# Primal--Dual Alternating Neural Learning for Timely Classification with Performance Guarantees

arXiv: https://arxiv.org/abs/2608.23480 · HTML: https://mlsanity.com/paper/2608.23480/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 26 references that are in the map.
- First posted on arXiv 24 Aug 2026.

## Builds on (most cited first, 10 of 10)

- [Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling](https://mlsanity.com/paper/1412.3555/) (2014)
- [Estimating Dynamic Treatment Regimes in Mobile Health Using V-learning](https://mlsanity.com/paper/1611.03531/) (2016)
- [TEASER: Early and Accurate Time Series Classification](https://mlsanity.com/paper/1908.03405/) (2019)
- [Estimating Optimal Infinite Horizon Dynamic Treatment Regimes via pT-Learning](https://mlsanity.com/paper/2110.10719/) (2021)
- [Neyman-Pearson (NP) classification algorithms and NP receiver operating characteristics (NP-ROC)](https://mlsanity.com/paper/1608.03109/) (2016)
- [Deep Reinforcement Learning for Cost-Effective Medical Diagnosis](https://mlsanity.com/paper/2302.10261/) (2023)
- [Statistically Efficient Advantage Learning for Offline Reinforcement Learning in Infinite Horizons](https://mlsanity.com/paper/2202.13163/) (2022)
- [Early Classification of Time Series: A Survey and Benchmark](https://mlsanity.com/paper/2406.18332/) (2024)
- [Learning Optimal Dynamic Treatment Regimens Subject to Stagewise Risk Controls](https://mlsanity.com/paper/2212.12501/) (2022)
- [Learning the Optimal Stopping for Early Classification within Finite Horizons via Sequential Probability Ratio Test](https://mlsanity.com/paper/2501.18059/) (2025)

## Abstract (arXiv)

Timely risk classification is essential in many clinical monitoring settings, where decisions must balance the benefit of classifying patients early for subsequent intervention against the value of observing additional data. Yet most existing statistical and machine-learning methods are designed for fully observed trajectories and offer limited control over key operating characteristics such as sensitivity, specificity, and monitoring cost. We cast the sequential classification problem within a multi-objective optimization framework targeting these three criteria. We characterize the optimal decision rule through a value recursion that quantifies, at each time point, the trade-off between immediate classification and continued monitoring. To estimate the rule from data, we formulate a constrained optimization problem that maximizes specificity while enforcing prespecified sensitivity and monitoring-cost constraints. We then develop an estimation procedure that employs a recurrent neural network to approximate the evolving value processes and a primal--dual updating scheme to satisfy the performance constraints. Through simulation studies and an application to continuous glucose monitoring for hypoglycemia risk prediction, we demonstrate that the proposed method yields accurate and timely sequential decision rules that adhere to the desired operating characteristics.