Scalable method for mean field control with kernel interactions via random Fourier features
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913153597571072 |
|---|---|
| author | Cao, Zhongyuan Das, Kaustav Langrené, Nicolas Laurière, Mathieu |
| author_facet | Cao, Zhongyuan Das, Kaustav Langrené, Nicolas Laurière, Mathieu |
| contents | We develop a scalable algorithm for mean field control problems with kernel interactions by combining particle system simulations with random Fourier feature approximations. The method replaces the quadratic-cost kernel evaluations by linear-time estimates, enabling efficient stochastic gradient descent for training feedback controls in large populations. We provide theoretical complexity bounds and demonstrate through crowd motion and flocking examples that the approach preserves control performance while substantially reducing computational cost. The results indicate that random feature approximations offer an effective and practical tool for high dimensional and large scale mean field control. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_01175 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Scalable method for mean field control with kernel interactions via random Fourier features Cao, Zhongyuan Das, Kaustav Langrené, Nicolas Laurière, Mathieu Optimization and Control 49N80, 60H35, 65C35, 42A38 G.3; G.1.6; G.1.2; F.2.1 We develop a scalable algorithm for mean field control problems with kernel interactions by combining particle system simulations with random Fourier feature approximations. The method replaces the quadratic-cost kernel evaluations by linear-time estimates, enabling efficient stochastic gradient descent for training feedback controls in large populations. We provide theoretical complexity bounds and demonstrate through crowd motion and flocking examples that the approach preserves control performance while substantially reducing computational cost. The results indicate that random feature approximations offer an effective and practical tool for high dimensional and large scale mean field control. |
| title | Scalable method for mean field control with kernel interactions via random Fourier features |
| topic | Optimization and Control 49N80, 60H35, 65C35, 42A38 G.3; G.1.6; G.1.2; F.2.1 |
| url | https://arxiv.org/abs/2601.01175 |