The Experts below are selected from a list of 68343 Experts worldwide ranked by ideXlab platform
Benjamin Van Roy - One of the best experts on this subject based on the ideXlab platform.
-
an information Theoretic Analysis of thompson sampling for large action spaces
2018Co-Authors: Shi Dong, Benjamin Van RoyAbstract:Information-Theoretic Bayesian regret bounds of Russo and Van Roy capture the dependence of regret on prior uncertainty. However, this dependence is through entropy, which can become arbitrarily large as the number of actions increases. We establish new bounds that depend instead on a notion of rate-distortion. Among other things, this allows us to recover through information-Theoretic arguments a near-optimal bound for the linear bandit. We also offer a bound for the logistic bandit that dramatically improves on the best previously available, though this bound depends on an information-Theoretic statistic that we have only been able to quantify via computation.
-
an information Theoretic Analysis for thompson sampling with many actions
2018Co-Authors: Shi Dong, Benjamin Van RoyAbstract:Information-Theoretic Bayesian regret bounds of Russo and Van Roy capture the dependence of regret on prior uncertainty. However, this dependence is through entropy, which can become arbitrarily large as the number of actions increases. We establish new bounds that depend instead on a notion of rate-distortion. Among other things, this allows us to recover through information-Theoretic arguments a near-optimal bound for the linear bandit. We also offer a bound for the logistic bandit that dramatically improves on the best previously available, though this bound depends on an information-Theoretic statistic that we have only been able to quantify via computation.
-
an information Theoretic Analysis of thompson sampling
2016Co-Authors: Daniel Russo, Benjamin Van RoyAbstract:We provide an information-Theoretic Analysis of Thompson sampling that applies across a broad range of online optimization problems in which a decision-maker must learn from partial feedback. This Analysis inherits the simplicity and elegance of information theory and leads to regret bounds that scale with the entropy of the optimal-action distribution. This strengthens preexisting results and yields new insight into how information improves performance.
James S Schwaber - One of the best experts on this subject based on the ideXlab platform.
-
information Theoretic Analysis of pulmonary stretch receptor spike trains
2001Co-Authors: Robert F. Rogers, Jacob D Runyan, Ganesh A Vaidyanathan, James S SchwaberAbstract:Primary afferent neurons transduce physical, continuous stimuli into discrete spike trains. Investigators have long been interested in interpreting the meaning of the number or pattern of action po...
Urs Niesen - One of the best experts on this subject based on the ideXlab platform.
-
an information Theoretic Analysis of deduplication
2019Co-Authors: Urs NiesenAbstract:Deduplication finds and removes long-range data duplicates. It is commonly used in cloud and enterprise server settings and has been successfully applied to primary, backup, and archival storage. Despite its practical importance as a source-coding technique, its Analysis from the point of view of information theory is missing. This paper provides such an information-Theoretic Analysis of data deduplication. It introduces a new source model adapted to the deduplication setting. It formalizes the two standard fixed-length and variable-length deduplication schemes, and it introduces a novel multi-chunk deduplication scheme. It then provides an Analysis of these three deduplication variants, emphasizing the importance of boundary synchronization between source blocks and deduplication chunks. In particular, under fairly mild assumptions, the proposed multi-chunk deduplication scheme is shown to be order optimal.
-
an information Theoretic Analysis of deduplication
2017Co-Authors: Urs NiesenAbstract:Deduplication finds and removes long-range data duplicates. It is commonly used in cloud and enterprise server settings and has been successfully applied to primary, backup, and archival storage. Despite its practical importance as a source-coding technique, its Analysis from the point of view of information theory is missing. This paper provides such an information-Theoretic Analysis of data deduplication. It introduces a new source model adapted to the deduplication setting. It formalizes both fixed and variable-length deduplication schemes, and it introduces a novel, multi-chunk deduplication scheme. It then provides an Analysis of these three deduplication variants, emphasizing the importance of boundary synchronization between source blocks and deduplication chunks. The proposed multi-chunk deduplication scheme is shown to be order optimal under fairly mild assumptions.
Tyler Moore - One of the best experts on this subject based on the ideXlab platform.
-
game Theoretic Analysis of ddos attacks against bitcoin mining pools
2014Co-Authors: Benjamin Johnson, Aron Laszka, Jens Grossklags, Marie Vasek, Tyler MooreAbstract:One of the unique features of the digital currency Bitcoin is that new cash is introduced by so-called miners carrying out resource-intensive proof-of-work operations. To increase their chances of obtaining freshly minted bitcoins, miners typically join pools to collaborate on the computations. However, intense competition among mining pools has recently manifested in two ways. Miners may invest in additional computing resources to increase the likelihood of winning the next mining race. But, at times, a more sinister tactic is also employed: a mining pool may trigger a costly distributed denial-of-service (DDoS) attack to lower the expected success outlook of a competing mining pool. We explore the trade-off between these strategies with a series of game-Theoretical models of competition between two pools of varying sizes. We consider differences in costs of investment and attack, as well as uncertainty over whether a DDoS attack will succeed. By characterizing the game’s equilibria, we can draw a number of conclusions. In particular, we find that pools have a greater incentive to attack large pools than small ones. We also observe that larger mining pools have a greater incentive to attack than smaller ones.
Robert F. Rogers - One of the best experts on this subject based on the ideXlab platform.
-
information Theoretic Analysis of pulmonary stretch receptor spike trains
2001Co-Authors: Robert F. Rogers, Jacob D Runyan, Ganesh A Vaidyanathan, James S SchwaberAbstract:Primary afferent neurons transduce physical, continuous stimuli into discrete spike trains. Investigators have long been interested in interpreting the meaning of the number or pattern of action po...
