OSNR applies matrix sketching to Newton-Raphson updates in online convex optimization to achieve sublinear dynamic regret with lower computational complexity across root finding, unconstrained, and constrained settings.
Study of the behaviour of
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
math.OC 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Robust learning problems are formulated as quasar-convex optimization, and HiPPA is proposed as an inexact high-order proximal method with global and superlinear convergence guarantees.
citing papers explorer
-
Online Sketched Newton-Raphson
OSNR applies matrix sketching to Newton-Raphson updates in online convex optimization to achieve sublinear dynamic regret with lower computational complexity across root finding, unconstrained, and constrained settings.
-
Robust Learning Meets Quasar-Convex Optimization: Inexact High-Order Proximal-Point Methods
Robust learning problems are formulated as quasar-convex optimization, and HiPPA is proposed as an inexact high-order proximal method with global and superlinear convergence guarantees.