Author

Kang Liu

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Aug 2026

Residual-Controlled Douglas--Rachford Splitting for Differentiable Solver Layers

Differentiable solver layers embed constrained optimization into end-to-end learning systems, but fixed-depth unrolling must trade off solution quality, feasibility, and computational budget. We propose Residual-Controlled Douglas--Rachford Splitting (RCDRS), a differentiable solver layer for conic linear programs. RCD...

Kang Liu, Jianchen Hu · 0 citations

#machine learning Preprint Sep 2026

Equilibrium bias and convergence in augmented primal--dual dynamics with sampled constraints

This work studies the stability and convergence of augmented primal-dual dynamics when constraint values are estimated from samples. Unbiased constraint observations can produce a biased augmented multiplier signal, shifting the equilibria of the mean dynamics. For componentwise inequalities, we give a necessary and su...

Kang Liu, Meng-Xiao Chen, Si-Qin Xiong et al. · 0 citations