COSEAL Workshop 2022


The ninth COSEAL Workshop is a forum for discussing the most recent advances in the automated configuration and selection of algorithms. It will take place on September 5th and is organized by Alexander Tornede, Eyke Hüllermeier and Marius Lindauer .

The workshop will consist of posters and talks about late-breaking research and useful tools, discussions regarding intra- and international cooperation, and many opportunities to interact with other attendees. There are no paper submissions, but the workshop provides the chance to discuss on-going research and recent results with other researchers.


Administrative questions :

Scope of the Workshop

The scope of COSEAL includes, but is not limited to:

  • Algorithm selection
  • Algorithm configuration 
  • Algorithm portfolios
  • Performance predictions and empirical performance models
  • Bayesian optimization
  • Hyperparameter optimization
  • Automated machine learning (AutoML)
  • Neural architecture search
  • Meta-learning
  • Algorithm and parameter control
  • Explorative landscape analysis
  • Programming by optimization
  • Hyper-heuristics

Important dates

  • Registration deadline : August 15th
  • Talk/poster abstract deadline : August 17th
  • Poster submission deadline: August 29th
  • Workshop : September 5th 2022


COSEAL 2022 workshop will be an virtual workshop with talks in Zoom, and poster sessions and social event in gather town.

Registration Fees

None! For free!

Registration and Applications

  • Attending [Deadline passed]
  • Applying for a poster [Deadline passed]
    • You only need to submit a title and an abstract
    • You don’t need to submit a paper – no reviewing!
    • If in scope of COSEAL, it will be accepted
  • Applying for a talk [Deadline passed]
    • You only need to submit a title and an abstract
    • You don’t need to submit a paper – no reviewing!
    • Since we have a limited number of talk slots, the workshop chairs will select the most interesting and novel topics
    • We recommend that besides giving a talk, also a poster is presented s.t. attendees have the chance to interact with you more


Time slots according to CEST

08:30 – 09:00Joining the Zoom call, small-talk and enjoy a tee or coffee togetherZoom
09:00 – 09:15OpeningZoom
09:15 – 09:45Contributed Talk I:
Consolidated learning – new approach to domain-specific strategy of hyperparameter optimization 
by Katarzyna Woźnica (Warsaw University of Technology)
09:45 – 10:15Contributed Talk II:
An Energy-based Probabilistic Framework for Algorithm Selection 
by Phong Le (Amazon)
10:15 – 10:45Coffee Break with Speed Dating in break out-rooms (15min with a small set of random attendees)Zoom
10:45 – 12:00Poster Session I (Poster Room 1)Gather.Town
12:00 – 14:00Lunch BreakGather.Town
14:00 – 14:30Contributed Talk III:
The Right Mutation Operator for Permutation Problems 
by Benjamin Doerr (Ecole Polytechnique)
14:30 – 15:00Contributed Talk IV:
Theory-inspired Parameter Control Benchmarks for Dynamic Algorithm Configuration 
by Nguyen Dang (University of St Andrews)
15:00 16:30Poster Session II (Poster Room 2)Gather.Town
16:30 – 18:00Breakout Session: What could be the next joint COSEAL research project?Zoom
18:00 – 18:15ClosingZoom
18:15 – open endSocial EventGather.Town

Links to the Zoom and Gather.Town instances have been sent out via email to all registered participants on 31/08/2022. If you have not received an email by 01/09/2022, please contact


The Gather.Town looks like below. The poster session I will happen in poster room 1 and session 2 will happen in room 2.

Contributed Talks

Theory-inspired Parameter Control Benchmarks for Dynamic Algorithm Configuration by Nguyen Dang (University of St Andrews)

An Energy-based Probabilistic Framework for Algorithm Selection by Phong Le (Amazon)

The Right Mutation Operator for Permutation Problems by Benjamin Doerr (Ecole Polytechnique)

Consolidated learning – new approach to domain-specific strategy of hyperparameter optimization by Katarzyna Woźnica (Warsaw University of Technology)

Poster Session I (Poster Room 1)

Reinforcement learning based adaptive metaheuristics by Michelle Tessari, Giovanni Iacca

Landscape Analysis for Hyperparameter Optimization: are we getting fooled? by René Traoré, Andrés Camero, Xiao Xiang Zhu

