A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
Filters
Extended Stochastic Complexity and Minimax Relative Loss Analysis
[chapter]
1999
Lecture Notes in Computer Science
Preserved Fulltext
An eective performance measure is the minimax relative cumulative loss (RCL), which is the minimum of the worst-case dierence between the cumulative loss for any prediction algorithm and that for the best ...
We are concerned with the problem of sequential prediction using a given hypothesis class of continuously-many prediction strategies. ...
For any sequential prediction algorithm A, we dene the worst-case relative cumulative loss (RCL
is equivalent with the minimax regret (3). ...
doi:10.1007/3-540-46769-6_3
fatcat:bn7t5e36uvh4tnj233anr2khgm
Page 6621 of Mathematical Reviews Vol. , Issue 2001I
[page]
2001
Mathematical Reviews
Preserved Fulltext
The Internet Archive has digitized a microfilm copy of this work. It may be possible to borrow a copy for reading.
Warmuth, Tracking the best re- gressor (24-31 (electronic)); Kenji Yamanishi, Minimax relative loss analysis for sequential prediction algorithms using parametric hypotheses (32-43 (electronic)); John ...
(1-11 (electronic)); Nicold Cesa-Bianchi and Gabor Lugosi, Minimax regret under log loss for general classes of experts (12-18 (electronic)); Tsachy Weissman and Neri Merhay, On prediction of individual ...
Universal prediction
1998
IEEE Transactions on Information Theory
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
This paper consists of an overview on universal prediction from an information-theoretic perspective. ...
Special attention is given to the notion of probability assignment under the self-information loss function, which is directly related to the theory of universal data compression. ...
mechanism, which is useful for prediction. ...
doi:10.1109/18.720534
fatcat:iuadncat2nbvvbln5q3omquqxm
PAC-Bayes with Minimax for Confidence-Rated Transduction
[article]
2015
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
We derive minimax optimal rules for confidence-rated prediction in this setting. ...
We consider using an ensemble of binary classifiers for transductive prediction, when unlabeled test data are known in advance. ...
Conclusion We have presented an analysis of aggregating an ensemble for binary classification, using minimax worstcase techniques to formulate it as an game and suggest an optimal prediction strategy g ...
arXiv:1501.03838v1
fatcat:zk5o4sz2gfglbo3mpsobtbligy
Online Nonparametric Regression
[article]
2014
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
In addition to a non-algorithmic study of minimax regret, we exhibit a generic forecaster that enjoys the established optimal rates. ...
loss and online nonparametric regression are the same. ...
Any algorithm derived from the above schema using relaxation Rel n enjoys a bound Reg n ≤ 1 n Rel n (·) on regret. ...
arXiv:1402.2594v1
fatcat:vpfkepd2zjchvemp4ceu7iohl4
How the twain can meet: Prospect theory and models of heuristics in risky choice
2017
Cognitive Psychology
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
In computer simulations, we estimated CPT's parameters for choices produced by various heuristics. ...
Finally, we show, both in an empirical and a model recovery study, how CPT parameter profiles can be used to detect the operation of heuristics. ...
There are good arguments for either choice of range. The most important point is to consistently use one range within an analysis or to conduct a comparative analysis. ...
doi:10.1016/j.cogpsych.2017.01.001
pmid:28189037
fatcat:33q25zcpafgntphctvl3t6qp2m
Sequential (Quickest) Change Detection: Classical Results and New Directions
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
This survey starts with the basics of sequential change detection, and then moves on to generalizations and extensions of sequential change detection theory and methods. ...
Online detection of changes in stochastic systems, referred to as sequential change detection or quickest change detection, is an important research topic in statistics, signal processing, and information ...
ACKNOWLEDGEMENT The authors are grateful to the Guest Editor and the anonymous reviewers for their helpful comments. ...
arXiv:2104.04186v1
fatcat:ypxkrjyyf5dprpsc5b4kxxrnhm
Luckiness and Regret in Minimum Description Length Inference
[chapter]
2011
Philosophy of Statistics
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2011; you can also visit the original URL.
The file type is application/pdf.
We then discuss how data compression relates to performance in various learning tasks, including parameter estimation, parametric and nonparametric model selection and sequential prediction of outcomes ...
Minimum Description Length (MDL) inference is based on the intuition that understanding the available data can be defined in terms of the ability to compress the data, i.e. to describe it in full using ...
