English
Related papers

Related papers: Cut your Losses with Squentropy

200 papers

Cross-entropy loss is a common choice when it comes to multiclass classification tasks and language modeling in particular. Minimizing this loss results in language models of very good quality. We show that it is possible to fine-tune these…

Computation and Language · Computer Science 2019-01-16 Vadim Popov , Mikhail Kudinov

We introduce two-scale loss functions for use in various gradient descent algorithms applied to classification problems via deep neural networks. This new method is generic in the sense that it can be applied to a wide range of machine…

Numerical Analysis · Mathematics 2021-09-03 Leonid Berlyand , Robert Creese , Pierre-Emmanuel Jabin

We study empirical scaling laws for language model performance on the cross-entropy loss. The loss scales as a power-law with model size, dataset size, and the amount of compute used for training, with some trends spanning more than seven…

Multi-task learning (MTL) is an active field in deep learning in which we train a model to jointly learn multiple tasks by exploiting relationships between the tasks. It has been shown that MTL helps the model share the learned features…

Computer Vision and Pattern Recognition · Computer Science 2021-11-30 Akihiro Nakano , Shi Chen , Kazuyuki Demachi

Assisted by the availability of data and high performance computing, deep learning techniques have achieved breakthroughs and surpassed human performance empirically in difficult tasks, including object recognition, speech recognition, and…

Machine Learning · Computer Science 2019-01-23 Shaeke Salman , Xiuwen Liu

Metric learning seeks perceptual embeddings where visually similar instances are close and dissimilar instances are apart, but learned representations can be sub-optimal when the distribution of intra-class samples is diverse and distinct…

Machine Learning · Computer Science 2021-08-30 Elad Levi , Tete Xiao , Xiaolong Wang , Trevor Darrell

Two things seem to be indisputable in the contemporary deep learning discourse: 1. The categorical cross-entropy loss after softmax activation is the method of choice for classification. 2. Training a CNN classifier from scratch on small…

Machine Learning · Computer Science 2019-12-12 Björn Barz , Joachim Denzler

We describe an approach to improving model fitting and model generalization that considers the entropy of distributions of modelling residuals. We use simple simulations to demonstrate the observational signatures of overfitting on ordered…

Methodology · Statistics 2019-08-05 Barnaby Rowe

Most Neural Networks (NNs) for classification are trained using Cross-Entropy as a loss function. This approach requires the model to have an explicit classification layer. However, there exist alternative approaches, such as Contrastive…

Machine Learning · Computer Science 2026-04-27 Leonardo Arrighi , Julia Eva Belloni , Aurélie Gallet , Ivan Gentile , Matteo Lippi , Marco Zullich

This paper describes one objective function for learning semantically coherent feature embeddings in multi-output classification problems, i.e., when the response variables have dimension higher than one. In particular, we consider the…

Computer Vision and Pattern Recognition · Computer Science 2020-03-23 Hugo Proença , Ehsan Yaghoubi , Pendar Alirezazadeh

The paradigm of weak-to-strong generalization constitutes the training of a strong AI model on data labeled by a weak AI model, with the goal that the strong model nevertheless outperforms its weak supervisor on the target task of interest.…

Machine Learning · Computer Science 2025-02-05 Abhijeet Mulgund , Chirag Pabbaraju

Neural networks have dramatically increased our capacity to learn from large, high-dimensional datasets across innumerable disciplines. However, their decisions are not easily interpretable, their computational costs are high, and building…

Computer Vision and Pattern Recognition · Computer Science 2024-07-08 Mackenzie J. Meni , Ryan T. White , Michael Mayo , Kevin Pilkiewicz

Large Language Models (LLMs) have demonstrated impressive performance across various tasks. However, current training approaches combine standard cross-entropy loss with extensive data, human feedback, or ad hoc methods to enhance…

Computation and Language · Computer Science 2024-12-16 Daniele Rege Cambrin , Giuseppe Gallipoli , Irene Benedetto , Luca Cagliero , Paolo Garza

We introduce a new loss function TripleEntropy, to improve classification performance for fine-tuning general knowledge pre-trained language models based on cross-entropy and SoftTriple loss. This loss function can improve the robust…

Computation and Language · Computer Science 2022-11-28 Witold Sosnowski , Anna Wroblewska , Piotr Gawrysiak

Proper losses such as cross-entropy incentivize classifiers to produce class probabilities that are well-calibrated on the training data. Due to the generalization gap, these classifiers tend to become overconfident on the test data,…

Machine Learning · Computer Science 2025-08-27 Viacheslav Komisarenko , Meelis Kull

Classification algorithms in machine learning often assume a flat label space. However, most real world data have dependencies between the labels, which can often be captured by using a hierarchy. Utilizing this relation can help develop a…

Machine Learning · Computer Science 2020-06-09 Palash Goyal , Shalini Ghosh

Medical images commonly exhibit multiple abnormalities. Predicting them requires multi-class classifiers whose training and desired reliable performance can be affected by a combination of factors, such as, dataset size, data source,…

Image and Video Processing · Electrical Eng. & Systems 2021-11-16 Sivaramakrishnan Rajaraman , Ghada Zamzmi , Sameer Antani

Cross-entropy is a widely used loss function in applications. It coincides with the logistic loss applied to the outputs of a neural network, when the softmax is used. But, what guarantees can we rely on when using cross-entropy as a…

Machine Learning · Computer Science 2023-06-21 Anqi Mao , Mehryar Mohri , Yutao Zhong

While machine learning (ML) architectures have evolved rapidly to account for complex data, loss functions like cross-entropy remain mostly structure-agnostic in many real-world applications. However, the `class-symmetric' nature of these…

Machine Learning · Computer Science 2026-05-28 Yasser Taha , Grégoire Montavon , Nils Körber

State-of-the-art neural networks are vulnerable to adversarial examples; they can easily misclassify inputs that are imperceptibly different than their training and test data. In this work, we establish that the use of cross-entropy loss…

Machine Learning · Computer Science 2019-01-25 Kamil Nar , Orhan Ocal , S. Shankar Sastry , Kannan Ramchandran