English
Related papers

Related papers: Adjusting Model Size in Continual Gaussian Process…

200 papers

Automatically determining the optimal size of a neural network for a given task without prior information currently requires an expensive global search and training many networks from scratch. In this paper, we address the problem of…

Machine Learning · Computer Science 2017-12-18 George Philipp , Jaime G. Carbonell

We address the challenge of optimizing meta-parameters (hyperparameters) in machine learning, a key factor for efficient training and high model performance. Rather than relying on expensive meta-parameter search methods, we introduce…

Machine Learning · Computer Science 2025-07-10 Arsalan Sharifnassab , Saber Salehkaleybar , Richard Sutton

In this paper, we consider the problem of Gaussian approximation for the online linear regression task. We derive the corresponding rates for the setting of a constant learning rate and study the explicit dependence of the convergence rate…

Machine Learning · Statistics 2025-09-18 Marat Khusainov , Marina Sheshukova , Alain Durmus , Sergey Samsonov

Data augmentation is commonly used to encode invariances in learning methods. However, this process is often performed in an inefficient manner, as artificial examples are created by applying a number of transformations to all points in the…

Machine Learning · Computer Science 2019-03-04 Michael Kuchnik , Virginia Smith

Does the process of training a neural network to solve a task tend to use all of the available weights even when the task could be solved with fewer weights? To address this question we study the effects of pruning fully connected,…

Machine Learning · Computer Science 2024-10-21 Nandi Schoots , Alex Jackson , Ali Kholmovaia , Peter McBurney , Murray Shanahan

Early stopping is a simple and widely used method to prevent over-training neural networks. We develop theoretical results to reveal the relationship between the optimal early stopping time and model dimension as well as sample size of the…

Machine Learning · Computer Science 2022-02-25 Ruoqi Shen , Liyao Gao , Yi-An Ma

Collecting operationally realistic data to inform machine learning models can be costly. Before collecting new data, it is helpful to understand where a model is deficient. For example, object detectors trained on images of rare objects may…

Machine Learning · Statistics 2025-12-24 Anna R. Flowers , Christopher T. Franck , Robert B. Gramacy , Justin A. Krometis

Convolutional neural networks (CNNs) are commonly trained using a fixed spatial image size predetermined for a given model. Although trained on images of aspecific size, it is well established that CNNs can be used to evaluate a wide range…

Computer Vision and Pattern Recognition · Computer Science 2019-08-27 Elad Hoffer , Berry Weinstein , Itay Hubara , Tal Ben-Nun , Torsten Hoefler , Daniel Soudry

Neural networks, a central tool in machine learning, have demonstrated remarkable, high fidelity performance on image recognition and classification tasks. These successes evince an ability to accurately represent high dimensional…

Machine Learning · Statistics 2023-02-08 Grant M. Rotskoff , Eric Vanden-Eijnden

Imbalanced datasets present a significant challenge for machine learning models, often leading to biased predictions. To address this issue, data augmentation techniques are widely used in natural language processing (NLP) to generate new…

Computation and Language · Computer Science 2023-04-21 Gabriel O. Assunção , Rafael Izbicki , Marcos O. Prates

For high-dimensional Gaussian data, we investigate theoretically how the features of a two-layer neural network adapt to the structure of the target function through a few large batch gradient descent steps, leading to an improvement in the…

Machine Learning · Statistics 2025-06-05 Yatin Dandi , Florent Krzakala , Bruno Loureiro , Luca Pesce , Ludovic Stephan

Molecular generative models, often employing GPT-style language modeling on molecular string representations, have shown promising capabilities when scaled to large datasets and model sizes. However, it remains unclear and subject to debate…

Machine Learning · Computer Science 2026-02-02 Dong Xu , Qihua Pan , Sisi Yuan , Jianqiang Li , Zexuan Zhu , Junkai Ji

Gaussian processes (GPs) are Bayesian non-parametric models popular in a variety of applications due to their accuracy and native uncertainty quantification (UQ). Tuning GP hyperparameters is critical to ensure the validity of prediction…

Machine Learning · Computer Science 2022-11-03 Killian Wood , Alec M. Dunton , Amanda Muyskens , Benjamin W. Priest

Gaussian processes (GPs) are a mature and widely-used component of the ML toolbox. One of their desirable qualities is automatic hyperparameter selection, which allows for training without user intervention. However, in many realistic…

Machine Learning · Computer Science 2024-02-16 Sebastian W. Ober , Artem Artemev , Marcel Wagenländer , Rudolfs Grobins , Mark van der Wilk

In recent years, the state-of-the-art in deep learning has been dominated by very large models that have been pre-trained on vast amounts of data. The paradigm is very simple: investing more computational resources (optimally) leads to…

Machine Learning · Computer Science 2024-05-24 Sotiris Anagnostidis , Gregor Bachmann , Imanol Schlag , Thomas Hofmann

Systems based on artificial neural networks (ANNs) have achieved state-of-the-art results in many natural language processing tasks. Although ANNs do not require manually engineered features, ANNs have many hyperparameters to be optimized.…

Computation and Language · Computer Science 2016-09-29 Franck Dernoncourt , Ji Young Lee

For many machine learning algorithms, predictive performance is critically affected by the hyperparameter values used to train them. However, tuning these hyperparameters can come at a high computational cost, especially on larger datasets,…

In continual learning, a learner has to keep learning from the data over its whole life time. A key issue is to decide what knowledge to keep and what knowledge to let go. In a neural network, this can be implemented by using a step-size…

Machine Learning · Computer Science 2024-02-01 Thomas Degris , Khurram Javed , Arsalan Sharifnassab , Yuxin Liu , Richard Sutton

Graphics Processing Units (GPUs) were once used solely for graphical computation tasks but with the increase in the use of machine learning applications, the use of GPUs to perform general-purpose computing has increased in the last few…

Hardware Architecture · Computer Science 2021-02-16 Asim Ikram , Muhammad Awais Ali , Mirza Omer Beg

Most deep neural networks are trained under fixed network architectures and require retraining when the architecture changes. If expanding the network's size is needed, it is necessary to retrain from scratch, which is expensive. To avoid…

Machine Learning · Computer Science 2023-11-09 Chau Pham , Piotr Teterwak , Soren Nelson , Bryan A. Plummer