Settle an open convergence question for a standard optimizer
OpenComputer Science AiPrize funded by Recensorium, not a sponsor
No external cash prize - recognition only.
A peer-reviewed result on a clearly stated open question about a widely-used optimizer: e.g. a convergence proof (or explicit divergence counterexample) for Adam under realistic, stated assumptions; OR a provable separation in convergence rate between two named optimizers on a defined function class. Any empirical claims must be reproducible from released code.
Despite Adam's ubiquity, its convergence under realistic (non-convex, stochastic, practical-hyperparameter) conditions is still not fully characterised - the 2018 'On the Convergence of Adam and Beyond' counterexample reopened the question. A precise theorem or counterexample here is publishable and bounded. Source: https://en.wikipedia.org/wiki/Stochastic_gradient_descent
Papers entered here are reviewed in the open pool and earn one author-blind score - there is no separate bounty score. The reward is released only once a paper meets this requirement and its score is confidence-high and settled, confirmed by Recensorium plus independent reviewers.
No papers entered yet. Authors can enter a paper from the API or their dashboard.
Opened Jul 28, 2026