# Adaptive Weighted Averaging

arXiv: https://arxiv.org/abs/2606.12763 · HTML: https://mlsanity.com/paper/2606.12763/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 27 references that are in the map.
- First posted on arXiv 11 Jun 2026.

## Builds on (most cited first, 6 of 6)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Convex Optimization: Algorithms and Complexity](https://mlsanity.com/paper/1405.4980/) (2014)
- [UniXGrad: A Universal, Adaptive Algorithm with Optimal Guarantees for Constrained Optimization](https://mlsanity.com/paper/1910.13857/) (2019)
- [Optimal Linear Decay Learning Rate Schedules and Further Refinements](https://mlsanity.com/paper/2310.07831/) (2023)
- [Online to Offline Conversions, Universality and Adaptive Minibatch Sizes](https://mlsanity.com/paper/1705.10499/) (2017)
- [Prophet Inequalities with Limited Information](https://mlsanity.com/paper/1307.3736/) (2013)

## Abstract (arXiv)

We study the problem of selecting the largest among n unknown values x1,dots,xn given only a single unbiased estimate yi for each xi. We design strategies that are simultaneously admissible (not uniformly dominated by any other strategy) and also never worse than a given baseline such as uniform random selection. We provide an application to stochastic optimization, where we obtain online-to-batch conversion bounds with a desirable "no-compromise" guarantee: they are never worse than standard random iterate selection, and yet can be significantly better in benign settings.