# Tune My Adam, Please!

arXiv: https://arxiv.org/abs/2508.19733 · HTML: https://mlsanity.com/paper/2508.19733/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 18 references that are in the map.
- First posted on arXiv 27 Aug 2025.

## Builds on (most cited first, 15 of 15)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization](https://mlsanity.com/paper/1603.06560/) (2016)
- [Transformers Can Do Bayesian Inference](https://mlsanity.com/paper/2112.10510/) (2021)
- [Non-stochastic Best Arm Identification and Hyperparameter Optimization](https://mlsanity.com/paper/1502.07943/) (2015)
- [A System for Massively Parallel Hyperparameter Tuning](https://mlsanity.com/paper/1810.05934/) (2018)
- [Freeze-Thaw Bayesian Optimization](https://mlsanity.com/paper/1406.3896/) (2014)
- [Using a thousand optimization tasks to learn hyperparameter search strategies](https://mlsanity.com/paper/2002.11887/) (2020)
- [In-Context Freeze-Thaw Bayesian Optimization for Hyperparameter Optimization](https://mlsanity.com/paper/2404.16795/) (2024)
- [Scaling Laws for Hyperparameter Optimization](https://mlsanity.com/paper/2302.00441/) (2023)
- [Supervising the Multi-Fidelity Race of Hyperparameter Configurations](https://mlsanity.com/paper/2202.09774/) (2022)
- [Cost-Sensitive Multi-Fidelity Bayesian Optimization with Transfer of Learning Curve Extrapolation](https://mlsanity.com/paper/2405.17918/) (2024)

## Built on by (most cited first, 2 of 2)

- [Configuration-to-Performance Scaling Law with Neural Ansatz](https://mlsanity.com/paper/2602.10300/) (2026)
- [On the Nonlinearity of Learning Rate Scaling for LLM Training](https://mlsanity.com/paper/2606.29158/) (2026)

## Abstract (arXiv)

The Adam optimizer remains one of the most widely used optimizers in deep learning, and effectively tuning its hyperparameters is key to optimizing performance. However, tuning can be tedious and costly. Freeze-thaw Bayesian Optimization (BO) is a recent promising approach for low-budget hyperparameter tuning, but is limited by generic surrogates without prior knowledge of how hyperparameters affect learning. We propose Adam-PFN, a new surrogate model for Freeze-thaw BO of Adam's hyperparameters, pre-trained on learning curves from TaskSet, together with a new learning curve augmentation method, CDF-augment, which artificially increases the number of available training examples. Our approach improves both learning curve extrapolation and accelerates hyperparameter optimization on TaskSet evaluation tasks, with strong performance on out-of-distribution (OOD) tasks.