Search Results for author:
Found 12 papers, 1 papers with code
Staying up to Date with Online Content Changes Using Reinforcement Learning for Scheduling
From traditional Web search engines to virtual assistants and Web accelerators, services that rely on online information need to continually keep track of remote content changes by explicitly requesting content updates from remote sources (e. g., web pages).
Multiplayer Bandit Learning, from Competition to Cooperation
We show that competing players explore less than a single player: there is $p^* \in (m, g)$ so that for all $p > p^*$, the players stay at the predictable arm.
Sorted Top-k in Rounds
When the comparisons are noiseless, we characterize how the optimal sample complexity depends on the number of rounds (up to a polylogarithmic factor for general $r$ and up to a constant factor for $r=1$ or 2).
Non-Stochastic Multi-Player Multi-Armed Bandits: Optimal Rate With Collision Information, Sublinear Without
We consider the non-stochastic version of the (cooperative) multi-player multi-armed bandit problem.
Online Learning with an Almost Perfect Expert
We study the multiclass online learning problem where a forecaster makes a sequence of predictions using the advice of $n$ experts.
Mixing time estimation in reversible Markov chains from a single sample path
The interval is constructed around the relaxation time $t_{\text{relax}} = 1/\gamma$, which is strongly related to the mixing time, and the width of the interval converges to zero roughly at a $1/\sqrt{n}$ rate, where $n$ is the length of the sample path.
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.
Bandit Convex Optimization: sqrt{T} Regret in One Dimension
We analyze the minimax regret of the adversarial bandit convex optimization problem.
Approval Voting and Incentives in Crowdsourcing
The growing need for labeled training data has made crowdsourcing an important part of machine learning.
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.
Online Learning with Composite Loss Functions
This class includes problems where the algorithm's loss is the minimum over the recent adversarial values, the maximum over the recent values, or a linear combination of the recent values.
Bandits with Switching Costs: T^{2/3} Regret
We prove that the player's $T$-round minimax regret in this setting is $\widetilde{\Theta}(T^{2/3})$, thereby closing a fundamental gap in our understanding of learning with bandit feedback.
