Skip to content
conftrace_

normalized gradient descent

4 papers

Explore in graph

Also known as

NGD

Co-occurring keywords · papers mentioning both

rigid motion (1) quasiconvex optimization (1) trajectory clustering (1) hyperplane tracking (1) dynamic scene analysis (1) moving hyperplane (1) quasi-convex function (1) locally lipschitz function (1) neural network (1) gradient difference (1)

Papers

Unlearning as multi-task optimization: A normalized gradient difference approach with an adaptive learning rate NAACL 2025 Fast Convergence in Learning Two-Layer Neural Networks with Separable Data AAAI 2023 Beyond Convexity: Stochastic Quasi-Convex Optimization NeurIPS 2015 Online Clustering of Moving Hyperplanes NeurIPS 2006