English
Related papers

Related papers: StarNet: Gradient-free Training of Deep Generative…

200 papers

Deep Learning (DL), in particular deep neural networks (DNN), by default is purely data-driven and in general does not require physics. This is the strength of DL but also one of its key limitations when applied to science and engineering…

Machine Learning · Statistics 2022-09-26 Hai V. Nguyen , Tan Bui-Thanh

To benefit from the modeling capacity of deep models in system identification, without worrying about inference time, this study presents a novel training strategy that uses deep models only at the training stage. For this purpose two…

Machine Learning · Computer Science 2023-12-29 Vahid MohammadZadeh Eivaghi , Mahdi Aliyari Shooredeli

This paper proposes a novel approach to train deep neural networks by unlocking the layer-wise dependency of backpropagation training. The approach employs additional modules called local critic networks besides the main network model to be…

Machine Learning · Computer Science 2018-09-28 Hojung Lee , Jong-seok Lee

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 learning algorithms have a large number of trainable parameters often with sizes of hundreds of thousands or more. Training this algorithm requires a large amount of training data and generating a sufficiently large dataset for these…

Computer Vision and Pattern Recognition · Computer Science 2024-06-03 Kidist Amde Mekonnen

To utilize pre-trained neural networks on edge and mobile devices, we often require efficient adaptation to user-specific runtime data distributions while operating under limited compute and memory resources. On-device retraining with a…

Machine Learning · Computer Science 2026-03-04 Irene Tenison , Soumyajit Chatterjee , Fahim Kawsar , Mohammad Malekzadeh

Deep neural networks (DNNs) must cater to a variety of users with different performance needs and budgets, leading to the costly practice of training, storing, and maintaining numerous user/task-specific models. There are solutions in the…

A longstanding goal in deep learning research has been to precisely characterize training and generalization. However, the often complex loss landscapes of neural networks have made a theory of learning dynamics elusive. In this work, we…

ListNet is a well-known listwise learning to rank model and has gained much attention in recent years. A particular problem of ListNet, however, is the high computation complexity in model training, mainly due to the large number of object…

Information Retrieval · Computer Science 2015-11-03 Tianyi Luo , Dong Wang , Rong Liu , Yiqiao Pan

Despite recent advances, the remaining bottlenecks in deep generative models are necessity of extensive training and difficulties with generalization from small number of training examples. We develop a new generative model called…

Machine Learning · Statistics 2017-09-06 Sergey Bartunov , Dmitry P. Vetrov

Machine learning methods are commonly used to solve inverse problems, wherein an unknown signal must be estimated from few indirect measurements generated via a known acquisition procedure. In particular, neural networks perform well…

Machine Learning · Computer Science 2025-12-05 Hannah Laus , Suzanna Parkinson , Vasileios Charisopoulos , Felix Krahmer , Rebecca Willett

Although deep learning has shown its powerful performance in many applications, the mathematical principles behind neural networks are still mysterious. In this paper, we consider the problem of learning a one-hidden-layer neural network…

Machine Learning · Computer Science 2019-07-17 Shuhao Xia , Yuanming Shi

Transcriptional profiling on microarrays to obtain gene expressions has been used to facilitate cancer diagnosis. We propose a deep generative machine learning architecture (called DeepCancer) that learn features from unlabeled microarray…

Artificial Intelligence · Computer Science 2016-12-14 Rajendra Rana Bhat , Vivek Viswanath , Xiaolin Li

Learning portable neural networks is very essential for computer vision for the purpose that pre-trained heavy deep models can be well applied on edge devices such as mobile phones and micro sensors. Most existing deep neural network…

Machine Learning · Computer Science 2020-01-01 Hanting Chen , Yunhe Wang , Chang Xu , Zhaohui Yang , Chuanjian Liu , Boxin Shi , Chunjing Xu , Chao Xu , Qi Tian

It has recently been conjectured that neural network solution sets reachable via stochastic gradient descent (SGD) are convex, considering permutation invariances (Entezari et al., 2022). This means that a linear path can connect two…

Machine Learning · Computer Science 2024-06-11 Ankit Sonthalia , Alexander Rubinstein , Ehsan Abbasnejad , Seong Joon Oh

Deep learning uses neural networks which are parameterised by their weights. The neural networks are usually trained by tuning the weights to directly minimise a given loss function. In this paper we propose to re-parameterise the weights…

Neural and Evolutionary Computing · Computer Science 2022-03-14 Michael Fairbank , Spyridon Samothrakis , Luca Citi

A deep generative model is developed for representation and analysis of images, based on a hierarchical convolutional dictionary-learning framework. Stochastic {\em unpooling} is employed to link consecutive layers in the model, yielding…

Computer Vision and Pattern Recognition · Computer Science 2015-12-25 Yunchen Pu , Xin Yuan , Andrew Stevens , Chunyuan Li , Lawrence Carin

In this paper, we theoretically prove that gradient descent can find a global minimum of non-convex optimization of all layers for nonlinear deep neural networks of sizes commonly encountered in practice. The theory developed in this paper…

Machine Learning · Statistics 2020-06-18 Kenji Kawaguchi , Jiaoyang Huang

State-of-the-art training algorithms for deep learning models are based on stochastic gradient descent (SGD). Recently, many variations have been explored: perturbing parameters for better accuracy (such as in Extragradient), limiting SGD…

Machine Learning · Computer Science 2022-03-23 Amirkeivan Mohtashami , Martin Jaggi , Sebastian U. Stich

A new generative technique is presented in this paper that uses Deep Learning to reconstruct stellar spectra based on a set of stellar parameters. Two different Neural Networks were trained allowing the generation of new spectra. First, an…

Solar and Stellar Astrophysics · Physics 2024-01-25 Marwan Gebran