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.
Filters
Fast Rates for Online Prediction with Abstention
[article]
2020
arXiv
pre-print
Preserved Fulltext
We exactly characterize the dependence on the abstention cost c and the number of experts N by providing matching upper and lower bounds of order log N/1-2c, which is to be contrasted with the best possible ...
and the fast rates mentioned above, under some natural assumptions on the sequence of abstention costs. ...
The protocol of online binary prediction with abstentions For each round t = 1, 2, . . . , T , repeat: 1. ...
arXiv:2001.10623v2
fatcat:rllvzrcdxrarxi7ng64ub4huyy
Active learning from noisy and abstention feedback
2015
2015 53rd Annual Allerton Conference on Communication, Control, and Computing (Allerton)
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.
We provide a model for this setting where the abstention rate and the noise rate increase as we get closer to the decision boundary of the ground truth hypothesis. ...
We provide an algorithm and an analysis of the number of queries it makes to the labeling oracle; finally we provide matching lower bounds to demonstrate that our algorithm has near-optimal estimation ...
PRELIMINARIES We consider active learning for binary classification. ...
doi:10.1109/allerton.2015.7447165
dblp:conf/allerton/YanCJ15
fatcat:igz7ybcnwjbmhavkjzomn7r2ey
On the use of ROC analysis for the optimization of abstaining classifiers
2007
Machine Learning
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 2018; you can also visit the original URL.
The file type is application/pdf.
These classifiers are built based on optimization criteria in the following three models: cost-based, bounded-abstention and bounded-improvement. ...
We propose a method to optimally build a specific type of abstaining binary classifiers using ROC analysis. ...
In the bounded-abstention model, the boundary condition is the maximum abstention rate of the classifier, whereas in the bounded-improvement model, the boundary condition is the maximum misclassification ...
doi:10.1007/s10994-007-5013-y
fatcat:dwtoywoea5efhmf3n5hvva5kru
Consistency in models for distributed learning under communication constraints
2006
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.
Other Versions
For several basic communication models in both the binary classification and regression frameworks, we question the existence of agent decision rules and fusion rules that result in a universally consistent ...
The answers to this question present new issues to consider with regard to universal consistency. ...
In Sections III, and IV, we study the models for binary classification in communication with and without abstention, respectively. ...
doi:10.1109/tit.2005.860420
fatcat:rcxuu5m5svfrtjfpunwkzfyzoi
Towards optimally abstaining from prediction with OOD test examples
[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.
Other Versions
Our work builds on a recent abstention algorithm of Goldwasser, Kalais, and Montasser (2020) for transductive binary classification. ...
In particular, our transductive abstention algorithm takes labeled training examples and unlabeled test examples as input, and provides predictions with optimal prediction loss guarantees. ...
This implies E[ 1 + 2 ] ≤ Õ( d/n),
D Transductive bounds for binary classification with Q = P In this section, we bound the expected worst-case test error for binary classification, given training and ...
arXiv:2105.14119v2
fatcat:dj5lvmoqd5euznols6zzp5g4wa
MOBA: A multi-objective bounded-abstention model for two-class cost-sensitive problems
[article]
2019
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.
Specifically, the MOBA model minimizes the error rate of each class under class-dependent abstention constraints. ...
To overcome such problems, a multi-objective bounded-abstention (MOBA) model is proposed to optimize essential metrics. ...
The general classification rule with reject option in binary classification is shown in Eq. (1) and can be explained as follows. ...
arXiv:1905.07297v1
fatcat:khfqegggwnc55c742rmixlosmi
Structured Output Learning with Abstention: Application to Accurate Opinion Prediction
[article]
2018
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
Moreover, the abstention-aware representations can be used to competitively predict user-review ratings based on a sentence-level opinion predictor. ...
To compare fully labeled training data with predictions potentially containing abstentions, we define a wide class of asymmetric abstention-aware losses. ...
In Binary classification with abstention, we have Y = {0, 1} and the abstention-aware loss ∆ bin a is defined by : ∆ bin a (h(x), r(x), y) = 1 if y = h(x) and r(x) = 1 0 if y = h(x) and r(x) ...
arXiv:1803.08355v2
fatcat:yngxcievebbrvi2mph3esacy4m
Optimizing abstaining classifiers using ROC analysis
2005
Proceedings of the 22nd international conference on Machine learning - ICML '05
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.
