English
Related papers

Related papers: Generalization in Representation Models via Random…

200 papers

Continual learning of deep neural networks is a key requirement for scaling them up to more complex applicative scenarios and for achieving real lifelong learning of these architectures. Previous approaches to the problem have considered…

Machine Learning · Computer Science 2020-06-25 Jary Pomponi , Simone Scardapane , Vincenzo Lomonaco , Aurelio Uncini

Random matrix theory has proven to be a valuable tool in analyzing the generalization of linear models. However, the generalization properties of even two-layer neural networks trained by gradient descent remain poorly understood. To…

Statistics Theory · Mathematics 2024-10-21 Jiping Li , Rishi Sonthalia

This study presents a novel model for invertible sentence embeddings using a residual recurrent network trained on an unsupervised encoding task. Rather than the probabilistic outputs common to neural machine translation models, our…

Computation and Language · Computer Science 2023-04-07 Jeremy Wilkerson

Recurrent neural networks are good at solving prediction problems. However, finding a network that suits a problem is quite hard because their performance is strongly affected by their architecture configuration. Automatic architecture…

Neural and Evolutionary Computing · Computer Science 2021-03-16 Andrés Camero , Jamal Toutouh , Enrique Alba

Evaluation of generative models is mostly based on the comparison between the estimated distribution and the ground truth distribution in a certain feature space. To embed samples into informative features, previous works often use…

Machine Learning · Computer Science 2022-12-15 Junghyuk Lee , Jun-Hyuk Kim , Jong-Seok Lee

Recurrent neural networks are a widely used class of neural architectures. They have, however, two shortcomings. First, they are often treated as black-box models and as such it is difficult to understand what exactly they learn as well as…

Machine Learning · Computer Science 2022-12-13 Cheng Wang , Carolin Lawrence , Mathias Niepert

We propose a novel training approach for improving the generalization in neural networks. We show that in contrast to regular constraints for orthogonality, our approach represents a {\em data-dependent} orthogonality constraint, and is…

Computer Vision and Pattern Recognition · Computer Science 2020-07-02 You Xie , Nils Thuerey

The widespread use of diffusion models has led to an abundance of AI-generated data, raising concerns about model collapse -- a phenomenon in which recursive iterations of training on synthetic data lead to performance degradation. Prior…

Machine Learning · Computer Science 2025-12-29 Lianghe Shi , Meng Wu , Huijie Zhang , Zekai Zhang , Molei Tao , Qing Qu

We are concerned with an approximation problem for a symmetric positive semidefinite matrix due to motivation from a class of nonlinear machine learning methods. We discuss an approximation approach that we call {matrix ridge…

Machine Learning · Statistics 2013-12-18 Zhihua Zhang

Recent evidence has shown the existence of a so-called double-descent and even triple-descent behavior for the generalization error of deep-learning models. This important phenomenon commonly appears in implemented neural network…

Machine Learning · Computer Science 2021-10-25 Antoine Bodin , Nicolas Macris

We propose automatic speech recognition (ASR) models inspired by echo state network (ESN), in which a subset of recurrent neural networks (RNN) layers in the models are randomly initialized and untrained. Our study focuses on RNN-T and…

Computation and Language · Computer Science 2021-02-19 Harsh Shrivastava , Ankush Garg , Yuan Cao , Yu Zhang , Tara Sainath

We prove that Riemannian contraction in a supervised learning setting implies generalization. Specifically, we show that if an optimizer is contracting in some Riemannian metric with rate $\lambda > 0$, it is uniformly algorithmically…

Machine Learning · Computer Science 2022-01-27 Leo Kozachkov , Patrick M. Wensing , Jean-Jacques Slotine

The representations of neural networks are often compared to those of biological systems by performing regression between the neural network responses and those measured from biological systems. Many different state-of-the-art deep neural…

Neurons and Cognition · Quantitative Biology 2023-12-13 Abdulkadir Canatar , Jenelle Feather , Albert Wakhloo , SueYeon Chung

Despite the widespread empirical success of ResNet, the generalization properties of deep ResNet are rarely explored beyond the lazy training regime. In this work, we investigate \emph{scaled} ResNet in the limit of infinitely deep and wide…

Machine Learning · Computer Science 2024-03-18 Yihang Chen , Fanghui Liu , Yiping Lu , Grigorios G. Chrysos , Volkan Cevher

Large-margin classifiers are popular methods for classification. We derive the asymptotic expression for the generalization error of a family of large-margin classifiers in the limit of both sample size $n$ and dimension $p$ going to…

Machine Learning · Statistics 2020-12-02 Hanwen Huang , Qinglong Yang

Accurate short-term energy consumption forecasting is essential for efficient power grid management, resource allocation, and market stability. Traditional time-series models often fail to capture the complex, non-linear dependencies and…

Computers and Society · Computer Science 2026-01-27 Abhishek Maity , Viraj Tukarul

Diffusion geometry is a manifold learning framework that uses random walks defined by Markov transition matrices to characterize the geometry of a dataset at multiple scales. We use diffusion geometry for neural representations,…

Machine Learning · Computer Science 2026-05-18 Atharva Khandait , Jan E. Gerken

Recurrent Neural Networks (RNNs) have achieved great success in the prediction of sequential data. However, their theoretical studies are still lagging behind because of their complex interconnected structures. In this paper, we establish a…

Machine Learning · Statistics 2024-11-06 Xuewei Cheng , Ke Huang , Shujie Ma

We study in this paper lower bounds for the generalization error of models derived from multi-layer neural networks, in the regime where the size of the layers is commensurate with the number of samples in the training data. We show that…

Machine Learning · Statistics 2022-07-08 Inbar Seroussi , Ofer Zeitouni

The single-layer feedforward neural network with random weights is a recurring motif in the neural networks literature. The advantage of these networks is their simplified training, which reduces to solving a ridge-regression problem. A…

Machine Learning · Computer Science 2025-02-25 M. Andrecut
‹ Prev 1 4 5 6 7 8 10 Next ›