#stochastically — Public Fediverse posts

'The ODE Method for Stochastic Approximation and Reinforcement Learning with Markovian Noise', by Shuze Daniel Liu, Shuhang Chen, Shangtong Zhang.

http://jmlr.org/papers/v26/24-0100.html

#stochastic #stochastically #martingale

'Optimizing Noise for f-Differential Privacy via Anti-Concentration and Stochastic Dominance', by Jordan Awan, Aishwarya Ramasethu.

http://jmlr.org/papers/v25/23-1624.html

#privacy #stochastically #stochastic

Expected Worst Case Regret via Stochastic Sequential Covering

Changlong Wu, Mohsen Heidari, Ananth Grama, Wojciech Szpankowski

Action editor: Shinichi Nakajima.

https://openreview.net/forum?id=H1SekypXKA

#stochastically #stochastic #regret