Moreau envelope
PulseAugur coverage of Moreau envelope — every cluster mentioning Moreau envelope across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
New Stochastic Penalty-Barrier Method for Constrained Machine Learning
Researchers have introduced the Stochastic Penalty-Barrier Method (SPBM), a novel approach for Constrained Machine Learning (CML). SPBM enhances classical methods by incorporating exponential averaging of dual variables…
-
New research quantifies theoretical limits of AI optimization algorithms · 2 sources tracked
Two new research papers explore the theoretical limits of optimization algorithms for nonconvex-strongly-concave and nonconvex-concave minimax problems. The first paper establishes a lower bound for stochastic algorithm…
-
New algorithms tackle nonconvex multi-objective bilevel optimization
Researchers have developed new Hessian-free algorithms, MOMEHA and MB-MOMEHA, to address multi-objective bilevel optimization problems, particularly those with nonconvex lower levels. These methods utilize the Moreau en…
-
New unified approach yields bounds for contractive stochastic approximation
Researchers have developed a novel, unified approach to establish mean-square and concentration bounds for stochastic approximation (SA) algorithms. This method addresses contractive mappings in arbitrary norms and mult…
-
New method targets stationary points in stochastic convex optimization
Researchers have developed a new method for finding stationary points in stochastic convex optimization problems. This approach aims for a stronger guarantee than previous methods, seeking to ensure the subdifferential …