English
Related papers

Related papers: Hadamard-Riemannian Optimization for Margin-Varian…

200 papers

Regularized risk minimization with the binary hinge loss and its variants lies at the heart of many machine learning problems. Bundle methods for regularized risk minimization (BMRM) and the closely related SVMStruct are considered the best…

Machine Learning · Computer Science 2009-09-09 Ankan Saha , Xinhua Zhang , S. V. N. Vishwanathan

Understanding the generalization of deep neural networks is one of the most important tasks in deep learning. Although much progress has been made, theoretical error bounds still often behave disparately from empirical observations. In this…

Machine Learning · Computer Science 2021-11-09 Ching-Yao Chuang , Youssef Mroueh , Kristjan Greenewald , Antonio Torralba , Stefanie Jegelka

The chaotic nature of fluid flow and the uncertainties in initial conditions limit predictability. Small errors that occur in the initial condition can grow exponentially until they saturate at $\mathcal{O}$(1). Ensemble forecasting…

Numerical Analysis · Mathematics 2024-07-16 Rui Fang

We introduce a novel bias-variance decomposition for a range of strictly convex margin losses, including the logistic loss (minimized by the classic LogitBoost algorithm), as well as the squared margin loss and canonical boosting loss.…

Machine Learning · Statistics 2022-04-27 Danny Wood , Tingting Mu , Gavin Brown

Forecasting revenues by aggregating analyst forecasts is a fundamental problem in financial research and practice. A key objective in this context is to improve the accuracy of the forecast by optimizing two performance metrics: the hit…

Methodology · Statistics 2025-03-27 Henry D. van Eijk , Sujit K. Ghosh

We take a new look at parameter estimation for Gaussian Mixture Models (GMMs). In particular, we propose using \emph{Riemannian manifold optimization} as a powerful counterpart to Expectation Maximization (EM). An out-of-the-box invocation…

Machine Learning · Statistics 2015-06-26 Reshad Hosseini , Suvrit Sra

AI inference at the edge is becoming increasingly common for low-latency services. However, edge environments are power- and resource-constrained, and susceptible to failures. Conventional failure resilience approaches, such as cloud…

Predictions in the form of probability distributions are crucial for effective decision-making. Quantile regression enables such predictions within spatial prediction settings that aim to create improved precipitation datasets by merging…

Machine Learning · Computer Science 2025-08-05 Georgia Papacharalampous , Hristos Tyralis , Nikolaos Doulamis , Anastasios Doulamis

We develop in this paper a framework of empirical gain maximization (EGM) to address the robust regression problem where heavy-tailed noise or outliers may present in the response variable. The idea of EGM is to approximate the density…

Machine Learning · Computer Science 2021-01-13 Yunlong Feng , Qiang Wu

Hybrid ensemble, an essential branch of ensembles, has flourished in the regression field, with studies confirming diversity's importance. However, previous ensembles consider diversity in the sub-model training stage, with limited…

Machine Learning · Computer Science 2023-05-16 Yun Bai , Ganglin Tian , Yanfei Kang , Suling Jia

Standard machine learning models optimized for average performance often fail on minority subgroups and lack robustness to distribution shifts. This challenge worsens when subgroups are latent and affected by complex interactions among…

Machine Learning · Statistics 2025-09-23 Siqi Li , Molei Liu , Ziye Tian , Chuan Hong , Nan Liu

In this paper, we present a new ensemble-based filter method by reconstructing the analysis step of the particle filter through a transport map, which directly transports prior particles to posterior particles. The transport map is…

Machine Learning · Statistics 2026-05-14 Dengfei Zeng , Lijian Jiang

Model ensemble is a popular approach to produce a low-variance and well-generalized model. However, it induces large memory and inference costs, which are often not affordable for real-world deployment. Existing work has resorted to sharing…

Computation and Language · Computer Science 2022-04-19 Chen Liang , Pengcheng He , Yelong Shen , Weizhu Chen , Tuo Zhao

Ensemble learning has proven effective in improving predictive performance and estimating uncertainty in neural networks. However, conventional ensemble methods often suffer from redundant parameter usage and computational inefficiencies…

Machine Learning · Computer Science 2024-12-23 Arnav Kharbanda , Advait Chandorkar

Machine learning algorithms with empirical risk minimization usually suffer from poor generalization performance due to the greedy exploitation of correlations among the training data, which are not stable under distributional shifts.…

Machine Learning · Computer Science 2021-06-18 Jiashuo Liu , Zheyuan Hu , Peng Cui , Bo Li , Zheyan Shen

The goal in label-imbalanced and group-sensitive classification is to optimize relevant metrics such as balanced error and equal opportunity. Classical methods, such as weighted cross-entropy, fail when training deep nets to the terminal…

Machine Learning · Computer Science 2021-11-09 Ganesh Ramachandra Kini , Orestis Paraskevas , Samet Oymak , Christos Thrampoulidis

Ensembles of artificial neural networks show improved generalization capabilities that outperform those of single networks. However, for aggregation to be effective, the individual networks must be as accurate and diverse as possible. An…

Artificial Intelligence · Computer Science 2007-05-23 P. M. Granitto , P. F. Verdes , H. A. Ceccatto

We consider the problem of cost sensitive multiclass classification, where we would like to increase the sensitivity of an important class at the expense of a less important one. We adopt an {\em apportioned margin} framework to address…

Machine Learning · Computer Science 2020-02-05 Lee-Ad Gottlieb , Eran Kaufman , Aryeh Kontorovich

We establish the first mathematically rigorous link between Bayesian, variational Bayesian, and ensemble methods. A key step towards this it to reformulate the non-convex optimisation problem typically encountered in deep learning as a…

Machine Learning · Statistics 2023-10-24 Veit David Wild , Sahra Ghalebikesabi , Dino Sejdinovic , Jeremias Knoblauch

Deep metric learning aims to learn an embedding function, modeled as deep neural network. This embedding function usually puts semantically similar images close while dissimilar images far from each other in the learned embedding space.…

Computer Vision and Pattern Recognition · Computer Science 2018-09-03 Wonsik Kim , Bhavya Goyal , Kunal Chawla , Jungmin Lee , Keunjoo Kwon