English
Related papers

Related papers: Guiding Neural Network Initialization via Marginal…

200 papers

We develop simple methods for constructing likelihoods and parameter priors for learning about the parameters and structure of a Bayesian network. In particular, we introduce several assumptions that permit the construction of likelihoods…

Machine Learning · Computer Science 2021-07-01 David Heckerman , Dan Geiger

We consider the structured-output prediction problem through probabilistic approaches and generalize the "perturb-and-MAP" framework to more challenging weighted Hamming losses, which are crucial in applications. While in principle our…

Machine Learning · Statistics 2018-11-22 Tatiana Shpakova , Francis Bach , Anton Osokin

Training RNNs to learn long-term dependencies is difficult due to vanishing gradients. We explore an alternative solution based on explicit memorization using linear autoencoders for sequences, which allows to maximize the short-term memory…

Machine Learning · Computer Science 2020-11-06 Antonio Carta , Alessandro Sperduti , Davide Bacciu

We propose to use deep learning to estimate parameters in statistical models when standard likelihood estimation methods are computationally infeasible. We show how to estimate parameters from max-stable processes, where inference is…

Methodology · Statistics 2021-08-02 Amanda Lenzi , Julie Bessac , Johann Rudi , Michael L. Stein

The present work addresses the challenge of training neural networks for Dynamic Initial Margin (DIM) computation in counterparty credit risk, a task traditionally burdened by the high costs associated with generating training datasets…

Computational Finance · Quantitative Finance 2024-07-24 Joel P. Villarino , Álvaro Leitao

The successes of intelligent systems have quite relied on the artificial learning of information, which lead to the broad applications of neural learning solutions. As a common sense, the training of neural networks can be largely improved…

Machine Learning · Computer Science 2025-04-15 Miao Cheng , Feiyan Zhou , Hongwei Zou , Limin Wang

The marginal likelihood, or evidence, plays a central role in Bayesian model selection, yet remains notoriously challenging to compute in likelihood-free settings. While Simulation-Based Inference (SBI) techniques such as Sequential Neural…

Computation · Statistics 2025-07-14 Paul Bastide , Arnaud Estoup , Jean-Michel Marin , Julien Stoehr

Motivated by the observation that humans can learn patterns from two given images at one time, we propose a dual pattern learning network architecture in this paper. Unlike conventional networks, the proposed architecture has two input…

Computer Vision and Pattern Recognition · Computer Science 2018-06-12 Haimin Zhang , Min Xu

Good initialization is essential for training Deep Neural Networks (DNNs). Oftentimes such initialization is found through a trial and error approach, which has to be applied anew every time an architecture is substantially modified, or…

Machine Learning · Statistics 2022-06-29 Tianyu He , Darshil Doshi , Andrey Gromov

In computational mechanics, multiple models are often present to describe a physical system. While Bayesian model selection is a helpful tool to compare these models using measurement data, it requires the computationally expensive…

Computation · Statistics 2025-04-14 Subhayan De , Reza Farzad , Patrick T. Brewick , Erik A. Johnson , Steven F. Wojtkiewicz

Gradient descent and coordinate descent are well understood in terms of their asymptotic behavior, but less so in a transient regime often used for approximations in machine learning. We investigate how proper initialization can have a…

Machine Learning · Computer Science 2017-06-14 Hadi Daneshmand , Hamed Hassani , Thomas Hofmann

Pre-training is essential to deep learning model performance, especially in medical image analysis tasks where limited training data are available. However, existing pre-training methods are inflexible as the pre-trained weights of one…

Computer Vision and Pattern Recognition · Computer Science 2022-06-09 Fangxin Shang , Yehui Yang , Dalu Yang , Junde Wu , Xiaorong Wang , Yanwu Xu

Algorithmic design in neural architecture search (NAS) has received a lot of attention, aiming to improve performance and reduce computational cost. Despite the great advances made, few authors have proposed to tailor initialization…

Machine Learning · Computer Science 2021-11-08 Kalifou René Traoré , Andrés Camero , Xiao Xiang Zhu

Probabilistic models are often trained by maximum likelihood, which corresponds to minimizing a specific f-divergence between the model and data distribution. In light of recent successes in training Generative Adversarial Networks,…

Machine Learning · Statistics 2024-12-17 Mingtian Zhang , Thomas Bird , Raza Habib , Tianlin Xu , David Barber

Convolutional Neural Networks spread through computer vision like a wildfire, impacting almost all visual tasks imaginable. Despite this, few researchers dare to train their models from scratch. Most work builds on one of a handful of…

Computer Vision and Pattern Recognition · Computer Science 2016-09-26 Philipp Krähenbühl , Carl Doersch , Jeff Donahue , Trevor Darrell

Overparameterized neural networks often show a benign overfitting property in the sense of achieving excellent generalization behavior despite the number of parameters exceeding the number of training examples. A promising direction to…

Machine Learning · Computer Science 2026-04-23 Yunwen Lei , Yufeng Xie

Maximum likelihood estimation is effective for identifying dynamical systems, but applying it to large networks becomes computationally prohibitive. This paper introduces a maximum likelihood estimation method that enables identification of…

Systems and Control · Electrical Eng. & Systems 2025-11-06 João Victor Galvão da Mata , Anders Hansson , Martin S. Andersen

In past few years, various initialization schemes have been proposed. These schemes are glorot initialization, He initialization, initialization using orthogonal matrix, random walk method for initialization. Some of these methods stress on…

Machine Learning · Computer Science 2025-09-08 Vijay Pandey

Selecting the best regularization parameter in inverse problems is a classical and yet challenging problem. Recently, data-driven approaches have become popular to tackle this challenge. These approaches are appealing since they do require…

Statistics Theory · Mathematics 2025-10-22 Jonathan Chirinos Rodriguez , Ernesto De Vito , Cesare Molinari , Lorenzo Rosasco , Silvia Villa

Training neural networks with first order optimisation methods is at the core of the empirical success of deep learning. The scale of initialisation is a crucial factor, as small initialisations are generally associated to a feature…

Machine Learning · Computer Science 2025-09-16 Etienne Boursier , Nicolas Flammarion