Skip to content
DraconiticResearch
Search Sources API
203,203 studies31 sourcesUpdated 8 min ago
PreprintarXiv licencearXiv

A Theoretical Analysis of a Bilevel Optimization Formulation for Combined Local-Global Optical Flow Models

  • El Mostafa Kalmoun
Open at sourcePDFDOICite

Abstract

This paper analyzes a bilevel formulation for learning the regularization parameter of combined local-global (CLG) optical flow models. The lower-level problem computes the flow from a Lucas--Kanade data term and a quadratic or total variation (TV) regularizer, and the upper-level problem selects the parameter that minimizes the squared distance to a ground-truth flow. The setting is finite-dimensional, and a full-rank assumption makes the lower-level solution unique. For the quadratic model we derive sufficient conditions for the existence of an optimal parameter, for every optimal parameter to be positive, and for strict local optimality. For TV regularization an optimal parameter always exists, because the lower-level solution vanishes for large parameters, and we give a sufficient condition for positivity that accounts for the coupling of the two flow components through the local structure tensors. Synthetic examples illustrate the conditions, including cases in which they fail.

Related

  1. Decision-focused predictions via pessimistic bilevel optimization: complexity and algorithms
    Víctor Bucarey López, Sophia Calderón, Gonzalo Muñoz +1
    Computational Optimization and ApplicationsPeer-reviewedLicence not statedCombinatorics & discrete mathematicsHAL
  2. Stochastic Nonconvex Bilevel Optimization: Improved Rates Without Rare-Visit Assumption
    Daniel Cortild, Mathias Staudigl, Juan Peypouquet +1
    arXivPreprintCC BY 4.0Full textOptimisation & controlarXiv
  3. Parametric Rates for Nonparametric Conditional-Moment Bilevel Optimization
    Fares El Khoury, Houssam Zenati, Nathan Kallus +2
    arXivPreprintCC BY 4.0Full textStatisticsarXiv
  4. An Ω(κy8ε−6) Lower Bound for Stochastic NC-SC Bilevel Optimization with First-order Oracles
    Zhihao Gu, Qilong Wu, Junchi Yang
    arXivPreprintarXiv licenceFull textOptimisation & controlarXiv
  5. Accelerating Finite-Sum Bilevel Optimization with Fully First-Order Oracles
    Qihao Zhou, Shanshui Niu
    arXivPreprintCC BY 4.0Full textOptimisation & controlStatisticsarXiv

Cite

BibTeXRIS
BibTeX
@misc{kalmoun2026theoretical,
  title = {{A Theoretical Analysis of a Bilevel Optimization Formulation for Combined Local-Global Optical Flow Models}},
  author = {El Mostafa Kalmoun},
  howpublished = {arXiv},
  year = {2026},
  month = nov,
  doi = {10.48550/arxiv.2611.08359},
  eprint = {2611.08359},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2611.08359},
}
RIS
TY  - UNPB
TI  - A Theoretical Analysis of a Bilevel Optimization Formulation for Combined Local-Global Optical Flow Models
AU  - El Mostafa Kalmoun
PY  - 2026
DA  - 2026/11/05
PB  - arXiv
DO  - 10.48550/arxiv.2611.08359
UR  - https://arxiv.org/abs/2611.08359
AB  - This paper analyzes a bilevel formulation for learning the regularization parameter of combined local-global (CLG) optical flow models. The lower-level problem computes the flow from a Lucas--Kanade data term and a quadratic or total variation (TV) regularizer, and the upper-level problem selects the parameter that minimizes the squared distance to a ground-truth flow. The setting is finite-dimensional, and a full-rank assumption makes the lower-level solution unique. For the quadratic model we derive sufficient conditions for the existence of an optimal parameter, for every optimal parameter to be positive, and for strict local optimality. For TV regularization an optimal parameter always exists, because the lower-level solution vanishes for large parameters, and we give a sufficient condition for positivity that accounts for the coupling of the two flow components through the local structure tensors. Synthetic examples illustrate the conditions, including cases in which they fail.
ER  -