πΉ Theoretically ECP is a no-regret algorithm.
πΉ Outperforms state-of-the-art algorithms, including Lipschitz, Bayesian, bandits, and evolutionary approaches.
π Paper: arxiv.org/abs/2502.042...
π» Code: github.com/fouratifares... β try it out, and share your thoughts!
10.02.2025 11:20 β π 0 π 0 π¬ 0 π 0
πΉ ECP is optimized for expensive functionsβexcels with low function call budgets.
πΉ ECP is empirically tested across 30 multi-dimensional non-convex synthetic and real-world optimization problems.
10.02.2025 11:17 β π 0 π 0 π¬ 1 π 0
π Tackling non-convex optimization? Stuck in local optima? Need a global optimizer for black-box functions?
Introducing ECPβa powerful global optimization algorithm (AISTATS β25)! π₯
πΉ ECP focuses on regions with the highest potential for optimality.
10.02.2025 11:17 β π 2 π 0 π¬ 0 π 0
PhD candidate in RL. Can I join?
07.12.2024 03:22 β π 0 π 0 π¬ 0 π 0
Math Assoc. Prof. (On leave, Aix-Marseille, France)
Teaching Project (non-profit): https://highcolle.com/
Research director | @McGillU @Mila_Quebec @IVADO_Qc | My team designs machine learning frameworks to understand biological systems from new angles of attack
Co-founder @forecastingco. Previously PhD UC Berkeley @berkeley_ai, @ENS_ParisSaclay (MVA) and @polytechnique π«π· πΊπΈ | ππ₯
Researcher in RL at the University of Liège
Anti-cynic. Towards a weirder future. Reinforcement Learning, Autonomous Vehicles, transportation systems, the works. Asst. Prof at NYU
https://emerge-lab.github.io
https://www.admonymous.co/eugenevinitsky
A LLN - large language Nathan - (RL, RLHF, society, robotics), athlete, yogi, chef
Writes http://interconnects.ai
At Ai2 via HuggingFace, Berkeley, and normal places
Research Scientist at Google DeepMind, interested in multiagent reinforcement learning, game theory, games, and search/planning.
Lover of Linux π§, coffee β, and retro gaming. Big fan of open-source. #gohabsgo π¨π¦
For more info: https://linktr.ee/sharky6000
Principal Researcher @ Microsoft Research.
AI, RL, cog neuro, philosophy.
www.momen-nejad.org
Interested in cognition and artificial intelligence. Research Scientist at Google DeepMind. Previously cognitive science at Stanford. Posts are mine.
lampinen.github.io
Staff research scientist at Google DeepMind. AI and neuro.
Former physicist, current human.
Find more at www.janexwang.com
AI, RL, NLP, Games Asst Prof at UCSD
Research Scientist at Nvidia
Lab: http://pearls.ucsd.edu
Personal: prithvirajva.com
professor at university of washington and founder at csm.ai. computational cognitive scientist. working on social and artificial intelligence and alignment.
http://faculty.washington.edu/maxkw/
AI and Games Researcher at NYU.
Professor, Department of Psychology and Center for Brain Science, Harvard University
https://gershmanlab.com/
web: http://maxim.ece.illinois.edu
substack: https://realizable.substack.com
Assistant professor at NUS. Scaling cooperative intelligence & infrastructure for an increasingly automated future. PhD @ MIT ProbComp / CoCoSci. Pronouns: η₯/δΌ
Researcher in robotics and machine learning (Reinforcement Learning). Maintainer of Stable-Baselines (SB3).
https://araffin.github.io/
Research Engineer at Google DeepMind
A special snowflake existing in 196883 dimensions
#ActuallyAutistic He/Him
AGI research @DeepMind.
Ex cofounder & CTO Vicarious AI (acqd by Alphabet),
Cofounder Numenta
Triply EE (BTech IIT-Mumbai, MS&PhD Stanford). #AGIComics
blog.dileeplearning.com
Safe and robust AI/ML, computational sustainability. Former President AAAI and IMLS. Distinguished Professor Emeritus, Oregon State University. https://web.engr.oregonstate.edu/~tgd/
