English
Related papers

Related papers: Speedup from a different parametrization within th…

200 papers

Autoencoders are a category of neural networks with applications in numerous domains and hence, improvement of their performance is gaining substantial interest from the machine learning community. Ensemble methods, such as boosting, are…

Machine Learning · Computer Science 2021-10-29 Sai Krishna , Thulasi Tholeti , Sheetal Kalyani

Many automated machine learning methods, such as those for hyperparameter and neural architecture optimization, are computationally expensive because they involve training many different model configurations. In this work, we present a new…

Machine Learning · Computer Science 2020-06-08 Martin Wistuba , Tejaswini Pedapati

A new design methodology for neural networks that is guided by traditional algorithm design is presented. To prove our point, we present two heuristics and demonstrate an algorithmic technique for incorporating additional weights in their…

Machine Learning · Computer Science 2018-06-07 Abhejit Rajagopal , Shivkumar Chandrasekaran , Hrushikesh N. Mhaskar

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

Probabilistic programming has emerged as a powerful paradigm in statistics, applied science, and machine learning: by decoupling modelling from inference, it promises to allow modellers to directly reason about the processes generating…

Machine Learning · Statistics 2019-06-10 Maria I. Gorinova , Dave Moore , Matthew D. Hoffman

The main flaw of neural network ensembling is that it is exceptionally demanding computationally, especially, if the individual sub-models are large neural networks, which must be trained separately. Having in mind that modern DNNs can be…

Machine Learning · Computer Science 2020-03-31 Ludwik Bukowski , Witold Dzwinel

To solve ever more complex problems, Deep Neural Networks are scaled to billions of parameters, leading to huge computational costs. An effective approach to reduce computational requirements and increase efficiency is to prune unnecessary…

Machine learning frameworks adopt iterative optimizers to train neural networks. Conventional eager execution separates the updating of trainable parameters from forward and backward computations. However, this approach introduces…

Machine Learning · Computer Science 2021-04-02 Zixuan Jiang , Jiaqi Gu , Mingjie Liu , Keren Zhu , David Z. Pan

In machine learning, there is a fundamental trade-off between ease of optimization and expressive power. Neural Networks, in particular, have enormous expressive power and yet are notoriously challenging to train. The nature of that…

Machine Learning · Computer Science 2015-11-24 Diogo Almeida , Nate Sauder

Robust iterative methods for solving large sparse systems of linear algebraic equations often suffer from the problem of optimizing the corresponding tuning parameters. To improve the performance of the problem of interest, specific…

Numerical Analysis · Mathematics 2023-10-18 Andrey Petrushov , Boris Krasnopolsky

We re-evaluate the standard practice of sharing weights between input and output embeddings in state-of-the-art pre-trained language models. We show that decoupled embeddings provide increased modeling flexibility, allowing us to…

Computation and Language · Computer Science 2020-10-27 Hyung Won Chung , Thibault Févry , Henry Tsai , Melvin Johnson , Sebastian Ruder

Promising resolutions of the generalization puzzle observe that the actual number of parameters in a deep network is much smaller than naive estimates suggest. The renormalization group is a compelling example of a problem which has very…

Machine Learning · Computer Science 2020-12-08 Anita de Mello Koch , Ellen de Mello Koch , Robert de Mello Koch

Solving different types of optimization models (including parameters fitting) for support vector machines on large-scale training data is often an expensive computational task. This paper proposes a multilevel algorithmic framework that…

Machine Learning · Statistics 2014-10-14 Talayeh Razzaghi , Ilya Safro

Recurrent Neural Networks (RNN) are widely used to solve a variety of problems and as the quantity of data and the amount of available compute have increased, so have model sizes. The number of parameters in recent state-of-the-art networks…

Machine Learning · Computer Science 2017-11-08 Sharan Narang , Erich Elsen , Gregory Diamos , Shubho Sengupta

Data augmentation methods are indispensable heuristics to boost the performance of deep neural networks, especially in image recognition tasks. Recently, several studies have shown that augmentation strategies found by search algorithms…

Computer Vision and Pattern Recognition · Computer Science 2019-11-19 Ryuichiro Hataya , Jan Zdenek , Kazuki Yoshizoe , Hideki Nakayama

The vast majority of optimization and online learning algorithms today require some prior information about the data (often in the form of bounds on gradients or on the optimal parameter value). When this information is not available, these…

Machine Learning · Computer Science 2017-06-07 Ashok Cutkosky , Kwabena Boahen

Many practitioners who use the EM algorithm complain that it is sometimes slow. When does this happen, and what can be done about it? In this paper, we study the general class of bound optimization algorithms - including…

Machine Learning · Computer Science 2012-12-12 Ruslan R Salakhutdinov , Sam T Roweis , Zoubin Ghahramani

Deep neural networks are highly expressive models that have recently achieved state of the art performance on speech and visual recognition tasks. While their expressiveness is the reason they succeed, it also causes them to learn…

Computer Vision and Pattern Recognition · Computer Science 2014-02-20 Christian Szegedy , Wojciech Zaremba , Ilya Sutskever , Joan Bruna , Dumitru Erhan , Ian Goodfellow , Rob Fergus

This work investigates the ``small-vs-large gap'', where repeating on fewer samples can lead to compute saving during training compared to using a larger dataset. This is observed across algorithmic tasks, architectures and optimizers and…

Machine Learning · Computer Science 2026-05-21 Jingwen Liu , Ezra Edelman , Surbhi Goel , Bingbin Liu

In recent years, there is a growing interest in combining techniques attributed to the areas of Statistics and Machine Learning in order to obtain the benefits of both approaches. In this article, the statistical technique lasso for…

Machine Learning · Statistics 2023-09-08 David Delgado , Ernesto Curbelo , Danae Carreras