logo
Loading...
Large-scale inverse learning of user equilibrium via multiconvex optimization
TransportationTransportation Research Part B: Methodological

Large-scale inverse learning of user equilibrium via multiconvex optimization

Z. Liu, Y. Yin, et al.

In research conducted by Zhichen Liu, Yafeng Yin, Xi Lin, and Zihao Wang, a scalable inverse learning framework is introduced for building context-dependent network equilibrium models from noisy link-flow data. The approach uses convex basis functions to learn the potential function directly from data, enabling GPU-accelerated estimation, consistent parameters, and travel patterns that adapt to context like day of week and weather.... show more
Abstract
This study proposes a scalable inverse learning framework for constructing context-dependent, nonparametric network equilibrium models from multiday noisy link-flow observations. Specifically, the potential function is parameterized as a nonnegative linear combination of convex bases. With a sufficiently rich set of basis functions, learning the nonnegative combination weights infers the functional form of the potential function directly from data. By replacing the context-dependent equilibrium constraints with well-defined, value-function-based suboptimality gap functions, this convex-basis-based parametrization allows a multiconvex inverse learning reformulation that can be decomposed and solved via a GPU-accelerated block coordinate descent algorithm. Moreover, the parametrized potential function incorporates context features (e.g., day of week, weather) and the learned model predicts user equilibria that vary with context rather than collapsing to a single average travel pattern. Under appropriate assumptions, this framework achieves asymptotically minimal fitting error and consistent parameter estimation. Synthetic and empirical experiments demonstrate the proposed framework's consistency and scalability.
Publisher
Transportation Research Part B: Methodological
Published On
Mar 30, 2026
Authors
Zhichen Liu, Yafeng Yin, Xi Lin, Zihao Wang
Tags
inverse learningnetwork equilibriumconvex basis functionscontext-dependent modelinglink-flow observationsGPU-accelerated optimizationsuboptimality gap
Listen, Learn & Level Up
Over 10,000 hours of research content in 25+ fields, available in 22+ languages.
No more digging through PDFs, just hit play and absorb the world's latest research in your language, on your time.
listen to research audio papers with researchbunny