FLAT: Smoothing the Rugged Landscape for Learnable, Sample-Efficient Traffic Calibration
Abstract
Calibrating microscopic traffic models for digital twins is an expensive black-box optimization problem: tuning car-following and lane-changing parameters requires a full simulation run, affording only a tight budget per recalibration window. Matching raw trajectories yields a rugged objective that sparse surrogates cannot learn, reducing sequential acquisition to near-random probing. We present FLAT, which couples what to optimize with where to sample next. An eight-dimensional behavioral fingerprint smooths the parameter-error landscape, making the objective learnable from a few dozen samples; annealed lower-confidence-bound (LCB) acquisition then spends each remaining run where it most reduces error. The surrogate, interchangeable among a Gaussian process (GP), random forest (RF), or multi-layer-perceptron (MLP) ensemble, plugs into the same LCB loop. Across six heterogeneous real-world scenes, FLAT-GP achieves the lowest scene-averaged behavioral error, winning 6/6 scenes against SPSA, GA, and CMA-ES and 5/6 against TPE under the matched budget. Some baselines need up to 4.4 times more simulations to match. Ablations show objective choice shifts final behavioral error by 81% on average, removing sequential LCB raises the six-scene mean by 20%, and surrogate choice shifts it by at most 4.2%, confirming gains trace to objective geometry and sequential allocation rather than surrogate capacity.
Related
- ButterMamba: Butterworth-Enhanced Spatial-Temporal Mamba for Efficient Traffic Flow Prediction
- Quantum Fidelity Landscape-Guided Prior Calibration for Single-Circuit QGAN Image Generation
- PINN-LPCDD: Physics-Informed Neural Network with Learnable and Physically Consistent Domain Decomposition for Compressible Multi-Medium Flows
- Neural Network Fractional Quantum Hall States with Learnable Orbital Pair Matrix Factors: Balancing Physical Priors and Flexibility
- Learnable Splines for Unstructured Neural Operators
BibTeX
@misc{deng2026flat,
title = {{FLAT: Smoothing the Rugged Landscape for Learnable, Sample-Efficient Traffic Calibration}},
author = {Haopeng Deng and Shuo He and Dayuan Wang},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.04337},
eprint = {2610.04337},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.04337},
}
RIS
TY - UNPB
TI - FLAT: Smoothing the Rugged Landscape for Learnable, Sample-Efficient Traffic Calibration
AU - Haopeng Deng
AU - Shuo He
AU - Dayuan Wang
PY - 2026
DA - 2026/10/03
PB - arXiv
DO - 10.48550/arxiv.2610.04337
UR - https://arxiv.org/abs/2610.04337
AB - Calibrating microscopic traffic models for digital twins is an expensive black-box optimization problem: tuning car-following and lane-changing parameters requires a full simulation run, affording only a tight budget per recalibration window. Matching raw trajectories yields a rugged objective that sparse surrogates cannot learn, reducing sequential acquisition to near-random probing. We present FLAT, which couples what to optimize with where to sample next. An eight-dimensional behavioral fingerprint smooths the parameter-error landscape, making the objective learnable from a few dozen samples; annealed lower-confidence-bound (LCB) acquisition then spends each remaining run where it most reduces error. The surrogate, interchangeable among a Gaussian process (GP), random forest (RF), or multi-layer-perceptron (MLP) ensemble, plugs into the same LCB loop. Across six heterogeneous real-world scenes, FLAT-GP achieves the lowest scene-averaged behavioral error, winning 6/6 scenes against SPSA, GA, and CMA-ES and 5/6 against TPE under the matched budget. Some baselines need up to 4.4 times more simulations to match. Ablations show objective choice shifts final behavioral error by 81% on average, removing sequential LCB raises the six-scene mean by 20%, and surrogate choice shifts it by at most 4.2%, confirming gains trace to objective geometry and sequential allocation rather than surrogate capacity.
ER -