Runtime Analysis with Variable Cost - Algorithmica
The usual approach in runtime analysis is to derive estimates on the number of fitness function evaluations required by a method until a suitable element of the search space is found. One justificatio...
Runtime analysis of evolutionary algorithms counts fitness function evaluations to optimum. We introduce cost models where eval costs differ among search points, allowing cost adaptive optimisation: find optimum by exploring cheaper parts of search space.
link.springer.com/article/10.1...
18.04.2025 13:04 β π 2 π 0 π¬ 0 π 0
Learning in games usually assumes small action spaces. This afternoon at #AAAI2025 we give an oral presentation showing that the PDCoEA co-evolutionary algorithm finds the Nash Equilibrium of the game below (2^n actions) in expected poly(n) time. Joint work with Shishen Lin.
28.02.2025 19:43 β π 4 π 0 π¬ 0 π 0
Reinforcement learning gathering a crowd at #AAAI
27.02.2025 15:05 β π 2 π 0 π¬ 0 π 0
Arrived in Philadelphia for the AAAI conference. We will present a runtime analysis of the PDCoEA (a coevolutionary algorithm) showing logarithmic (wrt number of strategies) expected runtime to find a Nash equilibrium in the game we studied.
25.02.2025 19:45 β π 2 π 0 π¬ 0 π 0
COST Action CA22137 ROAR-NET organizes two exciting events this year, the Training School and Code Fest, and has calls open for Short-Term Scientific Missisions (STSMs) and Young Researcher and Innovator Conference Grants roar-net.eu
21.02.2025 05:20 β π 1 π 2 π¬ 0 π 0
Assistant Professor at the Department of Computer Science, University of Liverpool.
https://lutzoe.github.io/
Researcher at Inria. Simulating the origins of life, cognition and culture. Using methods from ALife and AI.
Publications: https://scholar.google.com/citations?hl=en&user=rBnV60QAAAAJ&view_op=list_works&sortby=pubdate
Prev. posts still on X same username
What I do not understand, I can still create. -- unknown γ’γ‘γͺγ«γ§ε€§ε¦ζε‘γγ£γ¦γγΎγοΌγγ€γγγ³γͺγγ¨γ°γγθγγ¦γγΎγοΌζθδ½γη³»οΌ
Lila is a technology company pioneering the application of artificial intelligence to transform every aspect of the scientific method.
The world's leading venue for collaborative research in theoretical computer science. Follow us at http://YouTube.com/SimonsInstitute.
Research director | @McGillU @Mila_Quebec @IVADO_Qc | My team designs machine learning frameworks to understand biological systems from new angles of attack
mathematics, theoretical computer science, philosophy @ Universidad CatΓ³lica de Chile & Polish Academy of Sciences | 'The evolution of sense is, in a sense, the evolution of nonsense.'
Researcher in machine learning and optimization. Open source enthusiast. Parody songwriter (aka PianoHamster). OCD survivor.
TCS+ is the original online seminar in theoretical computer science, committed to the carbon-free dissemination of ideas across the globe since 2013. Talks from the cutting edge of research in TCS, for a wide audience: https://www.tcsplus.org
Assistant Professor @PrincetonCS
Research: Theoretical Computer Science, Optimization, Algorithmic Statistics.
phd student @UChicagoCS. interested in cryptography, algorithms, combinatorics.
gabey.zip
postdoc @ ai lab, Vrije Universiteit Brussel
working on providing reliable and verifiable ai mechanisms
#RL & formal methods
delgrange.me
Professor at the University of Washington, Paul G. Allen School of Computer Science & Engineering @uwcse.bsky.social
Working on cryptography, theoretical computer science, and computer security.
https://homes.cs.washington.edu/~tessaro/
Assoc. Prof. of CS at the Hebrew University.
Algorithmic Game Theory.
Economics and Computation.
https://sites.google.com/view/babaioff/about-me
CS Theory postdoc at MIT (https://math.mit.edu/~shivamn)
Associate Professor, Department of Computer Science, Johns Hopkins University.
https://www.cs.jhu.edu/~mdinitz/
Professor of Computer Science at Cambridge.
π¨π¦ Theoretical computer scientist. Assistant professor at @stfx-university.bsky.social. Website: taylorjsmith.xyz.
