8 papers
Online Learning in the Random Order Model
Martino Bernasconi, Andrea Celli, Riccardo Colini-Baldeschi +3
In the random-order model for online learning, the sequence of losses is chosen upfront by an adversary and presented to the learner after a random permutation. Any random-order in…
Optimal Type-Dependent Liquid Welfare Guarantees for Autobidding Agents with Budgets
Riccardo Colini-Baldeschi, Sophie Klumper, Twan Kroll +3
Online advertising systems have recently transitioned to autobidding, allowing advertisers to delegate bidding decisions to automated agents. Each advertiser directs their agent to…
The Parity Ray Regularizer for Pacing in Auction Markets
Andrea Celli, Riccardo Colini-Baldeschi, Christian Kroer +1
Budget-management systems are one of the key components of modern auction markets. Internet advertising platforms typically offer advertisers the possibility to pace the rate at wh…
Stochastic Bandits for Multi-platform Budget Optimization in Online Advertising
Vashist Avadhanula, Riccardo Colini-Baldeschi, Stefano Leonardi +2
We study the problem of an online advertising system that wants to optimally spend an advertiser's given budget for a campaign across multiple platforms, without knowing the value…
Equilibria in Auctions With Ad Types
Hadi Elzayn, Riccardo Colini-Baldeschi, Brian Lan +1
This paper studies equilibrium quality of semi-separable position auctions (known as the Ad Types setting) with greedy or optimal allocation combined with generalized second-price…
Envy, Regret, and Social Welfare Loss
Riccardo Colini-Baldeschi, Stefano Leonardi, Okke Schrijvers +1
Incentive compatibility (IC) is one of the most fundamental properties of an auction mechanism, including those used for online advertising. Recent methods by Feng et al. and Lahai…