Monitoring anytime algorithms

Hansen, Eric A.; Zilberstein, Shlomo

doi:10.1145/242587.242593

Cited by 13 publications

(15 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In any anytime classifier, it is hard to know when users should interrupt an anytime algorithm to get the best-so-far answer since anytime algorithms provides us "a tradeoff between solution quality and computation time that has proved useful in applying artificial intelligence techniques to time-critical problems" [12]. We never know when algorithms should optimally be interrupted in advance.…”

mentioning

confidence: 99%

Anytime Classification Using the Nearest Neighbor Algorithm with Applications to Stream Mining

Ueno

Keogh

et al. 2006

Sixth International Conference on Data Mining (ICDM'06)

View full text Add to dashboard Cite

For many real world problems we must perform classification under widely varying amounts of computational resources. For example, if asked to classify an instance taken from a bursty stream, we may have from milliseconds to minutes to return a class prediction. For such problems an anytime algorithm may be especially useful.In this work we show how we can convert the ubiquitous nearest neighbor classifier into an anytime algorithm that can produce an instant classification, or if given the luxury of additional time, can utilize the extra time to increase classification accuracy. We demonstrate the utility of our approach with a comprehensive set of experiments on data from diverse domains.

show abstract

mentioning

confidence: 99%

Anytime Classification Using the Nearest Neighbor Algorithm with Applications to Stream Mining

Ueno

Keogh

et al. 2006

Sixth International Conference on Data Mining (ICDM'06)

View full text Add to dashboard Cite

show abstract

“…Compilation techniques described in [60], can be used to compile programs consisting of both anytime and traditional algorithms 13 . Hansen and Zilberstein [14] extend previous work on meta-level control of anytime algorithms by using a non-myopic stopping rule. It finds an intermediate strategy between continuous monitoring and not monitoring at all.…”

Section: Related Workmentioning

confidence: 82%

“…A decision to reschedule helps in two ways: it would preclude the agent from reaching a bad state in which too many resources are spent on a schedule with bad performance characteristics; and it would allow for meta-level activities to be processed without the detrimental effects such processing would have on domain activities if slack is minimal. Hansen's work [14] on meta-level control of anytime algorithms using a non-myopic stopping rule is described in Section 5. It finds an intermediate strategy between continuous monitoring and not monitoring at all.…”

Section: Meta-level Controllermentioning

confidence: 99%

See 1 more Smart Citation

A framework for meta-level control in multi-agent systems

Raja

Lesser

2007

Auton Agent Multi-Agent Syst

View full text Add to dashboard Cite

Sophisticated agents operating in open environments must make decisions that efficiently trade off the use of their limited resources between dynamic deliberative actions and domain actions. This is the meta-level control problem for agents operating in resource-bounded multi-agent environments. Control activities involve decisions on when to invoke and the amount to effort to put into scheduling and coordination of domain activities. The focus of this paper is how to make effective meta-level control decisions. We show that meta-level control with bounded computational overhead allows complex agents to solve problems more efficiently than current approaches in dynamic open multi-agent environments. The meta-level control approach that we present is based on the decision-theoretic use of an abstract representation of the agent state. This abstraction concisely captures critical information necessary for decision making while bounding the cost of meta-level control and is appropriate for use in automatically learning the meta-level control policies.

show abstract

“…Due to their utility in real-world settings, anytime algorithms have been extensively studied [11] and have found application in a number of diverse domains. Applications range from path planning in real time strategy games [3] to the clustering of time series [17].…”

Section: Background and Related Workmentioning

confidence: 99%

Polishing the Right Apple: Anytime Classification Also Benefits Data Streams with Constant Arrival Times

Shieh

Keogh

2010

2010 IEEE International Conference on Data Mining

View full text Add to dashboard Cite

Abstract-Classification of items taken from data streams requires algorithms that operate in time sensitive and computationally constrained environments. Often, the available time for classification is not known a priori and may change as a consequence of external circumstances. Many traditional algorithms are unable to provide satisfactory performance while supporting the highly variable response times that exemplify such applications. In such contexts, anytime algorithms, which are amenable to trading time for accuracy, have been found to be exceptionally useful and constitute an area of increasing research activity. Previous techniques for improving anytime classification have generally been concerned with optimizing the probability of correctly classifying individual objects. However, as we shall see, serially optimizing the probability of correctly classifying individual objects K times, generally gives inferior results to batch optimizing the probability of correctly classifying K objects. In this work, we show that this simple observation can be exploited to improve overall classification performance by using an anytime framework to allocate resources among a set of objects buffered from a fast arriving stream. Our ideas are independent of object arrival behavior; and, perhaps unintuitively, even in data streams with constant arrival rates our technique exhibits a marked improvement in performance. The utility of our approach is demonstrated with extensive experimental evaluations conducted on a wide range of diverse datasets.

show abstract

Monitoring anytime algorithms

Cited by 13 publications

References 12 publications

Anytime Classification Using the Nearest Neighbor Algorithm with Applications to Stream Mining

Anytime Classification Using the Nearest Neighbor Algorithm with Applications to Stream Mining

A framework for meta-level control in multi-agent systems

Polishing the Right Apple: Anytime Classification Also Benefits Data Streams with Constant Arrival Times

Contact Info

Product

Resources

About