English
Related papers

Related papers: Collapsing of dimensionality

200 papers

Deep learning requires regularization mechanisms to reduce overfitting and improve generalization. We address this problem by a new regularization method based on distributional robust optimization. The key idea is to modify the…

Machine Learning · Computer Science 2020-06-08 Aurora Cobo Aguilera , Antonio Artés-Rodríguez , Fernando Pérez-Cruz , Pablo Martínez Olmos

Training of neural networks is a computationally intensive task. The significance of understanding and modeling the training dynamics is growing as increasingly larger networks are being trained. We propose in this work a model based on the…

Machine Learning · Computer Science 2022-12-20 Rotem Turjeman , Tom Berkov , Ido Cohen , Guy Gilboa

When fine-tuning Deep Neural Networks (DNNs) to new data, DNNs are prone to overwriting network parameters required for task-specific functionality on previously learned tasks, resulting in a loss of performance on those tasks. We propose…

Machine Learning · Computer Science 2025-01-22 Christopher Angelini , Nidhal Bouaynaya

Large scale, streaming datasets are ubiquitous in modern machine learning. Streaming algorithms must be scalable, amenable to incremental training and robust to the presence of non-stationarity. In this work consider the problem of learning…

Machine Learning · Statistics 2017-12-15 Ricardo Pio Monti , Christoforos Anagnostopoulos , Giovanni Montana

This paper explores the connection between two recently identified phenomena in deep learning: plasticity loss and neural collapse. We analyze their correlation in different scenarios, revealing a significant association during the initial…

Machine Learning · Computer Science 2024-04-04 Guglielmo Bonifazi , Iason Chalas , Gian Hess , Jakub Łucki

In this paper, we introduce a new regularization technique for transfer learning. The aim of the proposed approach is to capture statistical relationships among convolution filters learned from a well-trained network and transfer this…

Computer Vision and Pattern Recognition · Computer Science 2017-08-24 Mehmet Aygün , Yusuf Aytar , Hazım Kemal Ekenel

We present a computational method for empirically characterizing the training loss level-sets of deep neural networks. Our method numerically constructs a path in parameter space that is constrained to a set with a fixed near-zero training…

Machine Learning · Computer Science 2021-04-27 Naveed Tahir , Garrett E. Katz

Dropout and other feature noising schemes control overfitting by artificially corrupting the training data. For generalized linear models, dropout performs a form of adaptive regularization. Using this viewpoint, we show that the dropout…

Machine Learning · Statistics 2013-11-04 Stefan Wager , Sida Wang , Percy Liang

Regularization plays a vital role in the context of deep learning by preventing deep neural networks from the danger of overfitting. This paper proposes a novel deep learning regularization method named as DL-Reg, which carefully reduces…

Machine Learning · Computer Science 2020-11-05 Maryam Dialameh , Ali Hamzeh , Hossein Rahmani

Complex structures are typical in machine learning. Tailoring learning algorithms for every structure requires an effort that may be saved by defining a generic learning procedure adaptive to any complex structure. In this paper, we propose…

Machine Learning · Computer Science 2019-05-28 Pablo Strasser , Stephane Armand , Stephane Marchand-Maillet , Alexandros Kalousis

Data assisted reconstruction algorithms, incorporating trained neural networks, are a novel paradigm for solving inverse problems. One approach is to first apply a classical reconstruction method and then apply a neural network to improve…

Numerical Analysis · Mathematics 2020-03-26 Yoeri E. Boink , Markus Haltmeier , Sean Holman , Johannes Schwab

This paper is concerned with the problem of representing and learning a linear transformation using a linear neural network. In recent years, there has been a growing interest in the study of such networks in part due to the successes of…

Optimization and Control · Mathematics 2017-09-28 Amirhossein Taghvaei , Jin W. Kim , Prashant G. Mehta

Modern neural translation models based on the Transformer architecture are known for their high performance, particularly when trained on high-resource datasets. A standard next-token prediction training strategy, while widely adopted in…

Computation and Language · Computer Science 2026-02-20 Evgeniia Tokarchuk , Maya K. Nachesa , Sergey Troshin , Vlad Niculae

We design and analyze a new paradigm for building supervised learning networks, driven only by local optimization rules without relying on a global error function. Traditional neural networks with a fixed topology are made up of identical…

Adaptation and Self-Organizing Systems · Physics 2024-10-04 S. Barland , L. Gil

Proper regularization is critical for speeding up training, improving generalization performance, and learning compact models that are cost efficient. We propose and analyze regularized gradient descent algorithms for learning shallow…

Machine Learning · Computer Science 2018-06-08 Samet Oymak

The focus of this paper is the application of classical model order reduction techniques, such as Active Subspaces and Proper Orthogonal Decomposition, to Deep Neural Networks. We propose a generic methodology to reduce the number of layers…

Machine Learning · Computer Science 2024-01-22 Laura Meneghetti , Nicola Demo , Gianluigi Rozza

In the context of linear inverse problems, we propose and study a general iterative regularization method allowing to consider large classes of regularizers and data-fit terms. The algorithm we propose is based on a primal-dual diagonal…

Optimization and Control · Mathematics 2017-08-04 Guillaume Garrigos , Lorenzo Rosasco , Silvia Villa

We present a novel, domain-agnostic, model-independent, unsupervised, and universally applicable Machine Learning approach for dimensionality reduction based on the principles of algorithmic complexity. Specifically, but without loss of…

Data Structures and Algorithms · Computer Science 2025-05-06 Hector Zenil , Narsis A. Kiani , Alyssa Adams , Felipe S. Abrahão , Antonio Rueda-Toicen , Allan A. Zea , Luan Ozelim , Jesper Tegnér

The paper proposes a novel regularization procedure for machine learning. The proposed high-order regularization (HR) provides new insight into regularization, which is widely used to train a neural network that can be utilized to…

Machine Learning · Computer Science 2025-05-14 Xinghua Liu , Ming Cao

This material introduces the D-Subspace algorithm derived on the basis of the centralized algorithm [1], which originally addresses parameter estimation problems under a subspace constraint.

Signal Processing · Electrical Eng. & Systems 2024-11-19 Yitong Chen , Danqi Jin , Jie Chen , Cedric Richard