# Accelerating Optimization via Adaptive Prediction

arXiv: https://arxiv.org/abs/1509.05760 · HTML: https://mlsanity.com/paper/1509.05760/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Sep 2015.

## Built on by (most cited first, 5 of 5)

- [Can Q-Learning be Improved with Advice?](https://mlsanity.com/paper/2110.13052/) (2021)
- [On Corruption-Robustness in Performative Reinforcement Learning](https://mlsanity.com/paper/2505.05609/) (2025)
- [Low-Regret Active learning](https://mlsanity.com/paper/2104.02822/) (2021)
- [Functional Acceleration for Policy Mirror Descent](https://mlsanity.com/paper/2407.16602/) (2024)
- [Acceleration in Policy Optimization](https://mlsanity.com/paper/2306.10587/) (2023)

## Abstract (arXiv)

We present a powerful general framework for designing data-dependent optimization algorithms, building upon and unifying recent techniques in adaptive regularization, optimistic gradient predictions, and problem-dependent randomization. We first present a series of new regret guarantees that hold at any time and under very minimal assumptions, and then show how different relaxations recover existing algorithms, both basic as well as more recent sophisticated ones. Finally, we show how combining adaptivity, optimism, and problem-dependent randomization can guide the design of algorithms that benefit from more favorable guarantees than recent state-of-the-art methods.