On the Complexity of First-Order Methods in Stochastic Bilevel Optimization
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910326260236288 |
|---|---|
| author | Kwon, Jeongyeol Kwon, Dohyun Lyu, Hanbaek |
| author_facet | Kwon, Jeongyeol Kwon, Dohyun Lyu, Hanbaek |
| contents | We consider the problem of finding stationary points in Bilevel optimization when the lower-level problem is unconstrained and strongly convex. The problem has been extensively studied in recent years; the main technical challenge is to keep track of lower-level solutions $y^*(x)$ in response to the changes in the upper-level variables $x$. Subsequently, all existing approaches tie their analyses to a genie algorithm that knows lower-level solutions and, therefore, need not query any points far from them. We consider a dual question to such approaches: suppose we have an oracle, which we call $y^*$-aware, that returns an $O(ε)$-estimate of the lower-level solution, in addition to first-order gradient estimators {\it locally unbiased} within the $Θ(ε)$-ball around $y^*(x)$. We study the complexity of finding stationary points with such an $y^*$-aware oracle: we propose a simple first-order method that converges to an $ε$ stationary point using $O(ε^{-6}), O(ε^{-4})$ access to first-order $y^*$-aware oracles. Our upper bounds also apply to standard unbiased first-order oracles, improving the best-known complexity of first-order methods by $O(ε)$ with minimal assumptions. We then provide the matching $Ω(ε^{-6})$, $Ω(ε^{-4})$ lower bounds without and with an additional smoothness assumption on $y^*$-aware oracles, respectively. Our results imply that any approach that simulates an algorithm with an $y^*$-aware oracle must suffer the same lower bounds. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_07101 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | On the Complexity of First-Order Methods in Stochastic Bilevel Optimization Kwon, Jeongyeol Kwon, Dohyun Lyu, Hanbaek Optimization and Control Machine Learning We consider the problem of finding stationary points in Bilevel optimization when the lower-level problem is unconstrained and strongly convex. The problem has been extensively studied in recent years; the main technical challenge is to keep track of lower-level solutions $y^*(x)$ in response to the changes in the upper-level variables $x$. Subsequently, all existing approaches tie their analyses to a genie algorithm that knows lower-level solutions and, therefore, need not query any points far from them. We consider a dual question to such approaches: suppose we have an oracle, which we call $y^*$-aware, that returns an $O(ε)$-estimate of the lower-level solution, in addition to first-order gradient estimators {\it locally unbiased} within the $Θ(ε)$-ball around $y^*(x)$. We study the complexity of finding stationary points with such an $y^*$-aware oracle: we propose a simple first-order method that converges to an $ε$ stationary point using $O(ε^{-6}), O(ε^{-4})$ access to first-order $y^*$-aware oracles. Our upper bounds also apply to standard unbiased first-order oracles, improving the best-known complexity of first-order methods by $O(ε)$ with minimal assumptions. We then provide the matching $Ω(ε^{-6})$, $Ω(ε^{-4})$ lower bounds without and with an additional smoothness assumption on $y^*$-aware oracles, respectively. Our results imply that any approach that simulates an algorithm with an $y^*$-aware oracle must suffer the same lower bounds. |
| title | On the Complexity of First-Order Methods in Stochastic Bilevel Optimization |
| topic | Optimization and Control Machine Learning |
| url | https://arxiv.org/abs/2402.07101 |