# Learning to Bid in Repeated Second-Price Auctions with Dynamic Values and Aggregated Feedback

arXiv: https://arxiv.org/abs/2605.28133 · HTML: https://mlsanity.com/paper/2605.28133/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 26 references that are in the map.
- First posted on arXiv 27 May 2026.

## Builds on (most cited first, 16 of 16)

- [Convex optimization](https://mlsanity.com/paper/2106.01946/) (2021)
- [Time-uniform, nonparametric, nonasymptotic confidence sequences](https://mlsanity.com/paper/1810.08240/) (2018)
- [Dual Mirror Descent for Online Allocation Problems](https://mlsanity.com/paper/2002.10421/) (2020)
- [Continuous-Time Model-Based Reinforcement Learning](https://mlsanity.com/paper/2102.04764/) (2021)
- [A Unifying Framework for Online Optimization with Long-Term Constraints](https://mlsanity.com/paper/2209.07454/) (2022)
- [Online learning in repeated auctions](https://mlsanity.com/paper/1511.05720/) (2015)
- [Reinforcement learning for linear-convex models with jumps via stability analysis of feedback controls](https://mlsanity.com/paper/2104.09311/) (2021)
- [Attribution Modeling Increases Efficiency of Bidding in Display Advertising](https://mlsanity.com/paper/1707.06409/) (2017)
- [Efficient Algorithms for Stochastic Repeated Second-price Auctions](https://mlsanity.com/paper/2011.05072/) (2020)
- [Incrementality Bidding via Reinforcement Learning under Mixed and Delayed Rewards](https://mlsanity.com/paper/2206.01293/) (2022)
- [Maximizing the Success Probability of Policy Allocations in Online Systems](https://mlsanity.com/paper/2312.16267/) (2023)
- [Incrementality Bidding and Attribution](https://mlsanity.com/paper/2208.12809/) (2022)
- [Fixed point label attribution for real-time bidding](https://mlsanity.com/paper/2012.01767/) (2020)
- [A pragmatic policy learning approach to account for users' fatigue in repeated auctions](https://mlsanity.com/paper/2407.10504/) (2024)
- [Non-Linear Counterfactual Aggregate Optimization](https://mlsanity.com/paper/2509.03438/) (2025)
- [Ads that Stick: Near-Optimal Ad Optimization through Psychological Behavior Models](https://mlsanity.com/paper/2509.20304/) (2025)

## Abstract (arXiv)

We study the problem of learning to bid when the bidder's value is dynamic, i.e., when the current value depends on past outcomes. Specifically, we consider a bidder participating in repeated second-price auctions whose value depends on the time elapsed since their last successful bid, with auctions arriving in continuous time and only aggregated feedback revealed at the end of the horizon. Such a bidder must (1) balance the immediate benefit of winning the current auction against its impact on future values and (2) learn unknown environmental parameters. We derive regret bounds for a class of learning methods that combine plug-in estimators with a differential-equation characterization of the optimal policy, and show that a specific confidence bound algorithm learns the optimal policy with a near optimal regret of widetildeO(log N) for piecewise linear primitives, and widetildeO(N1/3) for general, smooth primitives, achieving these regrets without explicit randomization. These theoretical results are supported by numerical experiments.