English
Related papers

Related papers: A Boundary-Layer Mechanism for One-Third Scaling i…

200 papers

Singular learning models with non-positive Fisher information matrices include neural networks, reduced-rank regression, Boltzmann machines, normal mixture models, and others. These models have been widely used in the development of…

Machine Learning · Statistics 2025-02-12 Miki Aoyagi

This paper addresses the distributed stochastic minimax optimization problem subject to stochastic constraints. We propose a novel first-order Softmax-Weighted Switching Gradient method tailored for federated learning. Under full client…

Machine Learning · Computer Science 2026-03-09 Zhankun Luo , Antesh Upadhyay , Sang Bin Moon , Abolfazl Hashemi

The softmax function is a widely used activation function in the output layers of neural networks, responsible for converting raw scores into class probabilities while introducing essential non-linearity. Implementing Softmax efficiently…

Large language models often achieve strong benchmark gains without corresponding improvements in broader capability. We hypothesize that this discrepancy arises from differences in training regimes induced by data distribution. To…

Machine Learning · Computer Science 2026-04-10 Hongjian Zou , Yidan Wang , Qi Ding , Yixuan Liao , Xiaoxin Chen

Hypothesis-pruning maximizes the hypothesis updates for active learning to find those desired unlabeled data. An inherent assumption is that this learning manner can derive those updates into the optimal hypothesis. However, its convergence…

Machine Learning · Computer Science 2023-09-21 Xiaofeng Cao , Yaming Guo , Ivor W. Tsang , James T. Kwok

Pseudo-labels are confident predictions made on unlabeled target data by a classifier trained on labeled source data. They are widely used for adapting a model to unlabeled data, e.g., in a semi-supervised learning setting. Our key insight…

Machine Learning · Computer Science 2022-04-22 Xudong Wang , Zhirong Wu , Long Lian , Stella X. Yu

We propose a semi-supervised text classifier based on self-training using one positive and one negative property of neural networks. One of the weaknesses of self-training is the semantic drift problem, where noisy pseudo-labels accumulate…

Computation and Language · Computer Science 2024-01-02 Payam Karisani

We use partial class memberships in soft classification to model uncertain labelling and mixtures of classes. Partial class memberships are not restricted to predictions, but may also occur in reference labels (ground truth, gold standard…

Machine Learning · Statistics 2013-08-23 Claudia Beleites , Reiner Salzer , Valter Sergo

Deep neural networks have achieved remarkable performance across various tasks when supplied with large-scale labeled data. However, the collection of labeled data can be time-consuming and labor-intensive. Semi-supervised learning (SSL),…

Machine Learning · Computer Science 2024-06-28 Chaoqi Liang , Guanglei Yang , Lifeng Qiao , Zitong Huang , Hongliang Yan , Yunchao Wei , Wangmeng Zuo

Distance metric learning (DML) is to learn the embeddings where examples from the same class are closer than examples from different classes. It can be cast as an optimization problem with triplet constraints. Due to the vast number of…

Computer Vision and Pattern Recognition · Computer Science 2020-04-16 Qi Qian , Lei Shang , Baigui Sun , Juhua Hu , Hao Li , Rong Jin

We present a detailed study of surrogate losses and algorithms for multi-label learning, supported by $H$-consistency bounds. We first show that, for the simplest form of multi-label loss (the popular Hamming loss), the well-known…

Machine Learning · Computer Science 2024-07-19 Anqi Mao , Mehryar Mohri , Yutao Zhong

We conjecture that the inherent difference in generalisation between adaptive and non-adaptive gradient methods in deep learning stems from the increased estimation noise in the flattest directions of the true loss surface. We demonstrate…

Machine Learning · Statistics 2022-03-17 Diego Granziol , Nicholas Baskerville

Label noise and class imbalance commonly coexist in real-world data. Previous works for robust learning, however, usually address either one type of the data biases and underperform when facing them both. To mitigate this gap, this work…

Machine Learning · Computer Science 2023-09-06 Shenwang Jiang , Jianan Li , Jizhou Zhang , Ying Wang , Tingfa Xu

Training modern neural networks is an inherently noisy process that can lead to high \emph{prediction churn} -- disagreements between re-trainings of the same model due to factors such as randomization in the parameter initialization and…

Machine Learning · Computer Science 2021-06-15 Dara Bahri , Heinrich Jiang

We consider the weakly supervised binary classification problem where the labels are randomly flipped with probability $1- {\alpha}$. Although there exist numerous algorithms for this problem, it remains theoretically unexplored how the…

Machine Learning · Computer Science 2019-07-16 Xinyang Yi , Zhaoran Wang , Zhuoran Yang , Constantine Caramanis , Han Liu

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

Deep learning and model predictive control (MPC) can play complementary roles in legged robotics. However, integrating learned models with online planning remains challenging. When dynamics are learned with neural networks, three key…

Robotics · Computer Science 2026-01-21 Samuel A. Moore , Easop Lee , Boyuan Chen

In large-scale visual recognition and data mining tasks, the presence of noisy labels severely undermines the generalization capability of deep neural networks (DNNs). Prevalent sample selection methods rely primarily on training loss or…

Computer Vision and Pattern Recognition · Computer Science 2026-05-13 Ningkang Peng , Jingyang Mao , Qianfeng Yu , Xiaoqian Peng , Peirong Ma , Yanhui Gu

In machine learning, the scaling law describes how the model performance improves with the model and data size scaling up. From a learning theory perspective, this class of results establishes upper and lower generalization bounds for a…

Machine Learning · Computer Science 2025-02-14 Shihong Ding , Haihan Zhang , Hanzhen Zhao , Cong Fang

In this paper, we introduce a threshold-based framework for multiclass classification that generalizes the standard argmax rule. This is done by replacing the probabilistic interpretation of softmax outputs with a geometric one on the…

Machine Learning · Computer Science 2025-12-02 Francesco Marchetti , Edoardo Legnaro , Sabrina Guastavino
‹ Prev 1 8 9 10 Next ›