English
Related papers

Related papers: Learning Neural Networks with Adaptive Regularizat…

200 papers

We provide novel guaranteed approaches for training feedforward neural networks with sparse connectivity. We leverage on the techniques developed previously for learning linear networks and show that they can also be effectively adopted to…

Machine Learning · Computer Science 2015-04-29 Hanie Sedghi , Anima Anandkumar

Deep networks are an integral part of the current machine learning paradigm. Their inherent ability to learn complex functional mappings between data and various target variables, while discovering hidden, task-driven features, makes them a…

Computer Vision and Pattern Recognition · Computer Science 2019-06-14 Riddhish Bhalodia , Shireen Elhabian , Ladislav Kavan , Ross Whitaker

The remarkable performance of overparameterized deep neural networks (DNNs) must arise from an interplay between network architecture, training algorithms, and structure in the data. To disentangle these three components, we apply a…

Machine Learning · Computer Science 2025-07-09 Chris Mingard , Henry Rees , Guillermo Valle-Pérez , Ard A. Louis

We develop an approach to efficiently grow neural networks, within which parameterization and optimization strategies are designed by considering their effects on the training dynamics. Unlike existing growing methods, which follow simple…

Machine Learning · Computer Science 2023-06-23 Xin Yuan , Pedro Savarese , Michael Maire

In this paper, we aim at developing scalable neural network-type learning systems. Motivated by the idea of "constructive neural networks" in approximation theory, we focus on "constructing" rather than "training" feed-forward neural…

Machine Learning · Computer Science 2016-05-03 Shaobo Lin , Jinshan Zeng , Xiaoqin Zhang

Convolutional Neural Networks (CNNs) excel in many visual tasks but remain susceptible to adversarial attacks-imperceptible perturbations that degrade performance. Prior research reveals that brain-inspired regularizers, derived from neural…

Machine Learning · Computer Science 2026-02-16 Elie Attias , Cengiz Pehlevan , Dina Obeid

Knowledge embedded in the weights of the artificial neural network can be used to improve the network structure, such as in network compression. However, the knowledge is set up by hand, which may not be very accurate, and relevant…

Neural and Evolutionary Computing · Computer Science 2021-10-13 Mengqiao Han , Xiabi Liu , Zhaoyang Hai , Xin Duan

Parameter-space regularization in neural network optimization is a fundamental tool for improving generalization. However, standard parameter-space regularization methods make it challenging to encode explicit preferences about desired…

Machine Learning · Statistics 2023-12-29 Tim G. J. Rudner , Sanyam Kapoor , Shikai Qiu , Andrew Gordon Wilson

Generalization is essential for deep learning. In contrast to previous works claiming that Deep Neural Networks (DNNs) have an implicit regularization implemented by the stochastic gradient descent, we demonstrate explicitly Bayesian…

Machine Learning · Computer Science 2019-10-23 Xinjie Lan , Kenneth E. Barner

Bootstrapping is behind much of the successes of Deep Reinforcement Learning. However, learning the value function via bootstrapping often leads to unstable training due to fast-changing target values. Target Networks are employed to…

In this work, we propose a novel prior learning method for advancing generalization and uncertainty estimation in deep neural networks. The key idea is to exploit scalable and structured posteriors of neural networks as informative priors…

Machine Learning · Computer Science 2026-03-31 Dominik Schnaus , Jongseok Lee , Daniel Cremers , Rudolph Triebel

Polynomial functions have plenty of useful analytical properties, but they are rarely used as learning models because their function class is considered to be restricted. This work shows that when trained properly polynomial functions can…

Machine Learning · Computer Science 2021-06-30 Li-Ping Liu , Ruiyuan Gu , Xiaozhe Hu

Contemporary wisdom based on empirical studies suggests that standard recurrent neural networks (RNNs) do not perform well on tasks requiring long-term memory. However, precise reasoning for this behavior is still unknown. This paper…

Machine Learning · Computer Science 2021-01-21 Melikasadat Emami , Mojtaba Sahraee-Ardakan , Parthe Pandit , Sundeep Rangan , Alyson K. Fletcher

Relational learning can be used to augment one data source with other correlated sources of information, to improve predictive accuracy. We frame a large class of relational learning problems as matrix factorization problems, and propose a…

Machine Learning · Computer Science 2012-03-19 Ajit P. Singh , Geoffrey Gordon

This paper addresses the use of neural networks for the estimation of treatment effects from observational data. Generally, estimation proceeds in two stages. First, we fit models for the expected outcome and the probability of treatment…

Machine Learning · Statistics 2019-10-21 Claudia Shi , David M. Blei , Victor Veitch

We introduce a Normalized Convolutional Neural Layer, a novel approach to normalization in convolutional networks. Unlike conventional methods, this layer normalizes the rows of the im2col matrix during convolution, making it inherently…

Computer Vision and Pattern Recognition · Computer Science 2025-04-03 Dongsuk Kim , Geonhee Lee , Myungjae Lee , Shin Uk Kang , Dongmin Kim

A feed-forward neural network is demonstrated to efficiently unfold the energy distribution of protons and alpha particles passing through passive material. This model-independent approach works with unbinned data and does not require…

High Energy Physics - Experiment · Physics 2021-12-16 Ming-Liang Wong , Andrew Edmonds , Chen Wu

This paper describes a new model for an artificial neural network processing unit or neuron. It is slightly different to a traditional feedforward network by the fact that it favours a mechanism of trying to match the wave-like 'shape' of…

Neural and Evolutionary Computing · Computer Science 2014-03-06 Kieran Greer

Dropout regularization of deep neural networks has been a mysterious yet effective tool to prevent overfitting. Explanations for its success range from the prevention of "co-adapted" weights to it being a form of cheap Bayesian inference.…

Machine Learning · Statistics 2019-05-30 Eric Nalisnick , José Miguel Hernández-Lobato , Padhraic Smyth

We study regularization in the context of small sample-size learning with over-parameterized neural networks. Specifically, we shift focus from architectural properties, such as norms on the network weights, to properties of the internal…

Machine Learning · Computer Science 2021-05-18 Christoph D. Hofer , Florian Graf , Marc Niethammer , Roland Kwitt