English
Related papers

Related papers: Guiding Neural Network Initialization via Marginal…

200 papers

This paper investigates multilevel initialization strategies for training very deep neural networks with a layer-parallel multigrid solver. The scheme is based on the continuous interpretation of the training problem as a problem of optimal…

Machine Learning · Computer Science 2019-12-20 Eric C. Cyr , Stefanie Günther , Jacob B. Schroder

Weight initialization is important for faster convergence and stability of deep neural networks training. In this paper, a robust initialization method is developed to address the training instability in long short-term memory (LSTM)…

We develop a computational procedure to estimate the covariance hyperparameters for semiparametric Gaussian process regression models with additive noise. Namely, the presented method can be used to efficiently estimate the variance of the…

Machine Learning · Computer Science 2022-06-22 Siavash Ameli , Shawn C. Shadden

Initialization plays a critical role in Deep Neural Network training, directly influencing convergence, stability, and generalization. Common approaches such as Glorot and He initializations rely on randomness, which can produce uneven…

Machine Learning · Computer Science 2025-12-11 Alberto Fernández-Hernández , Jose I. Mestre , Manuel F. Dolz , Jose Duato , Enrique S. Quintana-Ortí

We propose a framework for computing, optimizing and integrating with respect to a smooth marginal likelihood in statistical models that involve high-dimensional parameters/latent variables and continuous low-dimensional hyperparameters.…

Methodology · Statistics 2026-02-10 Omiros Papaspiliopoulos , Timothée Stumpf-Fétizon , Jonathan Weare

Deep neural network models owe their representational power to the high number of learnable parameters. It is often infeasible to run these largely parametrized deep models in limited resource environments, like mobile phones. Network…

Computer Vision and Pattern Recognition · Computer Science 2018-07-27 Ufuk Can Biçici , Cem Keskin , Lale Akarun

Mechanistic network models specify the mechanisms by which networks grow and change, allowing researchers to investigate complex systems using both simulation and analytical techniques. Unfortunately, it is difficult to write likelihoods…

Methodology · Statistics 2023-07-19 Jonathan Larson , Jukka-Pekka Onnela

In many real-world deployments of machine learning systems, data arrive piecemeal. These learning scenarios may be passive, where data arrive incrementally due to structural properties of the problem (e.g., daily financial data) or active,…

Machine Learning · Computer Science 2021-01-01 Jordan T. Ash , Ryan P. Adams

We introduce a novel method for partial optimization of the connections in Deep Differentiable Logic Gate Networks (LGNs). Our training method utilizes a probability distribution over a subset of connections per gate input, selecting the…

Machine Learning · Computer Science 2025-07-09 Wout Mommen , Lars Keuninckx , Matthias Hartmann , Piet Wambacq

Data augmentation is often used to incorporate inductive biases into models. Traditionally, these are hand-crafted and tuned with cross validation. The Bayesian paradigm for model selection provides a path towards end-to-end learning of…

Machine Learning · Statistics 2022-03-02 Pola Schwöbel , Martin Jørgensen , Sebastian W. Ober , Mark van der Wilk

We propose a lower bound on the log marginal likelihood of Gaussian process regression models that can be computed without matrix factorisation of the full kernel matrix. We show that approximate maximum likelihood learning of model…

Machine Learning · Statistics 2021-02-17 Artem Artemev , David R. Burt , Mark van der Wilk

We present a computationally-efficient strategy to initialise the hyperparameters of a Gaussian process (GP) avoiding the computation of the likelihood function. Our strategy can be used as a pretraining stage to find initial conditions for…

Machine Learning · Computer Science 2023-04-27 Felipe Tobar , Elsa Cazelles , Taco de Wolff

Stochastic gradient descent (SGD), one of the most fundamental optimization algorithms in machine learning (ML), can be recast through a continuous-time approximation as a Fokker-Planck equation for Langevin dynamics, a viewpoint that has…

Machine Learning · Statistics 2025-08-19 Hiroshi Horii , Sothea Has

Innovations in neural architectures have fostered significant breakthroughs in language modeling and computer vision. Unfortunately, novel architectures often result in challenging hyper-parameter choices and training instability if the…

Machine Learning · Computer Science 2021-11-25 Chen Zhu , Renkun Ni , Zheng Xu , Kezhi Kong , W. Ronny Huang , Tom Goldstein

Proper initialization is crucial to the optimization and the generalization of neural networks. However, most existing neural recommendation systems initialize the user and item embeddings randomly. In this work, we propose a new…

Information Retrieval · Computer Science 2021-08-13 Yinan Zhang , Boyang Li , Yong Liu , Hao Wang , Chunyan Miao

Stochastic variational inference is an established way to carry out approximate Bayesian inference for deep models. While there have been effective proposals for good initializations for loss minimization in deep learning, far less…

Machine Learning · Statistics 2019-01-28 Simone Rossi , Pietro Michiardi , Maurizio Filippone

In this work, we investigate Batch Normalization technique and propose its probabilistic interpretation. We propose a probabilistic model and show that Batch Normalization maximazes the lower bound of its marginalized log-likelihood. Then,…

Machine Learning · Statistics 2018-03-22 Andrei Atanov , Arsenii Ashukha , Dmitry Molchanov , Kirill Neklyudov , Dmitry Vetrov

Deep neural networks achieve state-of-the-art performance for a range of classification and inference tasks. However, the use of stochastic gradient descent combined with the nonconvexity of the underlying optimization problems renders…

Machine Learning · Computer Science 2020-01-29 Ramina Ghods , Andrew S. Lan , Tom Goldstein , Christoph Studer

Overparameterized Neural Networks (NN) display state-of-the-art performance. However, there is a growing need for smaller, energy-efficient, neural networks tobe able to use machine learning applications on devices with limited…

Machine Learning · Statistics 2021-05-21 Soufiane Hayou , Jean-Francois Ton , Arnaud Doucet , Yee Whye Teh

This paper introduces the hypervolume maximization with a single solution as an alternative to the mean loss minimization. The relationship between the two problems is proved through bounds on the cost function when an optimal solution to…

Machine Learning · Computer Science 2016-02-04 Conrado S. Miranda , Fernando J. Von Zuben