English
Related papers

Related papers: Weighted Birkhoff Averages Accelerate Data-Driven …

200 papers

Federated Learning using the Federated Averaging algorithm has shown great advantages for large-scale applications that rely on collaborative learning, especially when the training data is either unbalanced or inaccessible due to privacy…

Machine Learning · Computer Science 2021-07-21 Jonatan Reyes , Lisa Di Jorio , Cecile Low-Kam , Marta Kersten-Oertel

The accelerated weight histogram (AWH) algorithm is an iterative extended ensemble algorithm, developed for statistical physics and computational biology applications. It is used to estimate free energy differences and expectations with…

Probability · Mathematics 2021-09-10 Henrik Hult , Guo-Jhen Wu

Sparse decision trees are one of the most common forms of interpretable models. While recent advances have produced algorithms that fully optimize sparse decision trees for prediction, that work does not address policy design, because the…

Machine Learning · Computer Science 2022-10-27 Ali Behrouz , Mathias Lecuyer , Cynthia Rudin , Margo Seltzer

Averaging checkpoints along the training trajectory is a simple yet powerful approach to improve the generalization performance of Machine Learning models and reduce training time. Motivated by these potential gains, and in an effort to…

Machine Learning · Computer Science 2025-11-25 Niccolò Ajroldi , Antonio Orvieto , Jonas Geiping

The weighted average is by far the most popular approach to combining multiple forecasts of some future outcome. This paper shows that both for probability or real-valued forecasts, a non-trivial weighted average of different forecasts is…

Methodology · Statistics 2015-09-28 Ville Satopää , Lyle Ungar

We consider a global variable consensus ADMM algorithm for solving large-scale PDE parameter estimation problems asynchronously and in parallel. To this end, we partition the data and distribute the resulting subproblems among the available…

Numerical Analysis · Mathematics 2019-05-01 Samy Wu Fung , Lars Ruthotto

While normalization techniques are widely used in deep learning, their theoretical understanding remains relatively limited. In this work, we establish the benefits of (generalized) weight normalization (WN) applied to the overparameterized…

Machine Learning · Computer Science 2025-10-02 Yudong Wei , Liang Zhang , Bingcong Li , Niao He

Weight averaging has become a standard technique for enhancing model performance. However, methods such as Stochastic Weight Averaging (SWA) and Latest Weight Averaging (LAWA) often require manually designed procedures to sample from the…

Machine Learning · Computer Science 2025-02-17 Peng Wang , Shengchao Hu , Zerui Tao , Guoxia Wang , Dianhai Yu , Li Shen , Quan Zheng , Dacheng Tao

Stochastic Gradient Descent (SGD) is one of the most popular algorithms in statistical and machine learning due to its computational and memory efficiency. Various averaging schemes have been proposed to accelerate the convergence of SGD in…

Machine Learning · Statistics 2025-04-08 Ziyang Wei , Wanrong Zhu , Wei Biao Wu

We study the averaging-based distributed optimization solvers over random networks. We show a general result on the convergence of such schemes using weight-matrices that are row-stochastic almost surely and column-stochastic in expectation…

Optimization and Control · Mathematics 2020-10-06 Adel Aghajan , Behrouz Touri

Aggregating multiple learners through an ensemble of models aim to make better predictions by capturing the underlying distribution of the data more accurately. Different ensembling methods, such as bagging, boosting, and stacking/blending,…

Machine Learning · Statistics 2020-11-03 Mohsen Shahhosseini , Guiping Hu , Hieu Pham

Stochastic gradient descent (SGD) has been widely studied in the literature from different angles, and is commonly employed for solving many big data machine learning problems. However, the averaging technique, which combines all iterative…

Machine Learning · Computer Science 2020-05-28 Zhishuai Guo , Yan Yan , Tianbao Yang

The Birkhoff Ergodic Theorem establishes pointwise convergence for integrable observables, but for $f\notin L^1$, no normalization yields almost sure convergence. This paper investigates trimmed ergodic sums, where the largest observations…

Dynamical Systems · Mathematics 2026-01-14 Max Auer , Sixu Liu

We provide an algorithm based on weighted-ensemble (WE) methods, to accurately sample systems at steady state. Applying our method to different one- and two-dimensional models, we succeed to calculate steady state probabilities of order…

Statistical Mechanics · Physics 2015-06-15 Justus A. Kromer , Lutz Schimansky-Geier , Raul Toral

We study correlation estimates of automatic sequences (that is, sequences computable by finite automata) with polynomial phases. As a consequence, we provide a new class of good weights for classical and polynomial ergodic theorems, not…

Dynamical Systems · Mathematics 2018-03-21 Tanja Eisner , Jakub Konieczny

High order upwind summation-by-parts finite difference operators have recently been developed. When combined with the simultaneous-approximation-term method to impose boundary conditions, the method converges faster than using traditional…

Numerical Analysis · Mathematics 2024-06-17 Yan Jiang , Siyang Wang

Objectives: Functional connectivity triggered by naturalistic stimulus (e.g., movies) and machine learning techniques provide a great insight in exploring the brain functions such as fluid intelligence. However, functional connectivity are…

Artificial Intelligence · Computer Science 2021-01-07 Xiaobo Liu , Su Yang

We propose Stochastic Weight Averaging in Parallel (SWAP), an algorithm to accelerate DNN training. Our algorithm uses large mini-batches to compute an approximate solution quickly and then refines it by averaging the weights of multiple…

Machine Learning · Computer Science 2020-01-09 Vipul Gupta , Santiago Akle Serrano , Dennis DeCoste

Wattenhofer [WW04] derive a complicated distributed algorithm to compute a weighted matching of an arbitrary weighted graph, that is at most a factor 5 away from the maximum weighted matching of that graph. We show that a variant of the…

Distributed, Parallel, and Cluster Computing · Computer Science 2007-05-23 Jaap-Henk Hoepman

We analyze a batched variant of Stochastic Gradient Descent (SGD) with weighted sampling distribution for smooth and non-smooth objective functions. We show that by distributing the batches computationally, a significant speedup in the…

Numerical Analysis · Mathematics 2017-03-02 Deanna Needell , Rachel Ward