English
Related papers

Related papers: On the Implicit Bias of Gradient Descent for Tempo…

200 papers

The effectiveness of recurrent neural networks can be largely influenced by their ability to store into their dynamical memory information extracted from input sequences at different frequencies and timescales. Such a feature can be…

Machine Learning · Computer Science 2020-07-01 Antonio Carta , Alessandro Sperduti , Davide Bacciu

When optimizing over-parameterized models, such as deep neural networks, a large set of parameters can achieve zero training error. In such cases, the choice of the optimization algorithm and its respective hyper-parameters introduces…

Machine Learning · Computer Science 2019-12-06 Gauthier Gidel , Francis Bach , Simon Lacoste-Julien

Deep neural networks are highly expressive machine learning models with the ability to interpolate arbitrary datasets. Deep nets are typically optimized via first-order methods and the optimization process crucially depends on the…

Machine Learning · Statistics 2019-11-12 Talha Cihad Gulcu

Deep neural networks have shown promising results for various clinical prediction tasks. However, training deep networks such as those based on Recurrent Neural Networks (RNNs) requires large labeled data, significant hyper-parameter tuning…

Machine Learning · Computer Science 2021-03-05 Priyanka Gupta , Pankaj Malhotra , Jyoti Narwariya , Lovekesh Vig , Gautam Shroff

Recurrent Neural Networks (RNNs) are widely used for online regression due to their ability to generalize nonlinear temporal dependencies. As an RNN model, Long-Short-Term-Memory Networks (LSTMs) are commonly preferred in practice, as these…

Machine Learning · Computer Science 2021-06-01 N. Mert Vural , Fatih Ilhan , Selim F. Yilmaz , Salih Ergüt , Suleyman S. Kozat

Normalized gradient descent has shown substantial success in speeding up the convergence of exponentially-tailed loss functions (which includes exponential and logistic losses) on linear classifiers with separable data. In this paper, we go…

Machine Learning · Computer Science 2023-06-28 Hossein Taheri , Christos Thrampoulidis

This paper addresses the problem of accurately estimating a function on one domain when only its discrete samples are available on another domain. To answer this challenge, we utilize a neural network, which we train to incorporate prior…

Machine Learning · Computer Science 2024-05-20 Guy Hay , Nir Sharon

We theoretically characterize gradient descent dynamics in deep linear networks trained at large width from random initialization and on large quantities of random data. Our theory captures the ``wider is better" effect of…

Machine Learning · Computer Science 2025-06-17 Blake Bordelon , Cengiz Pehlevan

Deep neural networks demonstrate to have a high performance on image classification tasks while being more difficult to train. Due to the complexity and vanishing gradient problem, it normally takes a lot of time and more computational…

Computer Vision and Pattern Recognition · Computer Science 2018-05-02 Mohammad Sadegh Ebrahimi , Hossein Karkeh Abadi

The notion of interpolation and extrapolation is fundamental in various fields from deep learning to function approximation. Interpolation occurs for a sample $x$ whenever this sample falls inside or on the boundary of the given dataset's…

Machine Learning · Computer Science 2021-11-02 Randall Balestriero , Jerome Pesenti , Yann LeCun

Recurrent recommender systems have been successful in capturing the temporal dynamics in users' activity trajectories. However, recurrent neural networks (RNNs) are known to have difficulty learning long-term dependencies. As a consequence,…

Information Retrieval · Computer Science 2022-01-27 Bo Chang , Can Xu , Matthieu Lê , Jingchen Feng , Ya Le , Sriraj Badam , Ed Chi , Minmin Chen

The results of training a neural network are heavily dependent on the architecture chosen; and even a modification of only its size, however small, typically involves restarting the training process. In contrast to this, we begin training…

Machine Learning · Computer Science 2024-02-12 Rupert Mitchell , Robin Menzenbach , Kristian Kersting , Martin Mundt

The ability of overparameterized deep networks to interpolate noisy data, while at the same time showing good generalization performance, has been recently characterized in terms of the double descent curve for the test error. Common…

Machine Learning · Computer Science 2023-04-11 Matteo Gamba , Erik Englesson , Mårten Björkman , Hossein Azizpour

We discuss methods for visualizing neural network decision boundaries and decision regions. We use these visualizations to investigate issues related to reproducibility and generalization in neural network training. We observe that changes…

Recurrent Neural Networks (RNNs) are commonly used for real-time processing, streaming data, and cases where the amount of training samples is limited. Backpropagation Through Time (BPTT) is the predominant algorithm for training RNNs;…

Machine Learning · Computer Science 2025-07-08 Nikolay Manchev , Luis C. Garcia-Peraza-Herrera

Recurrent neural networks (RNNs) can be interpreted as discrete-time state-space models, where the state evolution corresponds to an infinite-impulse-response (IIR) filtering operation governed by both feedforward weights and recurrent…

Machine Learning · Computer Science 2026-02-26 Alexander Morgan , Ummay Sumaya Khan , Lingjia Liu , Lizhong Zheng

Significant theoretical work has established that in specific regimes, neural networks trained by gradient descent behave like kernel methods. However, in practice, it is known that neural networks strongly outperform their associated…

Machine Learning · Computer Science 2022-07-01 Alex Damian , Jason D. Lee , Mahdi Soltanolkotabi

We examine the necessity of interpolation in overparameterized models, that is, when achieving optimal predictive risk in machine learning problems requires (nearly) interpolating the training data. In particular, we consider simple…

Machine Learning · Statistics 2022-06-17 Chen Cheng , John Duchi , Rohith Kuditipudi

Recurrent neural networks are often used for learning time-series data. Based on a few assumptions we model this learning task as a minimization problem of a nonlinear least-squares cost function. The special structure of the cost function…

Artificial Intelligence · Computer Science 2007-05-23 I. Szita , A. Lorincz

We explore conditions for when the gradient of a deep declarative node can be approximated by ignoring constraint terms and still result in a descent direction for the global loss function. This has important practical application when…

Machine Learning · Computer Science 2023-06-27 Stephen Gould , Ming Xu , Zhiwei Xu , Yanbin Liu