English
Related papers

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

200 papers

A leading hypothesis for the surprising generalization of neural networks is that the dynamics of gradient descent bias the model towards simple solutions, by searching through the solution space in an incremental order of complexity. We…

Machine Learning · Computer Science 2020-01-01 Daniel Gissin , Shai Shalev-Shwartz , Amit Daniely

Deep learning models, particularly Transformers, have achieved impressive results in various domains, including time series forecasting. While existing time series literature primarily focuses on model architecture modifications and data…

Machine Learning · Computer Science 2023-12-01 Valentino Assandri , Sam Heshmati , Burhaneddin Yaman , Anton Iakovlev , Ariel Emiliano Repetur

We provide theoretical investigation of curriculum learning in the context of stochastic gradient descent when optimizing the convex linear regression loss. We prove that the rate of convergence of an ideal curriculum learning method is…

Machine Learning · Computer Science 2023-12-29 Daphna Weinshall , Gad Cohen , Dan Amir

Recurrent neural networks (RNNs) have shown promising performance for language modeling. However, traditional training of RNNs using back-propagation through time often suffers from overfitting. One reason for this is that stochastic…

Computation and Language · Computer Science 2017-04-25 Zhe Gan , Chunyuan Li , Changyou Chen , Yunchen Pu , Qinliang Su , Lawrence Carin

Generalization of deep neural networks remains one of the main open problems in machine learning. Previous theoretical works focused on deriving tight bounds of model complexity, while empirical works revealed that neural networks exhibit…

Machine Learning · Computer Science 2022-01-31 James Wang , Cheng-Lin Yang

Deep learning inspired by differential equations is a recent research trend and has marked the state of the art performance for many machine learning tasks. Among them, time-series modeling with neural controlled differential equations…

Machine Learning · Computer Science 2022-09-22 Sheo Yon Jhin , Jaehoon Lee , Minju Jo , Seungji Kook , Jinsung Jeon , Jihyeon Hyeong , Jayoung Kim , Noseong Park

In deep learning, it is common to use more network parameters than training points. In such scenarioof over-parameterization, there are usually multiple networks that achieve zero training error so that thetraining algorithm induces an…

Machine Learning · Computer Science 2023-08-22 Hung-Hsu Chou , Carsten Gieshoff , Johannes Maly , Holger Rauhut

We investigate the generalization and optimization properties of shallow neural-network classifiers trained by gradient descent in the interpolating regime. Specifically, in a realizable scenario where model weights can achieve arbitrarily…

Machine Learning · Statistics 2023-03-29 Hossein Taheri , Christos Thrampoulidis

Recurrent neural networks (RNNs) stand at the forefront of many recent developments in deep learning. Yet a major difficulty with these models is their tendency to overfit, with dropout shown to fail when applied to recurrent layers. Recent…

Machine Learning · Statistics 2016-10-06 Yarin Gal , Zoubin Ghahramani

Bidirectional recurrent neural networks (RNN) are trained to predict both in the positive and negative time directions simultaneously. They have not been used commonly in unsupervised tasks, because a probabilistic interpretation of the…

Machine Learning · Computer Science 2015-11-03 Mathias Berglund , Tapani Raiko , Mikko Honkala , Leo Kärkkäinen , Akos Vetek , Juha Karhunen

There has been a long history of works showing that neural networks have hard time extrapolating beyond the training set. A recent study by Balestriero et al. (2021) challenges this view: defining interpolation as the state of belonging to…

Machine Learning · Computer Science 2022-07-19 Laurent Bonnasse-Gahot

Neural networks trained with standard objectives exhibit behaviors characteristic of probabilistic inference: soft clustering, prototype specialization, and Bayesian uncertainty tracking. These phenomena appear across architectures -- in…

Machine Learning · Computer Science 2026-01-01 Alan Oursland

A residual network (or ResNet) is a standard deep neural net architecture, with state-of-the-art performance across numerous applications. The main premise of ResNets is that they allow the training of each layer to focus on fitting just…

Machine Learning · Computer Science 2018-09-28 Ohad Shamir

Recurrent neural networks are nowadays successfully used in an abundance of applications, going from text, speech and image processing to recommender systems. Backpropagation through time is the algorithm that is commonly used to train…

Machine Learning · Computer Science 2018-01-10 Cedric De Boom , Thomas Demeester , Bart Dhoedt

Recurrent neural networks (RNNs) are more suitable for learning non-linear dependencies in dynamical systems from observed time series data. In practice all the external variables driving such systems are not known a priori, especially in…

Machine Learning · Computer Science 2020-06-02 Mhlasakululeka Mvubu , Emmanuel Kabuga , Christian Plitz , Bubacarr Bah , Ronnie Becker , Hans Georg Zimmermann

Over-parameterized deep neural networks (DNNs) with sufficient capacity to memorize random noise can achieve excellent generalization performance, challenging the bias-variance trade-off in classical learning theory. Recent studies claimed…

Machine Learning · Computer Science 2022-11-15 Xiao Zhang , Haoyi Xiong , Dongrui Wu

Recurrent neural networks are a successful neural architecture for many time-dependent problems, including time series analysis, forecasting, and modeling of dynamical systems. Training such networks with backpropagation through time is a…

Machine Learning · Computer Science 2025-01-30 Erik Lien Bolager , Ana Cukarska , Iryna Burak , Zahra Monfared , Felix Dietrich

Successful deep neural networks discover salient features of data. We show when and why they fail to learn out-of-distribution (OOD)-relevant representations from an in-distribution (ID) training window. This requires decoupling feature…

Machine Learning · Computer Science 2026-05-14 Leonel Aguilar , Jan Nagler , Christoph Hoelscher , Nino Antulov-Fantulin

Many machine/deep learning artificial neural networks are trained to simply be interpolation functions that map input variables to output values interpolated from the training data in a linear/nonlinear fashion. Even when the input/output…

Computational Physics · Physics 2020-03-18 Zhenglin Geng , Dan Johnson , Ronald Fedkiw

Long sequences occur in abundance within real-world scenarios, hence properly modelling them opens numerous down-stream use-cases. Deep neural networks, however, have often struggled with these for a variety of reasons. Recent advances,…

Machine Learning · Computer Science 2025-05-23 Jerry Huang
‹ Prev 1 3 4 5 6 7 10 Next ›