English
Related papers

Related papers: Neural Network Classifier as Mutual Information Ev…

200 papers

We address the data selection problem in statistical machine translation (SMT) as a classification task. The new data selection method is based on a neural network classifier. We present a new method description and empirical results…

Computation and Language · Computer Science 2016-12-22 Álvaro Peris , Mara Chinea-Rios , Francisco Casacuberta

In knowledge graph embedding, the theoretical relationship between the softmax cross-entropy and negative sampling loss functions has not been investigated. This makes it difficult to fairly compare the results of the two different loss…

Machine Learning · Computer Science 2022-03-17 Hidetaka Kamigaito , Katsuhiko Hayashi

We propose the Linearly Adaptive Cross Entropy Loss function. This is a novel measure derived from the information theory. In comparison to the standard cross entropy loss function, the proposed one has an additional term that depends on…

Machine Learning · Computer Science 2025-07-16 Jae Wan Shim

We propose a kernelized classification layer for deep networks. Although conventional deep networks introduce an abundance of nonlinearity for representation (feature) learning, they almost universally use a linear classifier on the learned…

Machine Learning · Computer Science 2021-03-22 Sadeep Jayasumana , Srikumar Ramalingam , Sanjiv Kumar

We propose a meta-learning method for learning from multiple noisy annotators. In many applications such as crowdsourcing services, labels for supervised learning are given by multiple annotators. Since the annotators have different skills…

Machine Learning · Computer Science 2025-06-13 Atsutoshi Kumagai , Tomoharu Iwata , Taishi Nishiyama , Yasutoshi Ida , Yasuhiro Fujiwara

Understanding the fundamental limits of robust supervised learning has emerged as a problem of immense interest, from both practical and theoretical standpoints. In particular, it is critical to determine classifier-agnostic bounds on the…

Machine Learning · Computer Science 2021-06-08 Arjun Nitin Bhagoji , Daniel Cullina , Vikash Sehwag , Prateek Mittal

Deep convolutional neural networks (CNNs) trained with logistic and softmax losses have made significant advancement in visual recognition tasks in computer vision. When training data exhibit class imbalances, the class-wise reweighted…

Machine Learning · Computer Science 2020-03-06 Xiangrui Li , Xin Li , Deng Pan , Dongxiao Zhu

Mutual information is a general statistical dependency measure which has found applications in representation learning, causality, domain generalization and computational biology. However, mutual information estimators are typically…

Machine Learning · Statistics 2023-10-17 Paweł Czyż , Frederic Grabowski , Julia E. Vogt , Niko Beerenwinkel , Alexander Marx

Deep neural networks have been shown to easily overfit to biased training data with label noise or class imbalance. Meta-learning algorithms are commonly designed to alleviate this issue in the form of sample reweighting, by learning a meta…

Machine Learning · Computer Science 2020-12-11 Hongxin Wei , Lei Feng , Rundong Wang , Bo An

Class-imbalanced data, in which some classes contain far more samples than others, is ubiquitous in real-world applications. Standard techniques for handling class-imbalance usually work by training on a re-weighted loss or on re-balanced…

Artificial Intelligence · Computer Science 2021-06-18 Arpit Bansal , Micah Goldblum , Valeriia Cherepanova , Avi Schwarzschild , C. Bayan Bruss , Tom Goldstein

A proper understanding of the striking generalization abilities of deep neural networks presents an enduring puzzle. Recently, there has been a growing body of numerically-grounded theoretical work that has contributed important insights to…

Machine Learning · Computer Science 2019-10-31 Tyler Lee , Anthony Ndirango

Recent studies have shown that deep neural networks are not well-calibrated and often produce over-confident predictions. The miscalibration issue primarily stems from using cross-entropy in classifications, which aims to align predicted…

Machine Learning · Computer Science 2025-02-05 Daehwan Kim , Haejun Chung , Ikbeom Jang

We propose a novel approach which exploits chaos to enhance classification accuracy. Specifically, the available data that need to be classified are treated as vectors that are first lifted into a higher-dimensional space and then used as…

Machine Learning · Computer Science 2026-04-21 Panos Stinis

Large language models (LLMs) have been garnering increasing attention in the recommendation community. Some studies have observed that LLMs, when fine-tuned by the cross-entropy (CE) loss with a full softmax, could achieve…

Information Retrieval · Computer Science 2024-08-27 Cong Xu , Zhangchi Zhu , Mo Yu , Jun Wang , Jianyong Wang , Wei Zhang

Class imbalance, which is also called long-tailed distribution, is a common problem in classification tasks based on machine learning. If it happens, the minority data will be overwhelmed by the majority, which presents quite a challenge…

Machine Learning · Computer Science 2023-03-29 Jia-Chen Zhao

Modern deep learning is primarily an experimental science, in which empirical advances occasionally come at the expense of probabilistic rigor. Here we focus on one such example; namely the use of the categorical cross-entropy loss to model…

Machine Learning · Statistics 2020-11-11 Elliott Gordon-Rodriguez , Gabriel Loaiza-Ganem , Geoff Pleiss , John P. Cunningham

Multi-view learning accomplishes the task objectives of classification by leverag-ing the relationships between different views of the same object. Most existing methods usually focus on consistency and complementarity between multiple…

Machine Learning · Computer Science 2022-01-14 Jian-wei Liu , Yuan-fang Wang , Run-kun Lu , Xionglin Luo

Estimating Mutual Information (MI), a key measure of dependence of random quantities without specific modelling assumptions, is a challenging problem in high dimensions. We propose a novel mutual information estimator based on parametrizing…

Machine Learning · Statistics 2025-10-24 Haoran Ni , Martin Lotz

Due to their flexibility and predictive performance, machine-learning based regression methods have become an important tool for predictive modeling and forecasting. However, most methods focus on estimating the conditional mean or specific…

Machine Learning · Statistics 2019-03-15 Rui Li , Howard D. Bondell , Brian J. Reich

The label distribution skew induced data heterogeniety has been shown to be a significant obstacle that limits the model performance in federated learning, which is particularly developed for collaborative model training over decentralized…

Machine Learning · Computer Science 2023-03-16 Jian Xu , Meiling Yang , Wenbo Ding , Shao-Lun Huang