English
Related papers

Related papers: On the Implicit Geometry of Cross-Entropy Paramete…

200 papers

Neural text classification models typically treat output labels as categorical variables which lack description and semantics. This forces their parametrization to be dependent on the label set size, and, hence, they are unable to scale to…

Computation and Language · Computer Science 2019-01-31 Nikolaos Pappas , James Henderson

Equivariant neural networks are designed to respect symmetries through their architecture, boosting generalization and sample efficiency when those symmetries are present in the data distribution. Real-world data, however, often departs…

Machine Learning · Computer Science 2025-12-12 Andrei Manolache , Luiz F. O. Chamon , Mathias Niepert

Understanding the geometry of neural network loss landscapes is a central question in deep learning, with implications for generalization and optimization. A striking phenomenon is linear mode connectivity (LMC), where independently trained…

Machine Learning · Computer Science 2025-11-14 Alexander Theus , Alessandro Cabodi , Sotiris Anagnostidis , Antonio Orvieto , Sidak Pal Singh , Valentina Boeva

Automatic annotation of large-scale datasets can introduce noisy training data labels, which adversely affect the learning process of deep neural networks (DNNs). Consequently, Noisy Labels Learning (NLL) has become a critical research…

Computer Vision and Pattern Recognition · Computer Science 2024-10-08 Maria Marrium , Arif Mahmood , Mohammed Bennamoun

We present a method for training multi-label, massively multi-class image classification models, that is faster and more accurate than supervision via a sigmoid cross-entropy loss (logistic regression). Our method consists in embedding…

Computer Vision and Pattern Recognition · Computer Science 2016-07-20 François Chollet

The widely-used cross-entropy (CE) loss-based deep networks achieved significant progress w.r.t. the classification accuracy. However, the CE loss can essentially ignore the risk of misclassification which is usually measured by the…

Computer Vision and Pattern Recognition · Computer Science 2021-05-04 Yubin Ge , Site Li , Xuyang Li , Fangfang Fan , Wanqing Xie , Jane You , Xiaofeng Liu

Pretrained encoders for mathematical texts have achieved significant improvements on various tasks such as formula classification and information retrieval. Yet they remain limited in representing and capturing student strategies for entire…

Computers and Society · Computer Science 2026-04-13 Siddhartha Pradhan , Ethan Prihar , Erin Ottmar

Modern deep neural networks are highly over-parameterized compared to the data on which they are trained, yet they often generalize remarkably well. A flurry of recent work has asked: why do deep networks not overfit to their training data?…

Machine Learning · Computer Science 2023-03-24 Minyoung Huh , Hossein Mobahi , Richard Zhang , Brian Cheung , Pulkit Agrawal , Phillip Isola

Network embedding, aiming to project a network into a low-dimensional space, is increasingly becoming a focus of network research. Semi-supervised network embedding takes advantage of labeled data, and has shown promising performance.…

Machine Learning · Computer Science 2025-08-05 Zheng Wang , Xiaojun Ye , Chaokun Wang , Jian Cui , Philip S. Yu

Training accurate deep neural networks (DNNs) in the presence of noisy labels is an important and challenging task. Though a number of approaches have been proposed for learning with noisy labels, many open issues remain. In this paper, we…

Machine Learning · Computer Science 2019-08-20 Yisen Wang , Xingjun Ma , Zaiyi Chen , Yuan Luo , Jinfeng Yi , James Bailey

Recent advances in the LLM-as-Extractor paradigm leverage large language models (LLMs) to transfer semantically rich item embeddings into sequential recommendation (SR) backbones. However, LLM-generated embeddings often suffer from strong…

Information Retrieval · Computer Science 2026-05-29 Dongcheol Lee , Hye-young Kim , Jongwuk Lee

Recently, substantial research efforts in Deep Metric Learning (DML) focused on designing complex pairwise-distance losses, which require convoluted schemes to ease optimization, such as sample mining or pair weighting. The standard…

Machine Learning · Computer Science 2021-11-29 Malik Boudiaf , Jérôme Rony , Imtiaz Masud Ziko , Eric Granger , Marco Pedersoli , Pablo Piantanida , Ismail Ben Ayed

Transductive graph-based semi-supervised learning methods usually build an undirected graph utilizing both labeled and unlabeled samples as vertices. Those methods propagate label information of labeled samples to neighbors through their…

Machine Learning · Computer Science 2013-12-25 Fengqi Li , Chuang Yu , Nanhai Yang , Feng Xia , Guangming Li , Fatemeh Kaveh-Yazdy

Learning from imbalanced data is one of the most significant challenges in real-world classification tasks. In such cases, neural networks performance is substantially impaired due to preference towards the majority class. Existing…

Machine Learning · Computer Science 2022-11-13 Bronislav Yasinnik , Moshe Salhov , Ofir Lindenbaum , Amir Averbuch

Foundational Models pretrained on huge amount of data learn representations that evolve across depth, forming a hierarchy of embeddings with distinct semantic content and geometric structure. Contrary to the widespread practice of using…

Machine Learning · Computer Science 2026-05-25 Arnesh Batra , Arush Gumber , Aniket Khandelwal , Jashn Khemani , Anubha Gupta

In this paper, we leverage over-parameterization to design regularization-free algorithms for the high-dimensional single index model and provide theoretical guarantees for the induced implicit regularization phenomenon. Specifically, we…

Machine Learning · Statistics 2021-11-18 Jianqing Fan , Zhuoran Yang , Mengxin Yu

Estimating causal treatment effects in observational settings is frequently compromised by selection bias arising from unobserved confounders. While traditional econometric methods struggle when these confounders are orthogonal to…

Artificial Intelligence · Computer Science 2026-01-06 Ahmed Dawoud , Osama El-Shamy

The generalization gap on the long-tailed data sets is largely owing to most categories only occupying a few training samples. Decoupled training achieves better performance by training backbone and classifier separately. What causes the…

Computer Vision and Pattern Recognition · Computer Science 2023-03-13 Zhiwei Zhang

Labeling a training set is often expensive and susceptible to errors, making the design of robust loss functions for label noise an important problem. The symmetry condition provides theoretical guarantees for robustness to such noise. In…

Machine Learning · Computer Science 2026-05-21 Alexandre Lemire Paquin , Brahim Chaib-Draa , Philippe Giguère

A key challenge in machine learning is to explain how learning dynamics select among the many solutions that achieve identical loss values in overparameterized models - a phenomenon known as implicit bias. Controlling this bias provides a…

Machine Learning · Computer Science 2026-04-07 Nicola Aladrah , Emanuele Ballarin , Matteo Biagetti , Alessio Ansuini , Alberto d'Onofrio , Fabio Anselmi