English
Related papers

Related papers: Fast Compute for ML Optimization

200 papers

Quantification of uncertainty is one of the most promising approaches to establish safe machine learning. Despite its importance, it is far from being generally solved, especially for neural networks. One of the most commonly used…

Machine Learning · Computer Science 2021-01-11 Joachim Sicking , Maram Akila , Maximilian Pintz , Tim Wirtz , Asja Fischer , Stefan Wrobel

In this paper, we propose a unified view of gradient-based algorithms for stochastic convex composite optimization by extending the concept of estimate sequence introduced by Nesterov. More precisely, we interpret a large class of…

Machine Learning · Statistics 2020-09-07 Andrei Kulunchakov , Julien Mairal

Overparametrized Deep Neural Networks (DNNs) often achieve astounding performances, but may potentially result in severe generalization error. Recently, the relation between the sharpness of the loss landscape and the generalization error…

Artificial Intelligence · Computer Science 2022-05-31 Jiawei Du , Hanshu Yan , Jiashi Feng , Joey Tianyi Zhou , Liangli Zhen , Rick Siow Mong Goh , Vincent Y. F. Tan

Many loss functions in representation learning are invariant under a continuous symmetry transformation. For example, the loss function of word embeddings (Mikolov et al., 2013) remains unchanged if we simultaneously rotate all word and…

Machine Learning · Statistics 2020-07-21 Robert Bamler , Stephan Mandt

Fast Incremental Expectation Maximization (FIEM) is a version of the EM framework for large datasets. In this paper, we first recast FIEM and other incremental EM type algorithms in the {\em Stochastic Approximation within EM} framework.…

Machine Learning · Computer Science 2021-01-01 Gersende Fort , P. Gach , E. Moulines

Mixed linear regression (MLR) model is among the most exemplary statistical tools for modeling non-linear distributions using a mixture of linear models. When the additive noise in MLR model is Gaussian, Expectation-Maximization (EM)…

Machine Learning · Statistics 2021-05-14 Babak Barazandeh , Ali Ghafelebashi , Meisam Razaviyayn , Ram Sriharsha

The Expectation Maximization (EM) algorithm is of key importance for inference in latent variable models including mixture of regressors and experts, missing observations. This paper introduces a novel EM algorithm, called…

Machine Learning · Computer Science 2020-12-04 Gersende Fort , Eric Moulines , Hoi-To Wai

Expectation Maximization (EM) is among the most popular algorithms for estimating parameters of statistical models. However, EM, which is an iterative algorithm based on the maximum likelihood principle, is generally only guaranteed to find…

Statistics Theory · Mathematics 2016-08-30 Ji Xu , Daniel Hsu , Arian Maleki

We propose a continuous-time scheme for large-scale optimization that introduces individual, adaptive momentum coefficients regulated by the kinetic energy of each model parameter. This approach automatically adjusts to local landscape…

Machine Learning · Computer Science 2026-02-03 Aikaterini Karoni , Rajit Rajpal , Benedict Leimkuhler , Gabriel Stoltz

In this paper, we propose a dynamical systems perspective of the Expectation-Maximization (EM) algorithm. More precisely, we can analyze the EM algorithm as a nonlinear state-space dynamical system. The EM algorithm is widely adopted for…

Optimization and Control · Mathematics 2018-10-05 Orlando Romero , Sarthak Chatterjee , Sérgio Pequito

Stochastic gradient descent with momentum (SGDM) is one of the most widely used optimization algorithms in machine learning. While optimization properties of SGDM have been extensively studied in the literature, it remains insufficiently…

Machine Learning · Computer Science 2026-05-28 Yunwen Lei , Zimeng Wang , Xiaoming Yuan

Optimization plays a key role in machine learning. Recently, stochastic second-order methods have attracted much attention due to their low computational cost in each iteration. However, these algorithms might perform poorly especially if…

Machine Learning · Computer Science 2017-10-25 Haishan Ye , Zhihua Zhang

We describe convergence acceleration schemes for multistep optimization algorithms. The extrapolated solution is written as a nonlinear average of the iterates produced by the original optimization method. Our analysis does not need the…

Optimization and Control · Mathematics 2019-10-18 Raghu Bollapragada , Damien Scieur , Alexandre d'Aspremont

We propose new methods to speed up convergence of the Alternating Direction Method of Multipliers (ADMM), a common optimization tool in the context of large scale and distributed learning. The proposed method accelerates the speed of…

Machine Learning · Computer Science 2016-04-05 Changkyu Song , Sejong Yoon , Vladimir Pavlovic

The Adaptive Smoothing Method (ASM) is a data-driven approach for traffic state estimation. It interpolates unobserved traffic quantities by smoothing measurements along spatio-temporal directions defined by characteristic traffic wave…

Optimization and Control · Mathematics 2022-12-14 Chuhan Yang , Bilal Thonnam Thodi , Saif Eddin Jabari

Fine-grained sparsity promises higher parametric capacity without proportional per-token compute, but often suffers from training instability, load balancing, and communication overhead. We introduce STEM (Scaling Transformers with…

We estimate a general mixture of Markov jump processes. The key novel feature of the proposed mixture is that the transition intensity matrices of the Markov processes comprising the mixture are entirely unconstrained. The Markov processes…

Methodology · Statistics 2022-04-12 Halina Frydman , Budhi Surya

Mixtures of generalized normal distributions (MGND) have gained popularity for modelling datasets with complex statistical behaviours. However, the estimation of the shape parameter within the maximum likelihood framework is quite complex,…

Methodology · Statistics 2025-06-03 Pierdomenico Duttilo , Stefano Antonio Gattone

Accurate and high-resolution Earth system model (ESM) simulations are essential to assess the ecological and socio-economic impacts of anthropogenic climate change, but are computationally too expensive to be run at sufficiently high…

Atmospheric and Oceanic Physics · Physics 2025-02-27 Philipp Hess , Michael Aich , Baoxiang Pan , Niklas Boers

Existing gradient-based optimization methods update parameters locally, in a direction that minimizes the loss function. We study a different approach, symmetry teleportation, that allows parameters to travel a large distance on the loss…

Machine Learning · Computer Science 2023-01-06 Bo Zhao , Nima Dehmamy , Robin Walters , Rose Yu