no code implementations • 12 Feb 2024 • Rachitesh Kumar, Jon Schneider, Balasubramanian Sivan
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.
no code implementations • 29 Jan 2024 • Guru Guruganesh, Yoav Kolumbus, Jon Schneider, Inbal Talgam-Cohen, Emmanouil-Vasileios Vlatakis-Gkaragkounis, Joshua R. Wang, S. Matthew Weinberg
We initiate the study of repeated contracts with a learning agent, focusing on agents who achieve no-regret outcomes.
no code implementations • NeurIPS 2023 • Jon Schneider, Julian Zimmert
In this setting, we resolve an open problem of Balseiro et al. by providing an efficient algorithm with a nearly tight (up to logarithmic factors) regret bound of $\widetilde{O}(\sqrt{TK})$, independent of the number of contexts.
no code implementations • 30 Jun 2023 • Robert Kleinberg, Renato Paes Leme, Jon Schneider, Yifeng Teng
We show that sublinear U-calibration error is a necessary and sufficient condition for all agents to achieve sublinear regret guarantees.
no code implementations • NeurIPS 2023 • William Brown, Jon Schneider, Kiran Vodrahalli
We show that this captures an extension of $\textit{Stackelberg}$ equilibria with a matching optimal value, and that there exists a wide class of games where a player can significantly increase their utility by deviating from a no-swap-regret algorithm against a no-swap learner (in fact, almost any game without pure Nash equilibria is of this form).
no code implementations • 3 Feb 2023 • Christoph Dann, Yishay Mansour, Mehryar Mohri, Jon Schneider, Balasubramanian Sivan
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.
no code implementations • 21 Oct 2022 • Hossein Esfandiari, Vahab Mirrokni, Jon Schneider
In this work, we present and study a new framework for online learning in systems with multiple users that provide user anonymity.
no code implementations • 15 Jun 2022 • Renato Paes Leme, Chara Podimata, Jon Schneider
We study the problem of contextual search in the adversarial noise model.
1 code implementation • 28 May 2022 • Jon Schneider, Kiran Vodrahalli
We then construct a history-restricted algorithm that achieves a per-round regret of $\Theta(1/\sqrt{M})$, which we complement with a tight lower bound.
no code implementations • 17 May 2022 • Yishay Mansour, Mehryar Mohri, Jon Schneider, Balasubramanian Sivan
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.
no code implementations • NeurIPS 2021 • Guru Guruganesh, Allen Liu, Jon Schneider, Joshua Wang
We consider the problem of multi-class classification, where a stream of adversarially chosen queries arrive and must be assigned a label online.
no code implementations • NeurIPS 2021 • Sreenivas Gollapudi, Guru Guruganesh, Kostas Kollias, Pasin Manurangsi, Renato Paes Leme, Jon Schneider
We design algorithms for this problem which achieve regret $O(d\log T)$ and $\exp(O(d \log d))$.
no code implementations • 2 Mar 2021 • Mark Braverman, Jon Schneider, S. Matthew Weinberg
We show that under these constraints, the auctioneer can attain a constant fraction of the "sell the business" benchmark, but no more than $2/e$ of this benchmark.
Computer Science and Game Theory Theoretical Economics
no code implementations • NeurIPS 2020 • Allen Liu, Renato Leme, Jon Schneider
Motivated by pricing applications in online advertising, we study a variant of linear regression with a discontinuous loss function that we term Myersonian regression.
no code implementations • 10 Sep 2020 • Negin Golrezaei, Vahideh Manshadi, Jon Schneider, Shreyas Sekar
We first show that existing learning algorithms---that are optimal in the absence of fake users---may converge to highly sub-optimal rankings under manipulation by fake users.
no code implementations • 11 Jun 2020 • Zhe Feng, Sébastien Lahaie, Jon Schneider, Jinchao Ye
The display advertising industry has recently transitioned from second- to first-price auctions as its primary mechanism for ad allocation and pricing.
no code implementations • 3 Mar 2020 • Allen Liu, Renato Paes Leme, Jon Schneider
We provide a generic algorithm with $O(d^2)$ regret where $d$ is the covering dimension of this class.
no code implementations • NeurIPS 2019 • Yuan Deng, Jon Schneider, Balasubramanian Sivan
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 $\varepsilon > 0$.
no code implementations • NeurIPS 2019 • Yuan Deng, Jon Schneider, Balusubramanian Sivan
How should a player who repeatedly plays a game against a no-regret learner strategize to maximize his utility?
no code implementations • NeurIPS 2018 • Jieming Mao, Renato Leme, Jon Schneider
For the symmetric loss $\ell(f(x_t), y_t) = \vert f(x_t) - y_t \vert$, we provide an algorithm for this problem achieving total loss $O(\log T)$ when $d=1$ and $O(T^{(d-1)/d})$ when $d>1$, and show that both bounds are tight (up to a factor of $\sqrt{\log T}$).
no code implementations • NeurIPS 2019 • Santiago Balseiro, Negin Golrezaei, Mohammad Mahdian, Vahab Mirrokni, Jon Schneider
We consider the variant of this problem where in addition to receiving the reward $r_{i, t}(c)$, the learner also learns the values of $r_{i, t}(c')$ for some other contexts $c'$ in set $\mathcal{O}_i(c)$; i. e., the rewards that would have been achieved by performing that action under different contexts $c'\in \mathcal{O}_i(c)$.
no code implementations • 9 Apr 2018 • Renato Paes Leme, Jon Schneider
We present an algorithm for the contextual search problem for the symmetric loss function $\ell(\theta, p) = |\theta - p|$ that achieves $O_{d}(1)$ total loss.
no code implementations • 25 Nov 2017 • Mark Braverman, Jieming Mao, Jon Schneider, S. Matthew Weinberg
- There exists a learning algorithm $\mathcal{A}$ such that if the buyer bids according to $\mathcal{A}$ then the optimal strategy for the seller is simply to post the Myerson reserve for $D$ every round.
no code implementations • 27 Jun 2017 • Mark Braverman, Jieming Mao, Jon Schneider, S. Matthew Weinberg
We study a strategic version of the multi-armed bandit problem, where each arm is an individual strategic agent and we, the principal, pull one arm each round.
no code implementations • 12 May 2016 • Xi Chen, Sivakanth Gopi, Jieming Mao, Jon Schneider
In particular, we present a linear time algorithm for the top-$K$ problem which has a competitive ratio of $\tilde{O}(\sqrt{n})$; i. e. to solve any instance of top-$K$, our algorithm needs at most $\tilde{O}(\sqrt{n})$ times as many samples needed as the best possible algorithm for that instance (in contrast, all previous known algorithms for the top-$K$ problem have competitive ratios of $\tilde{\Omega}(n)$ or worse).