'Scaled Conjugate Gradient Method for Nonconvex Optimization in Deep Neural Networks', by Naoki Sato, Koshiro Izumi, Hideaki Iiduka.

http://jmlr.org/papers/v25/22-0815.html

#nonconvex #adversarial #inception

Scaled Conjugate Gradient Method for Nonconvex Optimization in Deep Neural Networks

'An Algorithm with Optimal Dimension-Dependence for Zero-Order Nonsmooth Nonconvex Stochastic Optimization', by Guy Kornowski, Ohad Shamir.

http://jmlr.org/papers/v25/23-1159.html

#optimization #nonconvex #optimal

An Algorithm with Optimal Dimension-Dependence for Zero-Order Nonsmooth Nonconvex Stochastic Optimization

'Convergence for nonconvex ADMM, with applications to CT imaging', by Rina Foygel Barber, Emil Y. Sidky.

http://jmlr.org/papers/v25/21-0831.html

#tomography #nonconvex #optimization

Convergence for nonconvex ADMM, with applications to CT imaging

`in this work, we study the stochastic multiagent minimax problem, which assumes nonconvexity over the primal variable and Polyak–Lojasiewicz (PL) over the dual variable. This setting encompasses #nonconvex strong-concavity as a subproblem. The PL setting has attracted wide interest recently because it has been shown to hold in the neighborhood of the minima for over-parameterized neural networks`

https://asl.epfl.ch/wp-content/uploads/2024/01/icassp_2024c.pdf

Online Min-max Problems with Non-convexity and Non-stationarity

Yu Huang, Yuan Cheng, Yingbin Liang, Longbo Huang

Action editor: Lijun Zhang.

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

#optimal #optimization #nonconvex

Online Min-max Problems with Non-convexity and Non-stationarity

Online min-max optimization has recently gained considerable interest due to its rich applications to game theory, multi-agent reinforcement learning, online robust learning, etc. Theoretical...

OpenReview