These classifiers are built based on optimization criteria in the following three models: cost-based, bounded-abstention and bounded-improvement. ...
We propose a method to optimally build a specific type of abstaining binary classifiers using ROC analysis. ...
, 2000) ), the bounded-abstention model, and the bounded-improvement model. ...
doi:10.1145/1102351.1102435
dblp:conf/icml/Pietraszek05
fatcat:ovgctrvtcvhq7p4zzrs54hxczy
A General Framework for Abstention Under Label Shift
[article]
2022
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 2022; you can also visit the original URL.
The file type is application/pdf.
Other Versions
In this work, we present a general framework for abstention that can be applied to optimize any metric of interest, that is adaptable to label shift at test time, and that works out-of-the-box with any ...
Standard abstention methods tend to be focused on optimizing top-k accuracy, but in many applications, accuracy is not the metric of interest. ...
binary classification tasks) [Corces et al., 2016] . ...
arXiv:1802.07024v5
fatcat:i7dx6yhyjnfojll3lg6lihnz3y
Fast classification rates without standard margin assumptions
[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
Based on those results, we derive the necessary and sufficient conditions for classification (without a reject option) with fast rates in the agnostic setting achievable by improper learners. ...
First, we consider classification with a reject option, namely Chow's reject option model, and show that by slightly lowering the impact of hard instances, a learning rate of order O(d/nlogn/d) is always ...
Classification with a reject option (with abstentions). ...
arXiv:1910.12756v2
fatcat:e7cokll6mfeq3lwla4rbenlnma
Selective Ensembles for Consistent Predictions
[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.
low abstention rates. ...
On several benchmark datasets, selective ensembles reach zero inconsistently predicted points, with abstention rates as low 1.5%. ...
ACKNOWLEDGMENTS This work was developed with the support of NSF grant CNS-1704845, NSF CNS-1943016, as well as by DARPA and the Air Force Research Laboratory under agreement number FA8750-15-2-0277. ...
arXiv:2111.08230v1
fatcat:atlkwbmicna6xaya27fnoksiui
Consistency in Models for Communication Constrained Distributed Learning
[chapter]
2004
Lecture Notes in Computer Science
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 2005; you can also visit the original URL.
The file type is application/pdf.
., the asymptotics of several agent decision rules and fusion rules are considered in both binary classification and regression frameworks. ...
The agents are limited in their ability to communicate to a fusion center; the amount of information available for classification or regression is constrained. ...
Distributed Classification with Abstention: Stone's Theorem In this section, we show that the universal consistency of distributed classification with abstention follows immediately from Stone's Theorem ...
doi:10.1007/978-3-540-27819-1_31
fatcat:qnzykkyb6fe57ha45alxj2qkla
The Utility of Abstaining in Binary Classification
[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 explore the problem of binary classification in machine learning, with a twist - the classifier is allowed to abstain on any datum, professing ignorance about the true class label without committing ...
We review efficient algorithms with provable guarantees for each of these areas. ...
The Mistake Bound Model The Mistake Bound (MB) model [Lit88] for binary classification is a general framework for the study of online binary classification algorithms. ...
arXiv:1512.08133v1
fatcat:q7ekqcjdsnahnjmgpgpzdwqrba
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. ...
Introduction Modern applications of binary classification have recently driven renewed theoretical interest in the problem of confidence-rated prediction [1, 2, 3] . ...
arXiv:1501.03838v1
fatcat:zk5o4sz2gfglbo3mpsobtbligy
Abstaining Classification When Error Costs are Unequal and Unknown
[article]
2018
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.
Other Versions
In this paper, we propose a bounded-abstention method with two constraints of reject rates (BA2), which performs abstaining classification when error costs are unequal and unknown. ...
Meanwhile, BA2 achieves controllable reject rates of the positive and negative classes. ...
In this paper, we propose a ROC-based abstaining classification method, bounded-abstention with two constraints of reject rates (BA2), to overcome the limitations of using posterior probabilities and cost ...
arXiv:1806.03445v2
fatcat:ohy3mpd7sngzhjd3q6dthgu3hm
« Previous
Showing results 1 — 15 out of 570 results