{"id":"2602.21436","title":"Efficient Uncoupled Learning Dynamics with $\\tilde{O}\\!\\left(T^{-1/4}\\right)$ Last-Iterate Convergence in Bilinear Saddle-Point Problems over Convex Sets under Bandit Feedback","url":"https://codeofpaper.com/paper/2602.21436","arxiv_url":"https://arxiv.org/abs/2602.21436","published":"2026-02-24","code":"none","best":null,"most_starred_community":null,"implementations":[],"possible_matches":0}