English
Related papers

Related papers: Why does Throwing Away Data Improve Worst-Group Er…

200 papers

While discriminative classifiers often yield strong predictive performance, missing feature values at prediction time can still be a challenge. Classifiers may not behave as expected under certain ways of substituting the missing values,…

Machine Learning · Computer Science 2019-06-04 Pasha Khosravi , Yitao Liang , YooJung Choi , Guy Van den Broeck

We show that in language learning, contrary to received wisdom, keeping exceptional training instances in memory can be beneficial for generalization accuracy. We investigate this phenomenon empirically on a selection of benchmark natural…

Computation and Language · Computer Science 2007-05-23 Walter Daelemans , Antal van den Bosch , Jakub Zavrel

Natural language data follows a power-law distribution, with most knowledge and skills appearing at very low frequency. While a common intuition suggests that reweighting or curating data towards a uniform distribution may help models…

Artificial Intelligence · Computer Science 2026-04-28 Zixuan Wang , Xingyu Dang , Jason D. Lee , Kaifeng Lyu

Although many real-world applications, such as disease prediction, and fault detection suffer from class imbalance, most existing graph-based classification methods ignore the skewness of the distribution of classes; therefore, tend to be…

Machine Learning · Computer Science 2024-07-01 Mahdi Mohammadizadeh , Arash Mozhdehi , Yani Ioannou , Xin Wang

Plotting a learner's generalization performance against the training set size results in a so-called learning curve. This tool, providing insight in the behavior of the learner, is also practically valuable for model selection, predicting…

Machine Learning · Computer Science 2022-11-28 Marco Loog , Tom Viering

Heavy-tailed distributions are frequently used to enhance the robustness of regression and classification methods to outliers in output space. Often, however, we are confronted with "outliers" in input space, which are isolated observations…

Machine Learning · Statistics 2010-06-24 Fabian L. Wauthier , Michael I. Jordan

Virtually all machine learning tasks are characterized using some form of loss function, and "good performance" is typically stated in terms of a sufficiently small average loss, taken over the random draw of test data. While optimizing for…

Machine Learning · Statistics 2023-12-01 Matthew J. Holland , Kazuki Tanabe

An important aspect of large-scale structure data analysis is the presence of non-negligible theoretical uncertainties, which become increasingly important on small scales. We show how to incorporate these uncertainties in realistic power…

Cosmology and Nongalactic Astrophysics · Physics 2021-02-24 Anton Chudaykin , Mikhail M. Ivanov , Marko Simonović

Long-tailed data is a special type of multi-class imbalanced data with a very large amount of minority/tail classes that have a very significant combined influence. Long-tailed learning aims to build high-performance models on datasets with…

Machine Learning · Computer Science 2024-08-02 Chongsheng Zhang , George Almpanidis , Gaojuan Fan , Binquan Deng , Yanbo Zhang , Ji Liu , Aouaidjia Kamel , Paolo Soda , João Gama

In many machine learning for healthcare tasks, standard datasets are constructed by amassing data across many, often fundamentally dissimilar, sources. But when does adding more data help, and when does it hinder progress on desired model…

Machine Learning · Computer Science 2024-08-09 Judy Hanwen Shen , Inioluwa Deborah Raji , Irene Y. Chen

Deep neural networks still struggle on long-tailed image datasets, and one of the reasons is that the imbalance of training data across categories leads to the imbalance of trained model parameters. Motivated by the empirical findings that…

Computer Vision and Pattern Recognition · Computer Science 2022-12-06 Haoxuan Wang , Junchi Yan

The training datasets used in long-tailed recognition are extremely unbalanced, resulting in significant variation in per-class accuracy across categories. Prior works mostly used average accuracy to evaluate their algorithms, which easily…

Computer Vision and Pattern Recognition · Computer Science 2024-01-31 Hao Yu , Yingxiao Du , Jianxin Wu

It is impossible today to pretend that the practice of machine learning is always compatible with the idea that training and testing data follow the same distribution. Several authors have recently used ensemble techniques to show how…

Machine Learning · Computer Science 2025-03-03 Jianyu Zhang , Léon Bottou

Ex ante forecast outcomes should be interpreted as counterfactuals (potential histories), with errors as the spread between outcomes. Reapplying measurements of uncertainty about the estimation errors of the estimation errors of an…

Risk Management · Quantitative Finance 2012-09-12 Nassim N. Taleb

Learning theory has traditionally followed a model-centric approach, focusing on designing optimal algorithms for a fixed natural learning task (e.g., linear classification or regression). In this paper, we adopt a complementary…

Machine Learning · Computer Science 2025-04-29 Steve Hanneke , Shay Moran , Alexander Shlimovich , Amir Yehudayoff

In this paper, we study a simple and generic framework to tackle the problem of learning model parameters when a fraction of the training samples are corrupted. We first make a simple observation: in a variety of such settings, the…

Machine Learning · Computer Science 2019-02-20 Yanyao Shen , Sujay Sanghavi

The cross entropy loss is widely used due to its effectiveness and solid theoretical grounding. However, as training progresses, the loss tends to focus on hard to classify samples, which may prevent the network from obtaining gains in…

Machine Learning · Computer Science 2021-09-14 Barak Battash , Lior Wolf , Tamir Hazan

Outliers introduce significant training challenges in neural networks by propagating erroneous gradients, which can degrade model performance and generalization. We propose the Z-Error Loss, a statistically principled approach that…

Machine Learning · Computer Science 2025-06-04 Guillaume Godin

The study of loss function distributions is critical to characterize a model's behaviour on a given machine learning problem. For example, while the quality of a model is commonly determined by the average loss assessed on a testing set,…

Machine Learning · Computer Science 2023-06-06 Etrit Haxholli , Marco Lorenzi

While the {estimation} of risk is an important question in the daily business of banking and insurance, many existing plug-in estimation procedures suffer from an unnecessary bias. This often leads to the underestimation of risk and…

Risk Management · Quantitative Finance 2022-02-04 Marcin Pitera , Thorsten Schmidt
‹ Prev 1 3 4 5 6 7 10 Next ›