Prediction To use MDL for sequential prediction, we have to use codes that can be rendered as prequential forecasting systems. ...
doi:10.1016/b978-0-444-51862-0.50029-0
fatcat:ygm33cgeibfkpgb7m57lftxtju
Learning to learn from data: Using deep adversarial learning to construct optimal statistical procedures
2020
Science Advances
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
We use tools from deep learning to develop a new approach, adversarial Monte Carlo meta-learning, for constructing optimal statistical procedures. ...
Statistical problems are framed as two-player games in which Nature adversarially selects a distribution that makes it difficult for a statistician to answer the scientific question using data drawn from ...
Gilbert for helpful discussions. ...
doi:10.1126/sciadv.aaw2140
pmid:32166115
pmcid:PMC7051830
fatcat:7vc6actnljh7vdm5y6j3nzj5nq
Methodology and Application of Adaptive and Sequential Approaches in Contemporary Clinical Trials
2012
Journal of Probability and Statistics
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2015; you can also visit the original URL.
The file type is application/pdf.
Many adaptive and sequential approaches have been proposed for use in clinical trials to allow adaptations or modifications to aspects of a trial after its initiation without undermining the validity and ...
adaptive and sequential approaches and their applications in Phase I, II, and III clinical trials and discuss future directions in this field of research. ...
The design has two subtypes, optimal and minimax. ...
doi:10.1155/2012/527351
fatcat:lzi6aquxajepjjmovwa24uncd4
PAC-Bayesian aggregation and multi-armed bandits
[article]
2010
arXiv
pre-print
Preserved Fulltext
The Internet Archive has a preservation copy of this work in our general collections.
The file type is application/pdf.
This habilitation thesis presents several contributions to (1) the PAC-Bayesian analysis of statistical learning, (2) the three aggregation problems: given d functions, how to predict as well as (i) the ...
I would also like to thank Yuri Golubev for having accepted to participate and chair the habilitation committee. ...
Another solution is to use the exponentiated gradient algorithm introduced and studied by Kivinen and Warmuth [74] in the context of sequential prediction for the quadratic loss, and then extended to ...
arXiv:1011.3396v1
fatcat:oix5eiydzvat7oaqt6uwxxd6vy
A tutorial introduction to the minimum description length principle
[article]
2004
arXiv
pre-print
Preserved Fulltext
The Internet Archive has a preservation copy of this work in our general collections.
The file type is application/pdf.
It serves as a basis for the technical introduction given in the second chapter, in which all the ideas of the first chapter are made mathematically precise. ...
Log Loss for Universal Models Let M be some parametric model and letP be some universal model/code relative to M. What do the individual predictions P (X i | x i−1 ) look like? ...
prequential
probability
universal models,
non−predictive
including
use general
for log loss only
predictive
universal
models
with
log loss
universal models,
. ...
arXiv:math/0406077v1
fatcat:zhxexym4vbh2zpyko6pkawszly
Item Response Theory – A Statistical Framework for Educational and Psychological Measurement
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
The IRT models are latent factor models tailored to the analysis, interpretation, and prediction of individuals' behaviors in answering a set of measurement items that typically involve categorical response ...
We establish connections between item response theory and related topics in statistics, including empirical Bayes, nonparametric methods, matrix completion, regularized estimation, and sequential analysis ...
These models typically impose relatively strong parametric assumptions on the copula function. ...
arXiv:2108.08604v1
fatcat:4qkgd6wc4zfc3fn6zxy5mq2xsm
Active Learning: Problem Settings and Recent Developments
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2020 pre-print arXiv:2012.04225v1 fatcat:lgmbgfhub5gtdgntvn3cxwjt2y
In particular, research on learning acquisition functions to select samples from the data for labeling, theoretical work on active learning algorithms, and stopping criteria for sequential data acquisition ...
Active learning is a method of obtaining predictive models with high precision at a limited cost through the adaptive selection of samples for labeling. ...
Masanari Kimura for their valuable comments on the draft of this paper. ...
arXiv:2012.04225v2
fatcat:rbtg2kvi6vhj3odzayph4floum
Beyond UCB: Optimal and Efficient Contextual Bandits with Regression Oracles
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
We characterize the minimax rates for contextual bandits with general, potentially nonparametric function classes, and show that our algorithm is minimax optimal whenever the oracle obtains the optimal ...
We show how to transform any oracle for online regression with a given value function class into an algorithm for contextual bandits with the induced policy class, with no overhead in runtime or memory ...
Acknowledgements We thank Akshay Krishnamurthy and Haipeng Luo for helpful discussions. We acknowledge the support of ONR award #N00014-20-1-2336. ...
arXiv:2002.04926v2
fatcat:5iepwb62fjbmjjgd4y2bi6utku
« Previous
Showing results 1 — 15 out of 397 results