English
Related papers

Related papers: Alpha-divergence loss function for neural density …

200 papers

Deep neural networks (DNNs) are poorly calibrated when trained in conventional ways. To improve confidence calibration of DNNs, we propose a novel training method, distance-based learning from errors (DBLE). DBLE bases its confidence…

Machine Learning · Computer Science 2020-02-19 Chen Xing , Sercan Arik , Zizhao Zhang , Tomas Pfister

We study the problem of nonparametric estimation of density functions with a product form on the domain $\triangle=\{( x_1, \ldots, x_d)\in \mathbb{R}^d, 0\leq x_1\leq \dots \leq x_d \leq 1\}$. Such densities appear in the random truncation…

Statistics Theory · Mathematics 2016-04-22 Cristina Butucea , Jean-François Delmas , Anne Dutfoy , Richard Fischer

Variational representations of divergences and distances between high-dimensional probability distributions offer significant theoretical insights and practical advantages in numerous research areas. Recently, they have gained popularity in…

Machine Learning · Computer Science 2022-03-25 Jeremiah Birrell , Markos A. Katsoulakis , Yannis Pantazis

In this paper, we propose to solve a regularized distributionally robust learning problem in the decentralized setting, taking into account the data distribution shift. By adding a Kullback-Liebler regularization function to the robust…

Machine Learning · Computer Science 2022-09-13 Chaouki Ben Issaid , Anis Elgabli , Mehdi Bennis

Selecting the optimal resolution for discretizing high-dimensional data is a central problem in physics and data analysis, particularly in unsupervised settings where the underlying distribution is unknown. The Relevance-Resolution…

Statistical Mechanics · Physics 2026-03-06 Margherita Mele , Daniel Campos Moreno , Raffaello Potestio

We consider a generalization of the classifier-based density-ratio estimation task to a quasiprobabilistic setting where probability densities can be negative. The problem with most loss functions used for this task is that they implicitly…

Machine Learning · Statistics 2025-12-24 Matthew Drnevich , Stephen Jiggins , Kyle Cranmer

Dense retrieval models use bi-encoder network architectures for learning query and document representations. These representations are often in the form of a vector representation and their similarities are often computed using the dot…

Information Retrieval · Computer Science 2023-05-01 Hamed Zamani , Michael Bendersky

We propose a flexible method for estimating luminosity functions (LFs) based on kernel density estimation (KDE), the most popular nonparametric density estimation approach developed in modern statistics, to overcome issues surrounding…

Methodology · Statistics 2020-05-01 Zunli Yuan , Matt J. Jarvis , Jiancheng Wang

This study reveals the inherent tolerance of contrastive learning (CL) towards sampling bias, wherein negative samples may encompass similar semantics (\eg labels). However, existing theories fall short in providing explanations for this…

Machine Learning · Computer Science 2023-10-18 Junkang Wu , Jiawei Chen , Jiancan Wu , Wentao Shi , Xiang Wang , Xiangnan He

We study a family of loss functions named label-distributionally robust (LDR) losses for multi-class classification that are formulated from distributionally robust optimization (DRO) perspective, where the uncertainty in the given label…

Machine Learning · Computer Science 2023-06-29 Dixian Zhu , Yiming Ying , Tianbao Yang

Distributionally robust optimization (DRO) is a widely-used approach to learn models that are robust against distribution shift. Compared with the standard optimization setting, the objective function in DRO is more difficult to optimize,…

Machine Learning · Computer Science 2021-10-27 Jikai Jin , Bohang Zhang , Haiyang Wang , Liwei Wang

We propose kernel distributionally robust optimization (Kernel DRO) using insights from the robust optimization theory and functional analysis. Our method uses reproducing kernel Hilbert spaces (RKHS) to construct a wide range of convex…

Optimization and Control · Mathematics 2021-06-28 Jia-Jie Zhu , Wittawat Jitkrittum , Moritz Diehl , Bernhard Schölkopf

In this work, we propose new objective functions to train deep neural network based density ratio estimators and apply it to a change point detection problem. Existing methods use linear combinations of kernels to approximate the density…

Machine Learning · Computer Science 2019-05-27 Haidar Khan , Lara Marcuse , Bülent Yener

In algorithms for solving optimization problems constrained to a smooth manifold, retractions are a well-established tool to ensure that the iterates stay on the manifold. More recently, it has been demonstrated that retractions are a…

Numerical Analysis · Mathematics 2024-03-11 Axel Séguin , Gianluca Ceruti , Daniel Kressner

We derive the divergence-kernel formula for the linear response of random dynamical systems. Specifically, the pathwise expression is for the parameter-derivative of the marginal or stationary density, not an averaged observable. Our…

Dynamical Systems · Mathematics 2025-12-30 Angxiu Ni

We present Flow-Guided Density Ratio Learning (FDRL), a simple and scalable approach to generative modeling which builds on the stale (time-independent) approximation of the gradient flow of entropy-regularized f-divergences introduced in…

Machine Learning · Computer Science 2024-06-06 Alvin Heng , Abdul Fatir Ansari , Harold Soh

Estimating the ratio of two probability densities from finitely many observations of the densities is a central problem in machine learning and statistics with applications in two-sample testing, divergence estimation, generative modeling,…

Machine Learning · Computer Science 2024-03-12 Werner Zellinger , Stefan Kindermann , Sergei V. Pereverzyev

Training deep neural networks (DNNs) is an important and challenging optimization problem in machine learning due to its non-convexity and non-separable structure. The alternating minimization (AM) approaches split the composition structure…

Machine Learning · Computer Science 2023-04-05 Jintao Xu , Chenglong Bao , Wenxun Xing

This paper aims to address a common challenge in deep learning-based image transformation methods, such as image enhancement and super-resolution, which heavily rely on precisely aligned paired datasets with pixel-level alignments. However,…

Computer Vision and Pattern Recognition · Computer Science 2024-02-29 Zhangkai Ni , Juncheng Wu , Zian Wang , Wenhan Yang , Hanli Wang , Lin Ma

A loss function measures the discrepancy between the true values (observations) and their estimated fits, for a given instance of data. A loss function is said to be proper (unbiased, Fisher consistent) if the fits are defined over a unit…

Information Theory · Computer Science 2018-05-11 Amichai Painsky , Gregory W. Wornell
‹ Prev 1 4 5 6 7 8 10 Next ›