# ASAP: Unsupervised Post-training with Label Distribution Shift Adaptive Learning Rate

arXiv: https://arxiv.org/abs/2508.13445 · HTML: https://mlsanity.com/paper/2508.13445/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 43 references that are in the map.
- First posted on arXiv 19 Aug 2025.

## Builds on (most cited first, 25 of 25)

- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Detecting and Correcting for Label Shift with Black Box Predictors](https://mlsanity.com/paper/1802.03916/) (2018)
- [Online Adaptation to Label Distribution Shift](https://mlsanity.com/paper/2107.04520/) (2021)
- [Test-Time Domain Adaptation by Learning Domain-Aware Batch Normalization](https://mlsanity.com/paper/2312.10165/) (2023)
- [DLTTA: Dynamic Learning Rate for Test-time Adaptation on Cross-domain Medical Images](https://mlsanity.com/paper/2205.13723/) (2022)
- [Adapting to Online Label Shift with Provable Guarantees](https://mlsanity.com/paper/2207.02121/) (2022)
- [Enhancing Zero-Shot Vision Models by Label-Free Prompt Distribution Learning and Bias Correcting](https://mlsanity.com/paper/2410.19294/) (2024)
- [Protected Test-Time Adaptation via Online Entropy Matching: A Betting Approach](https://mlsanity.com/paper/2408.07511/) (2024)
- [Label Shift Adapter for Test-Time Adaptation under Covariate and Label Shifts](https://mlsanity.com/paper/2308.08810/) (2023)
- [Fairness through Aleatoric Uncertainty](https://mlsanity.com/paper/2304.03646/) (2023)
- [Tolerant Algorithms for Learning with Arbitrary Covariate Shift](https://mlsanity.com/paper/2406.02742/) (2024)
- [Causality and Independence Enhancement for Biased Node Classification](https://mlsanity.com/paper/2310.09586/) (2023)
- [Online Label Shift: Optimal Dynamic Regret meets Practical Algorithms](https://mlsanity.com/paper/2305.19570/) (2023)
- [FuseFL: One-Shot Federated Learning through the Lens of Causality with Progressive Model Fusion](https://mlsanity.com/paper/2410.20380/) (2024)
- [Bridging Multicalibration and Out-of-distribution Generalization Beyond Covariate Shift](https://mlsanity.com/paper/2406.00661/) (2024)
- [One-Shot Sequential Federated Learning for Non-IID Data by Enhancing Local Model Diversity](https://mlsanity.com/paper/2404.12130/) (2024)
- [Generalizable Person Re-identification via Balancing Alignment and Uniformity](https://mlsanity.com/paper/2411.11471/) (2024)
- [Learning Fair Invariant Representations under Covariate and Correlation Shifts Simultaneously](https://mlsanity.com/paper/2408.09312/) (2024)
- [SAILOR: Structural Augmentation Based Tail Node Representation Learning](https://mlsanity.com/paper/2308.06801/) (2023)
- [MaxEnt Loss: Constrained Maximum Entropy for Calibration under Out-of-Distribution Shift](https://mlsanity.com/paper/2310.17159/) (2023)
- [On the Benefits of Public Representations for Private Transfer Learning under Distribution Shift](https://mlsanity.com/paper/2312.15551/) (2023)
- [Continual Learning in Predictive Autoscaling](https://mlsanity.com/paper/2307.15941/) (2023)
- [Class Distribution Shifts in Zero-Shot Learning: Learning Robust Representations](https://mlsanity.com/paper/2311.18575/) (2023)
- [CASUAL: Conditional Support Alignment for Domain Adaptation with Label Shift](https://mlsanity.com/paper/2305.18458/) (2023)
- [Fairness under Covariate Shift: Improving Fairness-Accuracy tradeoff with few Unlabeled Test Samples](https://mlsanity.com/paper/2310.07535/) (2023)

## Built on by (most cited first, 3 of 3)

- [Fed-ADE: Adaptive Learning Rate for Federated Post-adaptation under Distribution Shift](https://mlsanity.com/paper/2603.01040/) (2026)
- [Multi2: Hierarchical Multi-Agent Decision-Making with LLM-Based Agents in Interactive Environments](https://mlsanity.com/paper/2606.03698/) (2026)
- [Post-Hoc Merging is Not Enough: Many-Shot Model Merging with Loss-Gap Balancing](https://mlsanity.com/paper/2606.16501/) (2026)

## Abstract (arXiv)

In real-world applications, machine learning models face online label shift, where label distributions change over time. Effective adaptation requires careful learning rate selection: too low slows adaptation and too high causes instability. We propose ASAP (Adaptive Shift Aware Post-training), which dynamically adjusts the learning rate by computing the cosine distance between current and previous unlabeled outputs and mapping it within a bounded range. ASAP requires no labels, model ensembles, or past inputs, using only the previous softmax output for fast, lightweight adaptation. Experiments across multiple datasets and shift scenarios show ASAP consistently improves accuracy and efficiency, making it practical for unsupervised model adaptation.