English
Related papers

Related papers: PopulAtion Parameter Averaging (PAPA)

200 papers

Ensembling is one approach that improves the performance of a neural network by combining a number of independent neural networks, usually by either averaging or summing up their individual outputs. We modify this ensembling approach by…

Neural and Evolutionary Computing · Computer Science 2024-01-05 Abien Fred Agarap , Arnulfo P. Azcarraga

Ensembles of neural networks (NNs) have long been used to estimate predictive uncertainty; a small number of NNs are trained from different initialisations and sometimes on differing versions of the dataset. The variance of the ensemble's…

Machine Learning · Computer Science 2018-11-30 Tim Pearce , Mohamed Zaki , Andy Neely

Model merging, particularly through weight averaging, has shown surprising effectiveness in saving computations and improving model performance without any additional training. However, the interpretability of why and how this technique…

Machine Learning · Computer Science 2025-08-20 Hu Wang , Congbo Ma , Ibrahim Almakky , Ian Reid , Gustavo Carneiro , Mohammad Yaqub

In distributed, or privacy-preserving learning, we are often given a set of probabilistic models estimated from different local repositories, and asked to combine them into a single model that gives efficient statistical estimation. A…

Machine Learning · Statistics 2017-03-01 Jun Han , Qiang Liu

Model selection strategies have been routinely employed to determine a model for data analysis in statistics, and further study and inference then often proceed as though the selected model were the true model that were known a priori. This…

Methodology · Statistics 2018-02-13 Priyam Mitra , Heng Lian , Ritwik Mitra , Hua Liang , Min-ge Xie

Many machine learning tasks involve learning functions that are known to be invariant or equivariant to certain symmetries of the input data. However, it is often challenging to design neural network architectures that respect these…

Machine Learning · Computer Science 2022-03-17 Omri Puny , Matan Atzmon , Heli Ben-Hamu , Ishan Misra , Aditya Grover , Edward J. Smith , Yaron Lipman

Ensemble methods in machine learning aim to improve prediction accuracy by combining multiple models. This is achieved by ensuring diversity among predictors to capture different data aspects. Homogeneous ensembles use identical models,…

Quantum Physics · Physics 2025-11-04 Emiliano Tolotti , Enrico Blanzieri , Davide Pastorello

Ensemble models refer to methods that combine a typically large number of classifiers into a compound prediction. The output of an ensemble method is the result of fitting a base-learning algorithm to a given data set, and obtaining diverse…

Machine Learning · Statistics 2019-06-10 Waldyn Martinez

We propose the particle dual averaging (PDA) method, which generalizes the dual averaging method in convex optimization to the optimization over probability distributions with quantitative runtime guarantee. The algorithm consists of an…

Machine Learning · Statistics 2022-01-25 Atsushi Nitanda , Denny Wu , Taiji Suzuki

Many real world data analysis problems exhibit invariant structure, and models that take advantage of this structure have shown impressive empirical performance, particularly in deep learning. While the literature contains a variety of…

Machine Learning · Computer Science 2020-05-04 Clare Lyle , Mark van der Wilk , Marta Kwiatkowska , Yarin Gal , Benjamin Bloem-Reddy

Data aggregation, also known as meta analysis, is widely used to combine knowledge on parameters shared in common (e.g., average treatment effect) between multiple studies. In this paper, we introduce an attractive data aggregation scheme…

Methodology · Statistics 2023-05-10 Snigdha Panigrahi , Jingshen Wang , Xuming He

Averaging, or smoothing, is a fundamental approach to obtain stable, de-noised estimates from noisy observations. In certain scenarios, observations made along trajectories of random dynamical systems are of particular interest. One popular…

Machine Learning · Statistics 2025-05-19 Frederik Köhne , Anton Schiela

Global average pooling (GAP) is a popular component in deep metric learning (DML) for aggregating features. Its effectiveness is often attributed to treating each feature vector as a distinct semantic entity and GAP as a combination of…

Machine Learning · Computer Science 2023-07-25 Yeti Z. Gurbuz , A. Aydin Alatan

When measuring the value of a function to be minimized is not only expensive but also with noise, the popular simultaneous perturbation stochastic approximation (SPSA) algorithm requires only two function values in each iteration. In this…

Optimization and Control · Mathematics 2022-03-08 Shiru Li , Yong Xia , Zi Xu

Multiple imputation provides an effective way to handle missing data. When several possible models are under consideration for the data, the multiple imputation is typically performed under a single-best model selected from the candidate…

Methodology · Statistics 2018-11-30 Gyuhyeong Goh , Jae Kwang Kim

This paper studies prediction with multiple candidate models, where the goal is to combine their outputs. This task is especially challenging in heterogeneous settings, where different models may be better suited to different inputs. We…

Machine Learning · Statistics 2025-10-28 Yuli Slavutsky , Sebastian Salazar , David M. Blei

Randomized trials are considered the gold standard for estimating causal effects. Trial findings are often used to inform policy and programming efforts, yet their results may not generalize well to a relevant target population due to…

Checkpoint merging is a technique for combining multiple model snapshots into a single superior model, potentially reducing training time for large language models. This paper explores checkpoint merging in the context of…

Machine Learning · Computer Science 2025-04-29 Shi Jie Yu , Sehyun Choi

The main aim in ensemble learning is using multiple individual classifiers outputs rather than one classifier output to aggregate them for more accurate classification. Generating an ensemble classifier generally is composed of three steps:…

Machine Learning · Computer Science 2021-01-26 Mansoureh Maadia , Uwe Aickelin , Hadi Akbarzadeh Khorshidi

In the literature, there are a few researches to design some parameters in the Proximal Point Algorithm (PPA), especially for the multi-objective convex optimizations. Introducing some parameters to PPA can make it more flexible and…

Optimization and Control · Mathematics 2018-12-11 Jianchao Bai , Jicheng Li , Pingfan Dai , Jiaofen Li