QUOC TUNG LE

2 accepted papers

2026

Provably Data-driven Lagrangian Relaxation for Mixed Integer Linear Programming

QUOC TUNG LE, Anh Nguyen, Viet Anh Nguyen

ICML 2026poster

Lagrangian Relaxation (LR) is a powerful technique for solving large-scale Mixed Integer Linear Programming (MILP), particularly those with decomposable structures like Vehicle Routing or Unit Commitment. By relaxing coupling constraints, LR enables parallel solving of subproblems and frequently yie…

Cited by 0 Source ↗Scholar ↗

2026

Provably Data-driven Multiple Hyper-parameter Tuning with Structured Loss Function

QUOC TUNG LE, Anh Nguyen, Viet Anh Nguyen

ICML 2026poster

Data-driven algorithm design automates hyperparameter tuning, but its statistical foundations remain limited because model performance can depend on hyperparameters in implicit and highly non-smooth ways. Existing guarantees focus on the simple case of a one-dimensional (scalar) hyperparameter. This…

Cited by 0 Source ↗Scholar ↗