English
Related papers

Related papers: Edgeworth Expansion for Semi-hard Triplet Loss

200 papers

We study a Edgeworth-type refinement of the central limit theorem for the discretizacion error of It\^o integrals. Towards this end, we introduce a new approach, based on the anticipating It\^o formula. This alternative technique allows us…

Probability · Mathematics 2018-02-22 Elisa Alòs , Masaaki Fukasawa

In this article we generalize the classical Edgeworth expansion for the probability density function (PDF) of sums of a finite number of symmetric independent identically distributed random variables with a finite variance to sums of…

Statistical Mechanics · Physics 2015-05-20 Netanel Hazut , Shlomi Medalion , David A. Kessler , Eli Barkai

In this paper, we derive higher order Edgeworth expansions for the finite sample distributions of the subsampling-based t-statistic and the Wald statistic in the Gaussian location model under the so-called fixed-smoothing paradigm. In…

Statistics Theory · Mathematics 2013-09-11 Xianyang Zhang , Xiaofeng Shao

Distance metric learning (DML) is to learn the embeddings where examples from the same class are closer than examples from different classes. It can be cast as an optimization problem with triplet constraints. Due to the vast number of…

Computer Vision and Pattern Recognition · Computer Science 2020-04-16 Qi Qian , Lei Shang , Baigui Sun , Juhua Hu , Hao Li , Rong Jin

Network method of moments arXiv:1202.5101 is an important tool for nonparametric network inference. However, there has been little investigation on accurate descriptions of the sampling distributions of network moment statistics. In this…

Statistics Theory · Mathematics 2021-08-09 Yuan Zhang , Dong Xia

In this work we investigate the multivariate statistical description of the matter distribution in the nonlinear regime. We introduce the multivariate Edgeworth expansion of the lognormal distribution to model the cosmological matter field.…

Cosmology and Nongalactic Astrophysics · Physics 2015-05-20 F. S. Kitaura

The "typical" asymptotic behavior of the weighted sums of independent, identically distibuted random vectors in k-dimensional space is considered. It is shown that under finitnes of fifth absolute moment of an individual term the rate of…

Probability · Mathematics 2023-12-25 Sagak Ayvazyan

We study Edgeworth expansions in limit theorems for self-normalized sums. Non-uniform bounds for expansions in the central limit theorem are established while only imposing minimal moment conditions. Within this result, we address the case…

Probability · Mathematics 2022-08-11 Pascal Beckedorf , Angelika Rohde

Deep metric learning objectives (e.g., triplet loss) require storing and comparing high-dimensional embeddings, making the per-batch loss buffer scale as $O(S\cdot D)$, where $S$ is the number of samples in a batch and $D$ is the feature…

Computer Vision and Pattern Recognition · Computer Science 2026-01-21 Alif Elham Khan , Mohammad Junayed Hasan , Humayra Anjum , Nabeel Mohammed

This paper extends Edgeworth-Cornish-Fisher expansions for the distribution and quantiles of nonparametric estimates in two ways. Firstly it allows observations to have different distributions. Secondly it allows the observations to be…

Methodology · Statistics 2010-02-24 C. S. Withers , S. Nadarajah

We obtain asymptotic expansions for local probabilities of partial sums for uniformly bounded independent but not necessarily identically distributed integer-valued random variables. The expansions involve products of polynomials and…

Probability · Mathematics 2020-12-02 Dmitry Dolgopyat , Yeor Hafouta

Contrastive loss and triplet loss are widely used objectives in deep metric learning, yet their effects on representation quality remain insufficiently understood. We present a theoretical and empirical comparison of these losses, focusing…

Multimedia · Computer Science 2025-10-07 Donghuo Zeng

Deep representation learning using triplet network for classification suffers from a lack of theoretical foundation and difficulty in tuning both the network and classifiers for performance. To address the problem, local-margin triplet loss…

Computer Vision and Pattern Recognition · Computer Science 2019-11-20 Phawis Thammasorn , Daniel Hippe , Wanpracha Chaovalitwongse , Matthew Spraker , Landon Wootton , Matthew Nyflot , Stephanie Combs , Jan Peeken , Eric Ford

Recent studies have highlighted that deep neural networks (DNNs) are vulnerable to adversarial examples. In this paper, we improve the robustness of DNNs by utilizing techniques of Distance Metric Learning. Specifically, we incorporate…

Machine Learning · Computer Science 2019-05-29 Pengcheng Li , Jinfeng Yi , Bowen Zhou , Lijun Zhang

This paper presents new results on the Edgeworth expansion for high frequency functionals of continuous diffusion processes. We derive asymptotic expansions for weighted functionals of the Brownian motion and apply them to provide the…

Probability · Mathematics 2013-09-10 Mark Podolskij , Nakahiro Yoshida

In the past few years, triplet loss-based metric embeddings have become a de-facto standard for several important computer vision problems, most no-tably, person reidentification. On the other hand, in the area of speech recognition the…

Audio and Speech Processing · Electrical Eng. & Systems 2022-02-08 Roman Vygon , Nikolay Mikhaylovskiy

In this paper we present the Edgeworth expansion for the Euler approximation scheme of a continuous diffusion process driven by a Brownian motion. Our methodology is based upon a recent work \cite{Yoshida2013}, which establishes Edgeworth…

Probability · Mathematics 2018-11-20 Mark Podolskij , Bezirgen Veliyev , Nakahiro Yoshida

We consider triangular arrays of Markov chains that converge weakly to a diffusion process. Edgeworth type expansions of third order for transition densities are proved. This is done for time horizons that converge to 0. For this purpose we…

Probability · Mathematics 2007-06-13 Valentin Konakov , Enno Mammen

Finite-width fully connected neural networks with Gaussian-initialized weights deviate from their infinite-width Gaussian limit, exhibiting non-vanishing higher-order cumulants. We approximate these deviations, for a neural network…

Machine Learning · Statistics 2026-05-26 Lucia Celli

We address the problem of distance metric learning in visual similarity search, defined as learning an image embedding model which projects images into Euclidean space where semantically and visually similar images are closer and dissimilar…

Computer Vision and Pattern Recognition · Computer Science 2019-10-01 Xiaonan Zhao , Huan Qi , Rui Luo , Larry Davis