# BanditLP: Large-Scale Stochastic Optimization for Personalized Recommendations

arXiv: https://arxiv.org/abs/2601.15552 · HTML: https://mlsanity.com/paper/2601.15552/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 45 references that are in the map.
- First posted on arXiv 22 Jan 2026.

## Builds on (most cited first, 21 of 21)

- [Laplace Redux -- Effortless Bayesian Deep Learning](https://mlsanity.com/paper/2106.14806/) (2021)
- [Scalable Bayesian Optimization Using Deep Neural Networks](https://mlsanity.com/paper/1502.05700/) (2015)
- [Bandits with Knapsacks](https://mlsanity.com/paper/1305.2545/) (2013)
- [Fairness-Aware Ranking in Search & Recommendation Systems with Application to LinkedIn Talent Search](https://mlsanity.com/paper/1905.01989/) (2019)
- [Neural Thompson Sampling](https://mlsanity.com/paper/2010.00827/) (2020)
- [Linear Stochastic Bandits Under Safety Constraints](https://mlsanity.com/paper/1908.05814/) (2019)
- ['In-Between' Uncertainty in Bayesian Neural Networks](https://mlsanity.com/paper/1906.11537/) (2019)
- [Open Bandit Dataset and Pipeline: Towards Realistic and Reproducible Off-Policy Evaluation](https://mlsanity.com/paper/2008.07146/) (2020)
- [Combinatorial Sleeping Bandits with Fairness Constraints](https://mlsanity.com/paper/1901.04891/) (2019)
- [EE-Net: Exploitation-Exploration Neural Networks in Contextual Bandits](https://mlsanity.com/paper/2110.03177/) (2021)
- [Multi-objective Bandits: Optimizing the Generalized Gini Index](https://mlsanity.com/paper/1706.04933/) (2017)
- [Safe Linear Stochastic Bandits](https://mlsanity.com/paper/1911.09501/) (2019)
- [A Neural Networks Committee for the Contextual Bandit Problem](https://mlsanity.com/paper/1409.8191/) (2014)
- [Multi-objective Contextual Multi-armed Bandit with a Dominant Objective](https://mlsanity.com/paper/1708.05655/) (2017)
- [Long-Term Value of Exploration: Measurements, Findings and Algorithms](https://mlsanity.com/paper/2305.07764/) (2023)
- [Thompson Sampling for Contextual Bandit Problems with Auxiliary Safety Constraints](https://mlsanity.com/paper/1911.00638/) (2019)
- [Thompson Sampling for Linearly Constrained Bandits](https://mlsanity.com/paper/2004.09258/) (2020)
- [Optimizing Scalable Targeted Marketing Policies with Constraints](https://mlsanity.com/paper/2312.01035/) (2023)
- [Efficient Vertex-Oriented Polytopic Projection for Web-scale Applications](https://mlsanity.com/paper/2103.05277/) (2021)
- [Measuring Fairness in Large-Scale Recommendation Systems with Missing Labels](https://mlsanity.com/paper/2406.05247/) (2024)
- [Beyond Basic A/B testing: Improving Statistical Efficiency for Business Growth](https://mlsanity.com/paper/2505.08128/) (2025)

## Built on by (most cited first, 1 of 1)

- [From Prediction to Incrementality: Causal Optimization for Large-Scale Targeting and Recommendation](https://mlsanity.com/paper/2608.10182/) (2026)

## Abstract (arXiv)

We present BanditLP, a scalable multi-stakeholder contextual bandit framework that unifies neural Thompson Sampling for learning objective-specific outcomes with a large-scale linear program for constrained action selection at serving time. The methodology is application-agnostic, compatible with arbitrary neural architectures, and deployable at web scale, with an LP solver capable of handling billions of variables. Experiments on public benchmarks and synthetic data show consistent gains over strong baselines. We apply this approach in LinkedIn's email marketing system and demonstrate business win, illustrating the value of integrated exploration and constrained optimization in production.