# Statistical Learning from Attribution Sets

arXiv: https://arxiv.org/abs/2602.06276 · HTML: https://mlsanity.com/paper/2602.06276/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 45 references that are in the map.
- First posted on arXiv 6 Feb 2026.

## Builds on (most cited first, 23 of 23)

- [Attention-based Deep Multiple Instance Learning](https://mlsanity.com/paper/1802.04712/) (2018)
- [Weakly-supervised Video Anomaly Detection with Robust Temporal Feature Magnitude Learning](https://mlsanity.com/paper/2101.10030/) (2021)
- [Online Learning under Delayed Feedback](https://mlsanity.com/paper/1306.0686/) (2013)
- [Real-Time Bidding by Reinforcement Learning in Display Advertising](https://mlsanity.com/paper/1701.02490/) (2017)
- [Real-Time Bidding with Multi-Agent Reinforcement Learning in Display Advertising](https://mlsanity.com/paper/1802.09756/) (2018)
- [Unbiased Multiple Instance Learning for Weakly Supervised Video Anomaly Detection](https://mlsanity.com/paper/2303.12369/) (2023)
- [Additive MIL: Intrinsically Interpretable Multiple Instance Learning for Pathology](https://mlsanity.com/paper/2206.01794/) (2022)
- [Optimized Cost per Click in Taobao Display Advertising](https://mlsanity.com/paper/1703.02091/) (2017)
- [Linear Bandits with Stochastic Delayed Feedback](https://mlsanity.com/paper/1807.02089/) (2018)
- [Stochastic Bandit Models for Delayed Conversions](https://mlsanity.com/paper/1706.09186/) (2017)
- [Display Advertising with Real-Time Bidding (RTB) and Behavioural Targeting](https://mlsanity.com/paper/1610.03013/) (2016)
- [Bid Optimization by Multivariable Control in Display Advertising](https://mlsanity.com/paper/1905.10928/) (2019)
- [Neural Auction: End-to-End Learning of Auction Mechanisms for E-Commerce Advertising](https://mlsanity.com/paper/2106.03593/) (2021)
- [Learning from Label Proportions by Learning with Label Noise](https://mlsanity.com/paper/2203.02496/) (2022)
- [Addressing Delayed Feedback for Continuous Training with Neural Networks in CTR prediction](https://mlsanity.com/paper/1907.06558/) (2019)
- [Easy Learning from Label Proportions](https://mlsanity.com/paper/2302.03115/) (2023)
- [Asymptotically Unbiased Estimation for Delayed Feedback Modeling via Label Correction](https://mlsanity.com/paper/2202.06472/) (2022)
- [PAC Learning Linear Thresholds from Label Proportions](https://mlsanity.com/paper/2310.10098/) (2023)
- [An extension of McDiarmid's inequality](https://mlsanity.com/paper/1511.05240/) (2015)
- [Optimistic Rates for Learning from Label Proportions](https://mlsanity.com/paper/2406.00487/) (2024)
- [See Beyond a Single View: Multi-Attribution Learning Leads to Better Conversion Rate Prediction](https://mlsanity.com/paper/2508.15217/) (2025)
- [Nearly Optimal Sample Complexity for Learning with Label Proportions](https://mlsanity.com/paper/2505.05355/) (2025)
- [Optimal Learning from Label Proportions with General Loss Functions](https://mlsanity.com/paper/2509.15145/) (2025)

## Abstract (arXiv)

We address the problem of training conversion prediction models in advertising domains under privacy constraints, where direct links between ad clicks and conversions are unavailable. Motivated by privacy-preserving browser APIs and the deprecation of third-party cookies, we study a setting where the learner observes a sequence of clicks and a sequence of conversions, but can only link a conversion to a set of candidate clicks (an attribution set) rather than a unique source. We formalize this as learning from attribution sets generated by an oblivious adversary equipped with a prior distribution over the candidates. Despite the lack of explicit labels, we construct an unbiased estimator of the population loss from these coarse signals via a novel approach. Leveraging this estimator, we show that Empirical Risk Minimization achieves generalization guarantees that scale with the informativeness of the prior and is also robust against estimation errors in the prior, despite complex dependencies among attribution sets. Simple empirical evaluations on standard datasets suggest our unbiased approach significantly outperforms common industry heuristics, particularly in regimes where attribution sets are large or overlapping.