English

The Sample Complexity of Parameter-Free Stochastic Convex Optimization

Machine Learning 2025-06-16 v1 Optimization and Control

Abstract

We study the sample complexity of stochastic convex optimization when problem parameters, e.g., the distance to optimality, are unknown. We pursue two strategies. First, we develop a reliable model selection method that avoids overfitting the validation set. This method allows us to generically tune the learning rate of stochastic optimization methods to match the optimal known-parameter sample complexity up to loglog\log\log factors. Second, we develop a regularization-based method that is specialized to the case that only the distance to optimality is unknown. This method provides perfect adaptability to unknown distance to optimality, demonstrating a separation between the sample and computational complexity of parameter-free stochastic convex optimization. Combining these two methods allows us to simultaneously adapt to multiple problem structures. Experiments performing few-shot learning on CIFAR-10 by fine-tuning CLIP models and prompt engineering Gemini to count shapes indicate that our reliable model selection method can help mitigate overfitting to small validation sets.

Keywords

Cite

@article{arxiv.2506.11336,
  title  = {The Sample Complexity of Parameter-Free Stochastic Convex Optimization},
  author = {Jared Lawrence and Ari Kalinsky and Hannah Bradfield and Yair Carmon and Oliver Hinder},
  journal= {arXiv preprint arXiv:2506.11336},
  year   = {2025}
}
R2 v1 2026-07-01T03:14:52.697Z