Online Mirror Descent
PulseAugur coverage of Online Mirror Descent — every cluster mentioning Online Mirror Descent across labs, papers, and developer communities, ranked by signal.
-
DiffNash uses diffusion models to find Nash equilibria in complex games
Researchers have developed DiffNash, a novel framework that utilizes diffusion models to compute Nash equilibria in high-dimensional continuous games. This approach addresses the limitations of conventional neural polic…
-
New optimization method achieves optimal rates for nonsmooth nonconvex composite problems
Researchers have developed a new method for stochastic nonsmooth nonconvex composite optimization, a problem relevant to training neural networks. This approach utilizes an online-to-nonconvex conversion framework, exte…
-
New framework for routing specialized AI models introduced
Researchers have introduced Multinomial Subset Routing (MSR), a novel online framework designed for routing tasks involving multiple specialized models. Unlike traditional methods that select a fixed subset of experts, …
-
New bandit algorithms tackle fairness and continuous K-Max problems · 6 sources tracked
Researchers have developed new algorithms for bandit problems, which are used in applications like recommendation systems. For continuous K-Max bandits, DCK-UCB achieves a sublinear regret bound of $\widetilde{O}(T^{3/4…
-
New research details approximation costs in Online Mirror Descent
A new paper explores the impact of approximation errors in Online Mirror Descent (OMD), a core algorithm for optimization and machine learning. The research reveals a complex relationship between the smoothness of the r…
-
Prudent-Banker algorithm ensures safety in delayed bandit feedback
Researchers have introduced Prudent-Banker, a new algorithm designed for adversarial multi-armed bandits that maintains safety guarantees even with delayed feedback. This novel approach combines a delay-adapted Online M…