English
Related papers

Related papers: A Theoretical Analysis of the Learning Dynamics un…

200 papers

Classical optimisation theory guarantees monotonic objective decrease for gradient descent (GD) when employed in a small step size, or ``stable", regime. In contrast, gradient descent on neural networks is frequently performed in a large…

Machine Learning · Computer Science 2025-10-21 Lachlan Ewen MacDonald , Hancheng Min , Leandro Palma , Salma Tarmoun , Ziqing Xu , René Vidal

Real-world data is extremely imbalanced and presents a long-tailed distribution, resulting in models that are biased towards classes with sufficient samples and perform poorly on rare classes. Recent methods propose to rebalance classes but…

Computer Vision and Pattern Recognition · Computer Science 2023-11-02 Weiqi Li , Fan Lyu , Fanhua Shang , Liang Wan , Wei Feng

The impact of gradient noise on training deep models is widely acknowledged but not well understood. In this context, we study the distribution of gradients during training. We introduce a method, Gradient Clustering, to minimize the…

Machine Learning · Computer Science 2020-07-10 Fartash Faghri , David Duvenaud , David J. Fleet , Jimmy Ba

Semi-Supervised Learning (SSL) has achieved great success in overcoming the difficulties of labeling and making full use of unlabeled data. However, SSL has a limited assumption that the numbers of samples in different classes are balanced,…

Machine Learning · Computer Science 2020-02-18 Minsung Hyun , Jisoo Jeong , Nojun Kwak

The performance of stochastic gradient descent (SGD) depends critically on how learning rates are tuned and decreased over time. We propose a method to automatically adjust multiple learning rates so as to minimize the expected error at any…

Machine Learning · Statistics 2013-02-19 Tom Schaul , Sixin Zhang , Yann LeCun

Despite tremendous success of deep neural network in machine learning, the underlying reason for its superior learning capability remains unclear. Here, we present a framework based on statistical physics to study dynamics of stochastic…

Machine Learning · Computer Science 2021-01-19 Yu Feng , Yuhai Tu

The generalization performance of a machine learning algorithm such as a neural network depends in a non-trivial way on the structure of the data distribution. To analyze the influence of data structure on test loss dynamics, we study an…

Machine Learning · Statistics 2022-03-16 Blake Bordelon , Cengiz Pehlevan

Recently many first and second order variants of SGD have been proposed to facilitate training of Deep Neural Networks (DNNs). A common limitation of these works stem from the fact that they use the same learning rate across all instances…

Machine Learning · Computer Science 2021-05-31 Shreyas Saxena , Nidhi Vyas , Dennis DeCoste

In this paper, we propose a balancing training method to address problems in imbalanced data learning. To this end, we derive a new loss used in the balancing training phase that alleviates the influence of samples that cause an overfitted…

Computer Vision and Pattern Recognition · Computer Science 2021-10-14 Seulki Park , Jongin Lim , Younghan Jeon , Jin Young Choi

This study proposes a method for imbalanced data classification based on deep probabilistic graphical models (DPGMs) to solve the problem that traditional methods have insufficient learning ability for minority class samples. To address the…

Machine Learning · Computer Science 2025-04-09 Yujia Lou , Jie Liu , Yuan Sheng , Jiawei Wang , Yiwei Zhang , Yaokun Ren

As part of autonomous car driving systems, semantic segmentation is an essential component to obtain a full understanding of the car's environment. One difficulty, that occurs while training neural networks for this purpose, is class…

Computer Vision and Pattern Recognition · Computer Science 2019-01-25 Robin Chan , Matthias Rottmann , Fabian Hüger , Peter Schlicht , Hanno Gottschalk

Deep learning networks are typically trained by Stochastic Gradient Descent (SGD) methods that iteratively improve the model parameters by estimating a gradient on a very small fraction of the training data. A major roadblock faced when…

Machine Learning · Computer Science 2020-06-11 Tao Lin , Lingjing Kong , Sebastian U. Stich , Martin Jaggi

Understanding the implicit bias of training algorithms is of crucial importance in order to explain the success of overparametrised neural networks. In this paper, we study the dynamics of stochastic gradient descent over diagonal linear…

Machine Learning · Computer Science 2021-12-08 Scott Pesme , Loucas Pillaud-Vivien , Nicolas Flammarion

In predictive tasks, real-world datasets often present different degrees of imbalanced (i.e., long-tailed or skewed) distributions. While the majority (the head) classes have sufficient samples, the minority (the tail) classes can be…

Machine Learning · Computer Science 2021-09-14 Chongsheng Zhang , Paolo Soda , Jingjun Bi , Gaojuan Fan , George Almpanidis , Salvador Garcia

Multi-task learning (MTL) aims to build general-purpose vision systems by training a single network to perform multiple tasks jointly. While promising, its potential is often hindered by "unbalanced optimization", where task interference…

Computer Vision and Pattern Recognition · Computer Science 2025-09-30 Yihang Guo , Tianyuan Yu , Liang Bai , Yanming Guo , Yirun Ruan , William Li , Weishi Zheng

The deep learning recipe of casting real-world problems as mathematical optimisation and tackling the optimisation by training deep neural networks using gradient-based optimisation has undoubtedly proven to be a fruitful one. The…

Machine Learning · Statistics 2023-10-24 Mihaela Claudia Rosca

Multimodal Domain Generalization (MMDG) leverages the complementary strengths of multiple modalities to enhance model generalization on unseen domains. A central challenge in multimodal learning is optimization imbalance, where modalities…

Machine Learning · Computer Science 2026-03-17 Hongzhao Li , Guohao Shen , Shupan Li , Mingliang Xu , Muhammad Haris Khan

Learning from imbalanced data is a challenging task. Standard classification algorithms tend to perform poorly when trained on imbalanced data. Some special strategies need to be adopted, either by modifying the data distribution or by…

Machine Learning · Computer Science 2022-08-26 Asif Newaz , Shahriar Hassan , Farhan Shahriyar Haq

We identify and formalize a fundamental gradient descent phenomenon resulting in a learning proclivity in over-parameterized neural networks. Gradient Starvation arises when cross-entropy loss is minimized by capturing only a subset of…

Machine Learning · Computer Science 2021-11-25 Mohammad Pezeshki , Sékou-Oumar Kaba , Yoshua Bengio , Aaron Courville , Doina Precup , Guillaume Lajoie

The goal of multi-task learning is to enable more efficient learning than single task learning by sharing model structures for a diverse set of tasks. A standard multi-task learning objective is to minimize the average loss across all…

Machine Learning · Computer Science 2024-02-22 Bo Liu , Xingchao Liu , Xiaojie Jin , Peter Stone , Qiang Liu
‹ Prev 1 3 4 5 6 7 10 Next ›