English
Related papers

Related papers: The Bregman-Tweedie Classification Model

200 papers

The logistic regression model is known to converge to a Poisson point process model if the binary response tends to infinitely imbalanced. In this paper, it is shown that this phenomenon is universal in a wide class of link functions on…

Statistics Theory · Mathematics 2013-04-23 Tomonari Sei

Supervised learning requires the specification of a loss function to minimise. While the theory of admissible losses from both a computational and statistical perspective is well-developed, these offer a panoply of different choices. In…

Machine Learning · Computer Science 2020-02-11 Richard Nock , Aditya Krishna Menon

Most of the non-asymptotic theoretical work in regression is carried out for the square loss, where estimators can be obtained through closed-form expressions. In this paper, we use and extend tools from the convex optimization literature,…

Machine Learning · Computer Science 2009-10-27 Francis Bach

In the usual statistical inference problem, we estimate an unknown parameter of a statistical model using the information in the random sample. A priori information about the parameter is also known in several real-life situations. One such…

Statistics Theory · Mathematics 2024-11-11 Lakshmi Kanta Patra , Constantinos Petropoulos , Shrajal Bajpai , Naresh Garg

The goal of binary classification is to estimate a discriminant function $\gamma$ from observations of covariate vectors and corresponding binary labels. We consider an elaboration of this problem in which the covariates are not available…

Statistics Theory · Mathematics 2009-09-29 XuanLong Nguyen , Martin J. Wainwright , Michael I. Jordan

The empirical use of variable transformations within (strictly) consistent loss functions is widespread, yet a theoretical understanding is lacking. To address this gap, we develop a theoretical framework that establishes formal…

Machine Learning · Statistics 2026-01-21 Hristos Tyralis , Georgia Papacharalampous

This study investigates component wise estimation of ordered variances of scale mixture of two normal distributions. For this study two special loss functions are considered namely squared error loss function and entropy loss function. We…

Statistics Theory · Mathematics 2026-01-28 Shrajal Bajpai , Lakshmi Kanta Patra

The notion of margin loss has been central to the development and analysis of algorithms for binary classification. To date, however, there remains no consensus as to the analogue of the margin loss for multiclass classification. In this…

Machine Learning · Statistics 2024-05-20 Yutong Wang , Clayton Scott

Multinomial logistic regression is one of the most popular models for modelling the effect of explanatory variables on a subject choice between a set of specified options. This model has found numerous applications in machine learning,…

Methodology · Statistics 2012-10-19 Cedric Archambeau , Francois Caron

In this paper, we propose a novel Branching Reinforcement Learning (Branching RL) model, and investigate both Regret Minimization (RM) and Reward-Free Exploration (RFE) metrics for this model. Unlike standard RL where the trajectory of each…

Machine Learning · Computer Science 2022-06-16 Yihan Du , Wei Chen

In this paper, we analyze the local convergence rate of optimistic mirror descent methods in stochastic variational inequalities, a class of optimization problems with important applications to learning theory and machine learning. Our…

Optimization and Control · Mathematics 2021-07-06 Waïss Azizian , Franck Iutzeler , Jérôme Malick , Panayotis Mertikopoulos

Let $\bx_j = \btheta +\bep_j, j=1,...,n$, be observations of an unknown parameter $\btheta$ in a Euclidean or separable Hilbert space $\scrH$, where $\bep_j$ are noises as random elements in $\scrH$ from a general distribution. We study the…

Statistics Theory · Mathematics 2022-01-03 Fan Zhou , Ping Li , Cun-Hui Zhang

We propose an extension of quasi-Newton methods, and investigate the convergence and the robustness properties of the proposed update formulae for the approximate Hessian matrix. Fletcher has studied a variational problem which derives the…

Computation · Statistics 2010-10-15 Takafumi Kanamori , Atsumi Ohara

This work introduces a sampling method capable of solving Bayesian inverse problems in function space. It does not assume the log-concavity of the likelihood, meaning that it is compatible with nonlinear inverse problems. The method…

Machine Learning · Statistics 2024-05-27 Lorenzo Baldassari , Ali Siahkoohi , Josselin Garnier , Knut Solna , Maarten V. de Hoop

Heckman selection model is the most popular econometric model in analysis of data with sample selection. However, selection models with Normal errors cannot accommodate heavy tails in the error distribution. Recently, Marchenko and Genton…

Computation · Statistics 2014-01-08 Peng Ding

While machine learning (ML) architectures have evolved rapidly to account for complex data, loss functions like cross-entropy remain mostly structure-agnostic in many real-world applications. However, the `class-symmetric' nature of these…

Machine Learning · Computer Science 2026-05-28 Yasser Taha , Grégoire Montavon , Nils Körber

Loss functions serve as the foundation of supervised learning and are often chosen prior to model development. To avoid potentially ad hoc choices of losses, statistical decision theory describes a desirable property for losses known as…

Machine Learning · Statistics 2023-11-30 Kevin Lam , Christian Walder , Spiridon Penev , Richard Nock

We systematically study the local single-valuedness of the Bregman proximal mapping and local smoothness of the Bregman--Moreau envelope of a nonconvex function under relative prox-regularity - an extension of prox-regularity - which was…

Optimization and Control · Mathematics 2020-02-03 Emanuel Laude , Peter Ochs , Daniel Cremers

This paper introduces the concept of uniform classification, which employs a unified threshold to classify all samples rather than adaptive threshold classifying each individual sample. We also propose the uniform classification accuracy as…

Computer Vision and Pattern Recognition · Computer Science 2024-03-13 Qiufu Li , Xi Jia , Jiancan Zhou , Linlin Shen , Jinming Duan

By analogy to the terminology of curved exponential families in statistics, we define curved Bregman divergences as Bregman divergences restricted to non-affine parameter subspaces and sub-dimensional Bregman divergences when the…

Information Theory · Computer Science 2026-03-30 Frank Nielsen