activity
20242026
collaborators

8 papers

cs.LG2026

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…

cs.LG2026

Exact Dual Geometry of SOC-ICNN Value Functions

Kang Liu, Jianchen Hu, Wei Peng

Input Convex Neural Networks (ICNNs) are commonly used in a two-stage manner: one first trains a convex network and then minimizes it over its input in a downstream inference probl…

cs.AI2026

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…

cs.LG2026

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…

cs.LG2025

OPBO: Order-Preserving Bayesian Optimization

Wei Peng, Jianchen Hu, Kang Liu +1

Bayesian optimization is an effective method for solving expensive black-box optimization problems. Most existing methods use Gaussian processes (GP) as the surrogate model for app…

cs.CV2025

Biomed-DPT: Dual Modality Prompt Tuning for Biomedical Vision-Language Models

Wei Peng, Kang Liu, Jianchen Hu +1

Prompt learning is one of the most effective paradigms for adapting pre-trained vision-language models (VLMs) to the biomedical image classification tasks in few shot scenarios. Ho…