The Sixth Data Science Meets Optimisation (DSO) Workshop at IJCAI 2024

The IJCAI DSO continues on DSO@IJCAI2022, DSO@IJCAI2021, DSO@IJCAI2020 and the DSO@IJCAI2019 workshop at the International Joint Conference on Artificial Intelligence (IJCAI). The DSO workshop is closely related to the DSO working group of The Association of European Operational Research Societies (EURO). In addition to DSO@FAIM 2018, previous related activities include: DSO@IJCAI-ECAI 2018 (Stockholm); stream at EURO 2018 (Valencia); stream at IFORS 2017 (Quebec); workshop at CPAIOR 2017 (Padua); workshop at CEC 2017 (San Sebastian); the foundational workshop (Leuven). More information about the previous editions of DSO is available at https://www.euro-online.org/websites/dso/.

Scope

The IJCAI DSO workshop builds upon the ongoing collaboration between researchers in data science, operations research (OR), and machine learning (ML). Operations research, as an interdisciplinary branch, draws from mathematics, statistics, and computer science, specializing in modelling and solving intricate problems across various sectors. In today’s digital era, the integration of ML and data science into OR is not merely beneficial but indispensable. Our workshop aims to showcase how techniques from OR and data science can mutually benefit each other.

List of Topics

The workshop invites submissions that include but are not limited to the following topics:

• Applying data science and ML methods to solve combinatorial optimization problems: such as end-to-end solving, algorithm selection based on historical data, speeding up or driving the search process using ML including (deep) reinforcement learning.
• Using optimization algorithms for the development of machine learning models: such as formulating the problem of learning predictive models as MIP, constraint programming or boolean satisfiability (SAT).
• Learning optimization models from data: including learning mathematical optimization formulations (objectives and constraints), learning constraints from data, and creating reinforcement learning models from data.
• Formal analysis of ML models via optimization or constraint satisfaction techniques: safety checking and verification via SMT or MIP, generation of adversarial examples via similar combinatorial techniques.
• Integrating techniques from ML and OR, to address contextual stochastic optimization problems and decision-making under uncertainty: such as decision-focused learning, predict-then-optimize.
• Hyperparameter tuning of ML models using search algorithms and meta-heuristics.
• Computing explanations for ML model via techniques developed for optimization or constraint reasoning systems.

Submission Instructions

Authors are invited to send a contribution in the IJCAI proceedings format, in the form of:

• Long paper: Submission of original work up to 7 pages in length (plus references).
• Short paper: Submission of work-in-progress with preliminary results, and of position papers, up to 4 pages in length (plus references).
• Extended abstract: Published journal/conference papers in the form of a 2-page extended abstract.

Submission should be prepared following the IJCAI formatting instructions at: https://www.ijcai.org/authors_kit. The review process is single-blind. The programme committee will select the papers to be presented at the workshop according to their suitability to the aims. Selected contributors will be invited to submit extended articles to a special issue of a journal.

Manuscripts must be submitted as PDF files via OpenReview online submission system: https://openreview.net/group?id=ijcai.org/IJCAI/2024/Workshop/DSO

Organizing Committee

• Hoong Chuin Lau (Singapore Management University, SG)

• Michele Lombardi (University of Bologna, IT)

• Jayanta Mandi (KU Leuven, BE)

• Yaoxin Wu (TU Eindhoven, NL)

• Neil Yorke-Smith (TU Delft, NL)

• Yingqian Zhang (TU Eindhoven, NL)

Format and Schedule

The workshop is planned as a full-day physical event. It will include invited talk sessions, open discussions, presentations of accepted works, and the exchange of ideas by researchers and practitioners working at the relevant intersection of data science, OR, in areas such as machine learning, symbolic AI, mathematical programming, simulation and heuristic-based optimization, constraint optimization and learning, sequential decision-making. The detailed schedule will be made available after the list of accepted papers is finalized.

Contact

Please direct all questions concerning submissions or IJCAI-DSO-24 in general to: yqzhang@tue.nl