activity
20162026
most citedInducing Neural Collapse in Imbalanced Learning: Do We Really Need a Learnable Classifier at the End of Deep Neural Network?

21 citations · 78 across the 16 of their papers we have counts for

collaborators
Showing 2026 · math.OCShow all

3 papers · 2 filters

math.OC2026

Polynomial Acceleration of Alternating Projections: Chebyshev Acceleration, Convergence Rates, and Retractions

Dengyu Zheng, Shixiang Chen

Alternating projections (AP) near a clean intersection of smooth manifolds can converge slowly when the Friedrichs angle is small. We develop the \emph{Fixed-Point Manifold Acceler…

math.OC2026

From Manifold Identification to Newton Acceleration on Intersections: Sparse Stiefel Optimization

Shixiang Chen, Wen Huang

We study a Newton acceleration for sparse composite optimization on the Stiefel manifold. The main difficulty is geometric: the active manifold identified by the nonsmooth regulari…

math.OC2026

Retractions by Alternating Projections

Shixiang Chen, Yixiao He, Wen Huang

Alternating projections and their variants are classical tools for computing points in intersections of sets. Existing analyses for smooth manifolds mainly focus on local convergen…