English
Related papers

Related papers: A Baseline $T\log^2 T$ Upper Bound for KL-Regulari…

200 papers

We prove the leading order of a conjecture by Fyodorov, Hiary and Keating, about the maximum of the Riemann zeta function on random intervals along the critical line. More precisely, as $T \rightarrow \infty$ for a set of $t \in [T, 2T]$ of…

Sinkhorn's algorithm is a method of choice to solve large-scale optimal transport (OT) problems. In this context, it involves an inverse temperature parameter $\beta$ that determines the speed-accuracy trade-off. To improve this trade-off,…

Machine Learning · Computer Science 2024-08-22 Lénaïc Chizat

This study introduces a novel approach for estimating plane-wave coefficients in sound field reconstruction, specifically addressing challenges posed by error-in-variable phase perturbations. Such systematic errors typically arise from…

Signal Processing · Electrical Eng. & Systems 2026-02-06 Yuyang Liu , Johan Karlsson , Filip Elvander

This work studies the quantitative stability of the quadratic optimal transport map between a fixed probability density $\rho$ and a probability measure $\mu$ on R^d , which we denote T$\mu$. Assuming that the source density $\rho$ is…

Functional Analysis · Mathematics 2023-03-09 Alex Delalande , Quentin Merigot

The beat time {\tau}_{fpt} associated with the energy transfer between two coupled oscillators is dictated by the bandwidth theorem which sets a lower bound {\tau}_{fpt}\sim 1/{\delta}{\omega}. We show, both experimentally and…

Classical Physics · Physics 2012-06-29 Hamidreza Ramezani , J. Schindler , F. M. Ellis , Uwe Guenther , Tsampikos Kottos

In this article, we give explicit bounds of order $\log t$ for $\sigma$ close to $1$, for two quantities: $|\zeta'(\sigma +it)/\zeta(\sigma +it)|$ and $|1/\zeta(\sigma +it)|$. We correct an error in the literature, and especially in the…

Number Theory · Mathematics 2026-02-03 Nicol Leong

We develop a novel theoretical framework for understating OT schemes respecting a class structure. For this purpose, we propose a convex OT program with a sum-of-norms regularization term, which provably recovers the underlying class…

Machine Learning · Computer Science 2023-05-23 Arman Rahbar , Ashkan Panahi , Morteza Haghir Chehreghani , Devdatt Dubhashi , Hamid Krim

Estimating Wasserstein distances between two high-dimensional densities suffers from the curse of dimensionality: one needs an exponential (wrt dimension) number of samples to ensure that the distance between two empirical measures is…

Machine Learning · Statistics 2020-07-13 François-Pierre Paty , Alexandre d'Aspremont , Marco Cuturi

We prove a near-unconditionality property for the normalized Haar basis of $L_1[0,1]$.

Functional Analysis · Mathematics 2016-03-21 Steven J. Dilworth , Smbat Gogyan , Denka Kutzarova , Thomas Schlumprecht

In this paper, we consider Strassen's version of optimal transport (OT) problem, which concerns minimizing the excess-cost probability (i.e., the probability that the cost is larger than a given value) over all couplings of two given…

Probability · Mathematics 2022-02-22 Lei Yu

We study the estimation of $\beta$ for the nonlinear model $y = f(X\sp{\top}\beta) + \epsilon$ when $f$ is a nonlinear transformation that is known, $\beta$ has sparse nonzero coordinates, and the number of observations can be much smaller…

Statistics Theory · Mathematics 2009-10-15 Zhiyi Chi

Perturbative considerations account for the properties of conventional metals, including the range of temperatures where the transport scattering rate is $1/\tau_\text{tr} = 2\pi \lambda T$, where $\lambda$ is a dimensionless strength of…

Strongly Correlated Electrons · Physics 2023-05-16 Chaitanya Murthy , Akshat Pandey , Ilya Esterlis , Steven A. Kivelson

Transport systems on networks are crucial in various applications, but face a significant risk of being adversely affected by unforeseen circumstances such as disasters. The application of entropy-regularized optimal transport (OT) on graph…

Machine Learning · Computer Science 2025-05-07 Koshi Oishi , Yota Hashizume , Tomohiko Jimbo , Hirotaka Kaji , Kenji Kashima

Consider the finite regular language L_n = {w0 : w \in {0,1}^*, |w| \le n}. It was shown by Ambainis, Nayak, Ta-Shma and Vazirani that while this language is accepted by a deterministic finite automaton of size O(n), any one-way quantum…

Quantum Physics · Physics 2007-05-23 Ashwin Nayak

Optimal Transport (OT) theory has seen an increasing amount of attention from the computer science community due to its potency and relevance in modeling and machine learning. It introduces means that serve as powerful ways to compare…

Machine Learning · Computer Science 2021-06-04 Luis Caicedo Torres , Luiz Manella Pereira , M. Hadi Amini

The empirical optimal transport (OT) cost between two probability measures from random data is a fundamental quantity in transport based data analysis. In this work, we derive novel guarantees for its convergence rate when the involved…

Statistics Theory · Mathematics 2022-02-22 Shayan Hundrieser , Thomas Staudt , Axel Munk

Optimal transport has emerged as a fundamental methodology with applications spanning multiple research areas in recent years. However, the convergence rate of the empirical estimator to its population counterpart suffers from the curse of…

Statistics Theory · Mathematics 2025-10-06 Jiaping Yang , Yunxin Zhang

Over the past few years, numerous computational models have been developed to solve Optimal Transport (OT) in a stochastic setting, where distributions are represented by samples and where the goal is to find the closest map to the ground…

Statistics Theory · Mathematics 2023-02-01 Adrien Vacher , François-Xavier Vialard

We provide an explicit family of pairs $(\alpha, \beta) \in \mathbb{R}^k \times \mathbb{R}^k$ such that for sufficiently regular $f$, there is a constant $C>0$ for which the theta sum bound…

Number Theory · Mathematics 2023-07-21 Francesco Cellarosi , Tariq Osman

In graph analysis, a classic task consists in computing similarity measures between (groups of) nodes. In latent space random graphs, nodes are associated to unknown latent variables. One may then seek to compute distances directly in the…

Machine Learning · Statistics 2022-01-12 Nicolas Keriven
‹ Prev 1 4 5 6 7 8 10 Next ›