Search Results for author:
Found 9 papers, 0 papers with code
Strategically-Robust Learning Algorithms for Bidding in First-Price Auctions
Concretely, we show that our algorithms achieve $O(\sqrt{T})$ regret when the highest competing bids are generated adversarially, and show that no online algorithm can do better.
Pseudonorm Approachability and Applications to Regret Minimization
We then use that to show, modulo mild normalization assumptions, that there exists an $\ell_\infty$-approachability algorithm whose convergence is independent of the dimension of the original vectorial payoff.
Robust Budget Pacing with a Single Sample
Given the inherent non-stationarity in an advertiser's value and also competing advertisers' values over time, a commonly used approach is to learn a target expenditure plan that specifies a target spend as a function of time, and then run a controller that tracks this plan.
Strategizing against Learners in Bayesian Games
We study repeated two-player games where one of the players, the learner, employs a no-regret learning strategy, while the other, the optimizer, is a rational utility maximizer.
Analysis of Dual-Based PID Controllers through Convolutional Mirror Descent
As a byproduct of our proofs, we provide the first regret bound for CMD for non-smooth convex optimization, which might be of independent interest.
Learning to Price Against a Moving Target
In the Learning to Price setting, a seller posts prices over time with the goal of maximizing revenue while learning the buyer's valuation.
Prior-Free Dynamic Auctions with Low Regret Buyers
We show that even in this prior-free setting, it is possible to extract a $(1-\varepsilon)$-approximation of the full economic surplus for any $\varepsilon > 0$.
Tight Lower Bounds for Multiplicative Weights Algorithmic Families
We study the fundamental problem of prediction with expert advice and develop regret lower bounds for a large family of algorithms for this problem.
Towards Optimal Algorithms for Prediction with Expert Advice
Further, we show that the optimal algorithm for $2$ and $3$ experts is a probability matching algorithm (analogous to Thompson sampling) against a particular randomized adversary.
