ICML 2021spotlight4 citations

Debiasing a First-order Heuristic for Approximate Bi-level Optimization

Valerii Likhosherstov, Xingyou Song, Krzysztof Choromanski, Jared Q Davis, Adrian Weller

Abstract

Approximate bi-level optimization (ABLO) consists of (outer-level) optimization problems, involving numerical (inner-level) optimization loops. While ABLO has many applications across deep learning, it suffers from time and memory complexity proportional to the length $r$ of its inner optimization loop. To address this complexity, an earlier first-order method (FOM) was proposed as a heuristic which omits second derivative terms, yielding significant speed gains and requiring only constant memory. Despite FOM’s popularity, there is a lack of theoretical understanding of its convergence properties. We contribute by theoretically characterizing FOM’s gradient bias under mild assumptions. We further demonstrate a rich family of examples where FOM-based SGD does not converge to a stationary point of the ABLO objective. We address this concern by proposing an unbiased FOM (UFOM) enjoying constant memory complexity as a function of $r$. We characterize the introduced time-variance tradeoff, demonstrate convergence bounds, and find an optimal UFOM for a given ABLO problem. Finally, we propose an efficient adaptive UFOM scheme.

BibTeX
@InProceedings{pmlr-v139-likhosherstov21a,
  title = 	 {Debiasing a First-order Heuristic for Approximate Bi-level Optimization},
  author =       {Likhosherstov, Valerii and Song, Xingyou and Choromanski, Krzysztof and Davis, Jared Q and Weller, Adrian},
  booktitle = 	 {Proceedings of the 38th International Conference on Machine Learning},
  pages = 	 {6621--6630},
  year = 	 {2021},
  editor = 	 {Meila, Marina and Zhang, Tong},
  volume = 	 {139},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {18--24 Jul},
  publisher =    {PMLR},
  pdf = 	 {http://proceedings.mlr.press/v139/likhosherstov21a/likhosherstov21a.pdf},
  url = 	 {https://proceedings.mlr.press/v139/likhosherstov21a.html},
  abstract = 	 {Approximate bi-level optimization (ABLO) consists of (outer-level) optimization problems, involving numerical (inner-level) optimization loops. While ABLO has many applications across deep learning, it suffers from time and memory complexity proportional to the length $r$ of its inner optimization loop. To address this complexity, an earlier first-order method (FOM) was proposed as a heuristic which omits second derivative terms, yielding significant speed gains and requiring only constant memory. Despite FOM’s popularity, there is a lack of theoretical understanding of its convergence properties. We contribute by theoretically characterizing FOM’s gradient bias under mild assumptions. We further demonstrate a rich family of examples where FOM-based SGD does not converge to a stationary point of the ABLO objective. We address this concern by proposing an unbiased FOM (UFOM) enjoying constant memory complexity as a function of $r$. We characterize the introduced time-variance tradeoff, demonstrate convergence bounds, and find an optimal UFOM for a given ABLO problem. Finally, we propose an efficient adaptive UFOM scheme.}
}
Debiasing a First-order Heuristic for Approximate Bi-level Optimization · ICML 2021