molecular docking—rendering previously intractable problems feasible. Moreover, learning-augmented optimizers exhibit real-time adaptability in dynamic environments, a critical capability for autonomous systems. Ultimately, this trend points toward fully automated algorithm design, embodied by the concept of "Learning to Optimize Intelligently," where ML autonomously selects, configures, and orchestrates optimization strategies with minimal human intervention.

This special issue invites contributions exploring deep integrations of ML and optimization, transcending superficial hybrid approaches to frameworks where machine learning fundamentally redefines the optimization process. We welcome original research demonstrating how learning-driven optimization can overcome longstanding barriers and open pathways to solving previously infeasible problems.

List of Topics

Topics of interest include, but are not limited to:

• Learning-Driven Optimization Algorithms:
  • Surrogate-assisted and model-based evolutionary computation
  • Bayesian optimization and its extensions
  • Deep learning-enhanced metaheuristics
  • Reinforcement learning for metaheuristic control and adaptation
• ML Techniques within Optimizers:
  • Representation learning for search space understanding and feature extraction
  • Predictive models for solution quality and fitness approximation
  • Generative models (GANs, VAEs) for solution generation and repair
  • Transfer learning and multi-task optimization
  • Automated Algorithm Design:
  • Hyperparameter optimization and algorithm selection via ML
  • Meta-learning for black box optimization and algorithm configuration
  • Adaptive operator selection using learning mechanisms
• Machine Learning aided Intelligent Optimization for Complex Problems:
  • Large-scale and multi/many-objective optimization
  • Dynamic, noisy, and uncertain optimization environments
  • Constrained and combinatorial optimization
  • Multi-modal optimization
• Applications and Benchmarks:
  • Real-world applications in Industry 4.0, digital twins, drug discovery, finance, and sustainable energy.
  • Novel benchmark suites and performance metrics for evaluating ML-enabled optimizers.

Submission Guidelines

Authors should prepare papers in accordance with the format requirements of Tsinghua Science and Technology, with reference to the Instruction given at  https://www.sciopen.com/journal/1007-0214, and submit the complete manuscript through the online manuscript submission system at https://mc03.manuscriptcentral.com/tst with manuscript type as “Special Issue on Machine Learning Enabled Intelligent Optimization”.

Important Dates

Deadline for submissions: June 30, 2026

Guest Editors

Ling Wang, Tsinghua University, Beijing, China. 

Wenyin Gong, China University of Geosciences, Wuhan, China.

Rui Wang, National University of Defense Technology, Changsha, China. 

Qingfu Zhang, City University of Hong Kong, Hong Kong, China.