Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2022
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2210.00422 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914014116708352 |
|---|---|
| author | Harchaoui, Zaid Oh, Sewoong Pal, Soumik Somani, Raghav Tripathi, Raghavendra |
| author_facet | Harchaoui, Zaid Oh, Sewoong Pal, Soumik Somani, Raghav Tripathi, Raghavendra |
| contents | We consider stochastic gradient descents on the space of large symmetric matrices of suitable functions that are invariant under permuting the rows and columns using the same permutation. We establish deterministic limits of these random curves as the dimensions of the matrices go to infinity while the entries remain bounded. Under a ``small noise'' assumption the limit is shown to be the gradient flow of functions on graphons whose existence was established in Oh, Somani, Pal, and Tripathi, \texit{J Theor Probab 37, 1469--1522 (2024)}. We also consider limits of stochastic gradient descents with added properly scaled reflected Brownian noise. The limiting curve of graphons is characterized by a family of stochastic differential equations with reflections and can be thought of as an extension of the classical McKean-Vlasov limit for interacting diffusions to the graphon setting. The proofs introduce a family of infinite-dimensional exchangeable arrays of reflected diffusions and a novel notion of propagation of chaos for large matrices of diffusions converging to such arrays in a suitable sense. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2210_00422 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | Stochastic optimization on matrices and a graphon McKean-Vlasov limit Harchaoui, Zaid Oh, Sewoong Pal, Soumik Somani, Raghav Tripathi, Raghavendra Probability Machine Learning 05C60, 05C63, 05C80, 68R10, 60K35, 60G09 We consider stochastic gradient descents on the space of large symmetric matrices of suitable functions that are invariant under permuting the rows and columns using the same permutation. We establish deterministic limits of these random curves as the dimensions of the matrices go to infinity while the entries remain bounded. Under a ``small noise'' assumption the limit is shown to be the gradient flow of functions on graphons whose existence was established in Oh, Somani, Pal, and Tripathi, \texit{J Theor Probab 37, 1469--1522 (2024)}. We also consider limits of stochastic gradient descents with added properly scaled reflected Brownian noise. The limiting curve of graphons is characterized by a family of stochastic differential equations with reflections and can be thought of as an extension of the classical McKean-Vlasov limit for interacting diffusions to the graphon setting. The proofs introduce a family of infinite-dimensional exchangeable arrays of reflected diffusions and a novel notion of propagation of chaos for large matrices of diffusions converging to such arrays in a suitable sense. |
| title | Stochastic optimization on matrices and a graphon McKean-Vlasov limit |
| topic | Probability Machine Learning 05C60, 05C63, 05C80, 68R10, 60K35, 60G09 |
| url | https://arxiv.org/abs/2210.00422 |