# Prediction-Powered Semi-Supervised Learning with Online Power Tuning

arXiv: https://arxiv.org/abs/2510.22586 · HTML: https://mlsanity.com/paper/2510.22586/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 41 references that are in the map.
- First posted on arXiv 26 Oct 2025.

## Builds on (most cited first, 29 of 29)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [Stochastic First- and Zeroth-order Methods for Nonconvex Stochastic Programming](https://mlsanity.com/paper/1309.5549/) (2013)
- [Using Self-Supervised Learning Can Improve Model Robustness and Uncertainty](https://mlsanity.com/paper/1906.12340/) (2019)
- [Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learning](https://mlsanity.com/paper/1908.02983/) (2019)
- [Age Progression/Regression by Conditional Adversarial Autoencoder](https://mlsanity.com/paper/1702.08423/) (2017)
- [In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learning](https://mlsanity.com/paper/2101.06329/) (2021)
- [Prediction-Powered Inference](https://mlsanity.com/paper/2301.09633/) (2023)
- [AdaGrad stepsizes: Sharp convergence over nonconvex landscapes](https://mlsanity.com/paper/1806.01811/) (2018)
- [Theoretical Analysis of Self-Training with Deep Networks on Unlabeled Data](https://mlsanity.com/paper/2010.03622/) (2020)
- [PPI++: Efficient Prediction-Powered Inference](https://mlsanity.com/paper/2311.01453/) (2023)
- [Graph-based Semi-supervised Learning: A Comprehensive Review](https://mlsanity.com/paper/2102.13303/) (2021)
- [Cross-Prediction-Powered Inference](https://mlsanity.com/paper/2309.16598/) (2023)
- [DASO: Distribution-Aware Semantics-Oriented Pseudo-label for Imbalanced Semi-Supervised Learning](https://mlsanity.com/paper/2106.05682/) (2021)
- [Theoretical Analysis of Weak-to-Strong Generalization](https://mlsanity.com/paper/2405.16043/) (2024)
- [Online to Offline Conversions, Universality and Adaptive Minibatch Sizes](https://mlsanity.com/paper/1705.10499/) (2017)
- [Semi-supervised Inference: General Theory and Estimation of Means](https://mlsanity.com/paper/1606.07268/) (2016)
- [Predictions as Surrogates: Revisiting Surrogate Outcomes in the Age of AI](https://mlsanity.com/paper/2501.09731/) (2025)
- [High-dimensional Analysis of Knowledge Distillation: Weak-to-Strong Generalization and Scaling Laws](https://mlsanity.com/paper/2410.18837/) (2024)
- [Self-training Converts Weak Learners to Strong Learners in Mixture Models](https://mlsanity.com/paper/2106.13805/) (2021)
- [Doubly Robust Self-Training](https://mlsanity.com/paper/2306.00265/) (2023)
- [On student-teacher deviations in distillation: does it pay to disobey?](https://mlsanity.com/paper/2301.12923/) (2023)
- [Knowledge Distillation Performs Partial Variance Reduction](https://mlsanity.com/paper/2305.17581/) (2023)
- [SLaM: Student-Label Mixing for Distillation with Unlabeled Examples](https://mlsanity.com/paper/2302.03806/) (2023)
- [Semi-Supervised Learning via Cross-Prediction-Powered Inference for Wireless Systems](https://mlsanity.com/paper/2405.15415/) (2024)
- [How Does Pseudo-Labeling Affect the Generalization Error of the Semi-Supervised Gibbs Algorithm?](https://mlsanity.com/paper/2210.08188/) (2022)
- [Dynamic Byzantine-Robust Learning: Adapting to Switching Byzantine Workers](https://mlsanity.com/paper/2402.02951/) (2024)

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

- [Uncertainty Quantification and Data Efficiency in AI: An Information-Theoretic Perspective](https://mlsanity.com/paper/2512.05267/) (2025)
- [Augmented Hypothesis Testing with Persona-Based LLM Simulations](https://mlsanity.com/paper/2609.24629/) (2026)
- [How Synthetic Labels Improve Conformal Prediction: A Perspective on Conditional Coverage](https://mlsanity.com/paper/2609.33482/) (2026)
- [ABC-Align: Prediction-Powered Alignment with Adaptive Bias Control](https://mlsanity.com/paper/2609.34374/) (2026)
- [How to Run Statistics over LLM Judges and Trust the Results: Calibrated Inference for Small-Sample AI Evaluation with evalstats](https://mlsanity.com/paper/2609.35815/) (2026)

## Abstract (arXiv)

Prediction-Powered Inference (PPI) is a recently proposed statistical inference technique for parameter estimation that leverages pseudo-labels on both labeled and unlabeled data to construct an unbiased, low-variance estimator. In this work, we extend its core idea to semi-supervised learning (SSL) for model training, introducing a novel unbiased gradient estimator. This extension addresses a key challenge in SSL: while unlabeled data can improve model performance, its benefit heavily depends on the quality of pseudo-labels. Inaccurate pseudo-labels can introduce bias, leading to suboptimal models.To balance the contributions of labeled and pseudo-labeled data, we utilize an interpolation parameter and tune it on the fly, alongside the model parameters, using a one-dimensional online learning algorithm. We verify the practical advantage of our approach through experiments on both synthetic and real datasets, demonstrating improved performance over classic SSL baselines and PPI methods that tune the interpolation parameter offline.