Fares Fourati
@faresfourati.bsky.social
PhD candidate at KAUST. Working on RL, bandits, and optimization.
fouratifares.github.io/website/
fouratifares.github.io/website/
🔹 Theoretically ECP is a no-regret algorithm.
🔹 Outperforms state-of-the-art algorithms, including Lipschitz, Bayesian, bandits, and evolutionary approaches.
📜 Paper: arxiv.org/abs/2502.042...
💻 Code: github.com/fouratifares... – try it out, and share your thoughts!
🔹 Outperforms state-of-the-art algorithms, including Lipschitz, Bayesian, bandits, and evolutionary approaches.
📜 Paper: arxiv.org/abs/2502.042...
💻 Code: github.com/fouratifares... – try it out, and share your thoughts!
arxiv.org
February 10, 2025 at 11:20 AM
🔹 Theoretically ECP is a no-regret algorithm.
🔹 Outperforms state-of-the-art algorithms, including Lipschitz, Bayesian, bandits, and evolutionary approaches.
📜 Paper: arxiv.org/abs/2502.042...
💻 Code: github.com/fouratifares... – try it out, and share your thoughts!
🔹 Outperforms state-of-the-art algorithms, including Lipschitz, Bayesian, bandits, and evolutionary approaches.
📜 Paper: arxiv.org/abs/2502.042...
💻 Code: github.com/fouratifares... – try it out, and share your thoughts!
🔹 ECP is optimized for expensive functions—excels with low function call budgets.
🔹 ECP is empirically tested across 30 multi-dimensional non-convex synthetic and real-world optimization problems.
🔹 ECP is empirically tested across 30 multi-dimensional non-convex synthetic and real-world optimization problems.
February 10, 2025 at 11:17 AM
🔹 ECP is optimized for expensive functions—excels with low function call budgets.
🔹 ECP is empirically tested across 30 multi-dimensional non-convex synthetic and real-world optimization problems.
🔹 ECP is empirically tested across 30 multi-dimensional non-convex synthetic and real-world optimization problems.
PhD candidate in RL. Can I join?
December 7, 2024 at 3:22 AM
PhD candidate in RL. Can I join?