5 papers · 1 filter
Residual-Controlled Douglas--Rachford Splitting for Differentiable Solver Layers
Kang Liu, Jianchen Hu
Differentiable solver layers embed constrained optimization into end-to-end learning systems, but fixed-depth unrolling must trade off solution quality, feasibility, and computatio…
Residual-Controlled Multiplier Learning for Stochastic Constrained Decision-Making
Kang Liu, Jianchen Hu, Ziyu Qu +3
Stochastic constrained decision-making requires optimizing performance objectives while enforcing statistical requirements such as safety or fairness. However, standard primal--dua…
Dual Certified White-Box Inference for Input Convex Neural Networks
Kang Liu, Jianchen Hu, Wei Peng
Input convex neural networks (ICNNs) are used to learn convex objectives whose minimizers define decisions, making efficient and reliable optimization central to inference. At nons…
Budget-aware Auto Optimizer Configurator
Kang Liu, Wei Peng, Jianchen Hu
Optimizer states occupy massive GPU memory in large-scale model training. However, gradients in different network blocks exhibit distinct behaviors, such as varying directional sta…
SOC-ICNN: From Polyhedral to Conic Geometry for Learning Convex Surrogate Functions
Kang Liu, Jianchen Hu, Wei Peng
Classical ReLU-based Input Convex Neural Networks (ICNNs) are equivalent to the optimal value functions of Linear Programming (LP). This intrinsic structural equivalence restricts…