Search Results for author:
Found 25 papers, 1 papers with code
Competitive analysis of the top-K ranking problem
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).
Multi-armed Bandit Problems with Strategic Arms
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.
Selling to a No-Regret Buyer
- 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.
Contextual Search via Intrinsic Volumes
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.
Contextual Bandits with Cross-learning
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 $c'\in \mathcal{O}_i(c)$.
Contextual Pricing for Lipschitz Buyers
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 $\sqrt{\log T}$).
Strategizing against No-regret Learners
How should a player who repeatedly plays a game against a no-regret learner strategize to maximize his utility?
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 $\varepsilon > 0$.
Optimal Contextual Pricing and Extensions
We provide a generic algorithm with $O(d^2)$ regret where $d$ is the covering dimension of this class.
Reserve Price Optimization for First Price Auctions
The display advertising industry has recently transitioned from second- to first-price auctions as its primary mechanism for ad allocation and pricing.
Learning Product Rankings Robust to Fake Users
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.
Myersonian Regression
Motivated by pricing applications in online advertising, we study a variant of linear regression with a discontinuous loss function that we term Myersonian regression.
Prior-free Dynamic Mechanism Design With Limited Liability
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
Contextual Recommendations and Low-Regret Cutting-Plane Algorithms
We design algorithms for this problem which achieve regret $O(d\log T)$ and $\exp(O(d \log d))$.
Margin-Independent Online Multiclass Learning via Convex Geometry
We consider the problem of multi-class classification, where a stream of adversarially chosen queries arrive and must be assigned a label online.
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.
History-Restricted Online Learning
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.
Corruption-Robust Contextual Search through Density Updates
We study the problem of contextual search in the adversarial noise model.
Anonymous Bandits for Multi-User Systems
In this work, we present and study a new framework for online learning in systems with multiple users that provide user anonymity.
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.
Is Learning in Games Good for the Learners?
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).
U-Calibration: Forecasting for an Unknown Agent
We show that sublinear U-calibration error is a necessary and sufficient condition for all agents to achieve sublinear regret guarantees.
Optimal cross-learning for contextual bandits with unknown context distributions
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.
Contracting with a Learning Agent
We initiate the study of repeated contracts with a learning agent, focusing on agents who achieve no-regret outcomes.
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.
