English
Related papers

Related papers: AnyLoss: Transforming Classification Metrics into …

200 papers

Estimating the ratio of two probability densities from a finite number of observations is a central machine learning problem. A common approach is to construct estimators using binary classifiers that distinguish observations from the two…

Machine Learning · Computer Science 2025-01-28 Werner Zellinger

While neural network binary classifiers are often evaluated on metrics such as Accuracy and $F_1$-Score, they are commonly trained with a cross-entropy objective. How can this training-evaluation gap be addressed? While specific techniques…

Machine Learning · Computer Science 2022-06-03 Nathan Tsoi , Kate Candon , Deyuan Li , Yofti Milkessa , Marynel Vázquez

The adoption of deep learning across various fields has been extensive, yet there is a lack of focus on evaluating the performance of deep learning pipelines. Typically, with the increased use of large datasets and complex models, the…

Machine Learning · Computer Science 2024-05-21 Yewen Fan , Nian Si , Xiangchen Song , Kun Zhang

We consider learning to optimize a classification metric defined by a black-box function of the confusion matrix. Such black-box learning settings are ubiquitous, for example, when the learner only has query access to the metric of…

Machine Learning · Computer Science 2021-06-25 Gaurush Hiranandani , Jatin Mathur , Harikrishna Narasimhan , Mahdi Milani Fard , Oluwasanmi Koyejo

We construct a surrogate loss to directly optimise the significance metric used in particle physics. We evaluate our loss function for a simple event classification task using a linear model and show that it produces decision boundaries…

High Energy Physics - Phenomenology · Physics 2024-12-13 Jai Bardhan , Cyrin Neeraj , Subhadip Mitra , Tanumoy Mandal

Statistical decision problems lie at the heart of statistical machine learning. The simplest problems are binary and multiclass classification and class probability estimation. Central to their definition is the choice of loss function,…

Machine Learning · Computer Science 2023-08-21 Robert C. Williamson , Zac Cranko

Model calibration is essential for ensuring that the predictions of deep neural networks accurately reflect true probabilities in real-world classification tasks. However, deep networks often produce over-confident or under-confident…

Machine Learning · Computer Science 2025-04-01 Jinxu Lin , Linwei Tao , Minjing Dong , Chang Xu

Designing an effective loss function plays an important role in visual analysis. Most existing loss function designs rely on hand-crafted heuristics that require domain experts to explore the large design space, which is usually sub-optimal…

Computer Vision and Pattern Recognition · Computer Science 2019-08-15 Chuming Li , Yuan Xin , Chen Lin , Minghao Guo , Wei Wu , Wanli Ouyang , Junjie Yan

In this work we propose a novel concept of a hierarchical confusion matrix, opening the door for popular confusion matrix based (flat) evaluation measures from binary classification problems, while considering the peculiarities of…

Machine Learning · Computer Science 2024-02-14 Kevin Riehl , Michael Neunteufel , Martin Hemberg

In this paper, we develop upon the emerging topic of loss function learning, which aims to learn loss functions that significantly improve the performance of the models trained under them. Specifically, we propose a new meta-learning…

Machine Learning · Computer Science 2024-07-02 Christian Raymond , Qi Chen , Bing Xue , Mengjie Zhang

We consider sequential maximization of performance metrics that are general functions of a confusion matrix of a classifier (such as precision, F-measure, or G-mean). Such metrics are, in general, non-decomposable over individual instances,…

Machine Learning · Computer Science 2024-06-24 Wojciech Kotłowski , Marek Wydmuch , Erik Schultheis , Rohit Babbar , Krzysztof Dembczyński

An anomalous sound detection system to detect unknown anomalous sounds usually needs to be built using only normal sound data. Moreover, it is desirable to improve the system by effectively using a small amount of anomalous sound data,…

Sound · Computer Science 2021-06-14 Ibuki Kuroyanagi , Tomoki Hayashi , Kazuya Takeda , Tomoki Toda

Miscalibration - a mismatch between a model's confidence and its correctness - of Deep Neural Networks (DNNs) makes their predictions hard to rely on. Ideally, we want networks to be accurate, calibrated and confident. We show that, as…

Machine Learning · Computer Science 2020-10-27 Jishnu Mukhoti , Viveka Kulharia , Amartya Sanyal , Stuart Golodetz , Philip H. S. Torr , Puneet K. Dokania

Deep Metric Learning (DML) learns a non-linear semantic embedding from input data that brings similar pairs together while keeping dissimilar data away from each other. To this end, many different methods are proposed in the last decade…

Computer Vision and Pattern Recognition · Computer Science 2023-01-02 Davood Zabihzadeh , Zahraa Alitbi , Seyed Jalaleddin Mousavirad

Deep learning has proven to be a highly effective tool for a wide range of applications, significantly when leveraging the power of multi-loss functions to optimize performance on multiple criteria simultaneously. However, optimal selection…

Computer Vision and Pattern Recognition · Computer Science 2025-07-29 Amin Golnari , Mostafa Diba

Metric learning has become an attractive field for research on the latest years. Loss functions like contrastive loss, triplet loss or multi-class N-pair loss have made possible generating models capable of tackling complex scenarios with…

Machine Learning · Computer Science 2019-05-28 Alfonso Medela , Artzai Picon

Loss minimization is a dominant paradigm in machine learning, where a predictor is trained to minimize some loss function that depends on an uncertain event (e.g., "will it rain tomorrow?''). Different loss functions imply different…

Machine Learning · Computer Science 2021-09-14 Parikshit Gopalan , Adam Tauman Kalai , Omer Reingold , Vatsal Sharan , Udi Wieder

The confusion matrix is a standard tool for evaluating classifiers by providing insights into class-level errors. In heterogeneous settings, its values are shaped by two main factors: class similarity -- how easily the model confuses two…

Machine Learning · Computer Science 2026-03-31 Johan Erbani , Pierre-Edouard Portier , Elod Egyed-Zsigmond , Sonia Ben Mokhtar , Diana Nurbakova

This paper explores connections between margin-based loss functions and consistency in binary classification and regression applications. It is shown that a large class of margin-based loss functions for binary classification/regression…

Machine Learning · Statistics 2023-01-30 Jeffrey Buzas

We consider the problem of learning a loss function which, when minimized over a training dataset, yields a model that approximately minimizes a validation error metric. Though learning an optimal loss function is NP-hard, we present an…

Machine Learning · Computer Science 2019-07-02 Matthew Streeter