English
Related papers

Related papers: Sample Efficient Model Evaluation

200 papers

We consider the problem of estimating the class prior in an unlabeled dataset. Under the assumption that an additional labeled dataset is available, the class prior can be estimated by fitting a mixture of class-wise data distributions to…

Machine Learning · Computer Science 2016-11-08 Marthinus C. du Plessis , Gang Niu , Masashi Sugiyama

In this paper, I proof that Importance Sampling estimates based on dependent sample sets are consistent under certain conditions. This can be used to reduce variance in Bayesian Models with factorizing likelihoods, using sample sets that…

Methodology · Statistics 2015-03-03 Ingmar Schuster

We introduce a new framework for sample-efficient model evaluation that we call active testing. While approaches like active learning reduce the number of labels needed for model training, existing literature largely ignores the cost of…

Machine Learning · Statistics 2021-06-15 Jannik Kossen , Sebastian Farquhar , Yarin Gal , Tom Rainforth

Annotated datasets are an essential ingredient to train, evaluate, compare and productionalize supervised machine learning models. It is therefore imperative that annotations are of high quality. For their creation, good quality management…

Machine Learning · Computer Science 2024-05-30 Jan-Christoph Klie , Juan Haladjian , Marc Kirchner , Rahul Nair

Experts classifying data are often imprecise. Recently, several models have been proposed to train classifiers using the noisy labels generated by these experts. How to choose between these models? In such situations, the true labels are…

Methodology · Statistics 2014-05-15 Rafael Izbicki , Rafael Bassi Stern

Supervised classification algorithms are used to solve a growing number of real-life problems around the globe. Their performance is strictly connected with the quality of labels used in training. Unfortunately, acquiring good-quality…

Machine Learning · Computer Science 2024-07-08 Daniel Kałuża , Andrzej Janusz , Dominik Ślęzak

We consider the problem of estimating how well a model class is capable of fitting a distribution of labeled data. We show that it is often possible to accurately estimate this "learnability" even when given an amount of data that is too…

Machine Learning · Computer Science 2019-03-26 Weihao Kong , Gregory Valiant

Learning from positive and unlabeled data (PU learning) is actively researched machine learning task. The goal is to train a binary classification model based on a training dataset containing part of positives which are labeled, and…

Machine Learning · Statistics 2023-12-29 Wojciech Rejchel , Paweł Teisseyre , Jan Mielniczuk

Traditional semi-supervised learning uses only labeled instances to train a classifier and then this classifier is utilized to classify unlabeled instances, while sometimes there are only positive instances which are elements of the target…

Machine Learning · Computer Science 2019-03-28 TingTing Li , WeiYa Fan , YunSong Luo

Importance sampling is often used in machine learning when training and testing data come from different distributions. In this paper we propose a new variant of importance sampling that can reduce the variance of importance sampling-based…

Machine Learning · Computer Science 2016-11-11 Philip S. Thomas , Emma Brunskill

Given a sample of size $N$, it is often useful to select a subsample of smaller size $n<N$ to be used for statistical estimation or learning. Such a data selection step is useful to reduce the requirements of data labeling and the…

Machine Learning · Statistics 2023-10-05 Germain Kolossov , Andrea Montanari , Pulkit Tandon

For many interesting tasks, such as medical diagnosis and web page classification, a learner only has access to some positively labeled examples and many unlabeled examples. Learning from this type of data requires making assumptions about…

Machine Learning · Computer Science 2018-08-28 Jessa Bekker , Jesse Davis

State-of-the-art machine learning models require access to significant amount of annotated data in order to achieve the desired level of performance. While unlabelled data can be largely available and even abundant, annotation process can…

Machine Learning · Computer Science 2020-10-15 Rahaf Aljundi , Nikolay Chumerin , Daniel Olmeda Reino

When a deep learning model is deployed in the wild, it can encounter test data drawn from distributions different from the training data distribution and suffer drop in performance. For safe deployment, it is essential to estimate the…

Machine Learning · Computer Science 2023-05-16 Jiefeng Chen , Frederick Liu , Besim Avci , Xi Wu , Yingyu Liang , Somesh Jha

In semi-supervised learning, the prevailing understanding suggests that observing additional unlabeled samples improves estimation accuracy for linear parameters only in the case of model misspecification. In this work, we challenge such a…

Methodology · Statistics 2025-09-03 Kai Chen , Yuqian Zhang

Data rebalancing techniques, including oversampling and undersampling, are a common approach to addressing the challenges of imbalanced data. To tackle unresolved problems related to both oversampling and undersampling, we propose a new…

Machine Learning · Computer Science 2025-07-11 Karen Medlin , Sven Leyffer , Krishnan Raghavan

We consider an active learning setting where the algorithm has access to a large pool of unlabeled data and a small pool of labeled data. In each iteration, the algorithm chooses few unlabeled data points and obtains their labels from an…

Machine Learning · Computer Science 2019-10-11 Muni Sreenivas Pydi , Vishnu Suresh Lokhande

Classification is an important task in many fields including biomedical research and machine learning. Traditionally, a classification rule is constructed based a bunch of labeled data. Recently, due to technological innovation and…

Methodology · Statistics 2014-06-19 Jing Wang , Eunsik Park , Yuan-chin Ivan Chang

Pairwise similarities and dissimilarities between data points might be easier to obtain than fully labeled data in real-world classification problems, e.g., in privacy-aware situations. To handle such pairwise information, an empirical risk…

Machine Learning · Computer Science 2019-04-29 Takuya Shimada , Han Bao , Issei Sato , Masashi Sugiyama

There has been increased interest in devising learning techniques that combine unlabeled data with labeled data ? i.e. semi-supervised learning. However, to the best of our knowledge, no study has been performed across various techniques…

Machine Learning · Computer Science 2011-09-12 N. V. Chawla , Grigoris Karakoulas