# PARWiS: Winner determination under shoestring budgets using active pairwise comparisons

arXiv: https://arxiv.org/abs/2603.01171 · HTML: https://mlsanity.com/paper/2603.01171/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 22 references that are in the map.
- First posted on arXiv 1 Mar 2026.

## Builds on (most cited first, 7 of 7)

- [Contextual Dueling Bandits](https://mlsanity.com/paper/1502.06362/) (2015)
- [Double Thompson Sampling for Dueling Bandits](https://mlsanity.com/paper/1604.07101/) (2016)
- [Spectral MLE: Top-K Rank Aggregation from Pairwise Comparisons](https://mlsanity.com/paper/1504.07218/) (2015)
- [Sparse Dueling Bandits](https://mlsanity.com/paper/1502.00133/) (2015)
- [Linear Contextual Bandits with Interference](https://mlsanity.com/paper/2409.15682/) (2024)
- [Fast online inference for nonlinear contextual bandit based on Generative Adversarial Network](https://mlsanity.com/paper/2202.08867/) (2022)
- [Scalable Bayesian Preference Learning for Crowds](https://mlsanity.com/paper/1912.01987/) (2019)

## Abstract (arXiv)

Determining a winner among a set of items using active pairwise comparisons under a limited budget is a challenging problem in preference-based learning. The goal of this study is to implement and evaluate the PARWiS algorithm, which shows spectral ranking and disruptive pair selection to identify the best item under shoestring budgets. This work have extended the PARWiS with a contextual variant (Contextual PARWiS) and a reinforcement learning-based variant (RL PARWiS), comparing them against baselines, including Double Thompson Sampling and a random selection strategy. This evaluation spans synthetic and real-world datasets (Jester and MovieLens), using budgets of 40, 60, and 80 comparisons for 20 items. The performance is measured through recovery fraction, true rank of reported winner, reported rank of true winner, and cumulative regret, alongside the separation metric (Delta1,2). Results show that PARWiS and RL PARWiS outperform baselines across all datasets, particularly in the Jester dataset with a higher (Delta1,2), while performance gaps narrow in the more challenging MovieLens dataset with a smaller (Delta1,2). Contextual PARWiS shows comparable performance to PARWiS, indicating that contextual features may require further tuning to provide significant benefits.