DeepCAVE: An Interactive Analysis Tool for Automated Machine Learning by René Sass, Eddie Bergman, André Biedenkapp, Frank Hutter, Marius Lindauer

On the potential of automated algorithm configuration on multi-modal multi-objective optimization problems by Jeroen Rook, Heike Trautmann, Jakob Bossek, Christian Grimme

PyExperimenter: easily execute experiments and track results by Tanja Tornede, Alexander Tornede, Lukas Fehring, Lukas Gehring, Helena Graf, Jonas Hanselle, Marvel Wever, Felix Mohr

IMFAS: Towards Meta-learned Algorithm Selection using Implicit Fidelity Information by Aditya Mohan, Tim Ruhkopf, Deng Difan, Marius Lindauer

On the Applicability of Offline Reinforcement Learning for Dynamic Algorithm Configuration of Differential Evolution by Florian Diederichs, André Biedenkapp, Noor Awad, Frank Hutter

Applying Principal Component Analysis to improve Bayesian Optimization in High Dimensions by Elena Raponi, Kirill Antonov, Maria Laura Santoni, Hao Wang, and Carola Doerr

Theory-inspired Parameter Control Benchmarks for Dynamic Algorithm Configuration by Martin Krejca, Nguyen Dang, André Biedenkapp, Frank Hutter, Carola Doerr

Combined Ranking and Regression Trees for Algorithm Selection by Lukas Fehring, Alexander Tornede

Learning-to-Prune: A machine learning framework for solving combinatorial optimisation problems by Deepak Ajwani

A Survey of Methods for Automated Algorithm Configuration by Elias Schede, Jasmin Brandt, Alexander Tornede, Marcel Wever, Viktor Bengs, Eyke Hüllermeier, Kevin Tierney

An Explainable Landscape-aware Algorithm Performance Prediction Approach for Understanding Similarities in Algorithm Behavior by Ana Nikolikj, Ryan Lang, Peter Korosec, Tome Eftimov

Poster Session II (Poster Room 2)

Fairness-aware AutoML: Assumptions, Opportunities, Evaluation Protocols, and Guidelines by Florian Pfisterer, Matthias Feurer, Katharina Eggensperger, Hilde Weerts, Edward Bergman, Noor Awad, Joaquin Vanschoren, Bernd Bischl, Frank Hutter

Taking the Hassle out of Side Channel Attacks: Comparative Study of Neural Architecture Search Strategies by Pritha Gupta

The Feasibility of Greedy Ensemble Selection for Automated Recommender Systems by Tobias Vente, Lennart Purucker, Joeran Beel

The Impact of Performance Variability on Dynamic Algorithm Configuration by Diederick Vermetten, Hao Wang, Carola Doerr, Manuel López-Ibañez and Thomas Bäck

Self-adaptation via Multi-objectivisation: Multi-Objective Self-Adaptive EA (MOSA-EA) by Xiaoyu QIN, Per Kristian Lehre

Cooperative Meta-Learning Service for Recommender Systems by Lukas Wegmeth, Joeran Beel

Consolidated learning – new approach to domain-specific strategy of hyperparameter optimization by Katarzyna Woźnica, Piotr Wilczyński, Mateusz Grzyb, Zuzanna Trafas, Przemysław Biecek

Reactive Learning Rate Scheduling by Samuel Schüler, Göktuğ Karakaşlı, André Biedenkapp, Steven Adriaensen, Frank Hutter

forester: automated partner for planting transparent tree-based models by Anna Kozak, Adrianna Grudzień, Hubert Ruczyński, Patryk Słowakiewicz

Algorithm Selection and Hyperparameter Optimization with Imprecise Performance Data by Jonas Hanselle, Felix Mohr, Eyke Hüllermeier

Automatically Stopping Random Forests by Felix Mohr

MO-HPOBench: A Comprehensive Benchmark for Multi-Objective Hyperparameter Optimization by Noor Awad, Philipp Müller, Ayushi Sharma, Katharina Eggensperger, Matthias Feurer, Florian Pfisterer, Lennart Schneider, Bernd Bischl, Janek Thomas, Frank Hutter

Sponsored by

SFB 901 On-The-Fly Computing (Universität Paderborn)

Supported by

  • Daniel Ritter (Leibniz University Hannover)