Výsledky vyhledávání

Report

Optimal payoff under Bregman-Wasserstein divergence constraints

Autor: Pesenti, Silvana M., Vanduffel, Steven, Yang, Yang, Yao, Jing

We study optimal payoff choice for an expected utility maximizer under the constraint that their payoff is not allowed to deviate ``too much'' from a given benchmark. We solve this problem when the deviation is assessed via a Bregman-Wasserstein (BW)

Externí odkaz: http://arxiv.org/abs/2411.18397

Zobrazit plný text záznamu

Akademický článek

Talking about the Lost Generation : Sacred Music of Willaert, Gombert, and Michele Pesenti

Autor: Cumming, Julie E., Schubert, Peter

Publikováno v: The Journal of Musicology, 2015 Jul . 32(3), 323-327.

Externí odkaz: https://www.jstor.org/stable/10.1525/jm.2015.32.3.323

Zobrazit plný text záznamu

Report

Explaining Human Comparisons using Alignment-Importance Heatmaps

Autor: Truong, Nhut, Pesenti, Dario, Hasson, Uri

We present a computational explainability approach for human comparison tasks, using Alignment Importance Score (AIS) heatmaps derived from deep-vision models. The AIS reflects a feature-map's unique contribution to the alignment between Deep Neural

Externí odkaz: http://arxiv.org/abs/2409.16292

Zobrazit plný text záznamu

Report

Robust Elicitable Functionals

Autor: Miao, Kathleen E., Pesenti, Silvana M.

Elicitable functionals and (strict) consistent scoring functions are of interest due to their utility of determining (uniquely) optimal forecasts, and thus the ability to effectively backtest predictions. However, in practice, assuming that a distrib

Externí odkaz: http://arxiv.org/abs/2409.04412

Zobrazit plný text záznamu

Report

Kullback-Leibler Barycentre of Stochastic Processes

Autor: Jaimungal, Sebastian, Pesenti, Silvana M.

We consider the problem where an agent aims to combine the views and insights of different experts' models. Specifically, each expert proposes a diffusion process over a finite time horizon. The agent then combines the experts' models by minimising t

Externí odkaz: http://arxiv.org/abs/2407.04860

Zobrazit plný text záznamu

Report

Fourier Analysis of Iterative Algorithms

Autor: Jones, Chris, Pesenti, Lucas

We study a general class of nonlinear iterative algorithms which includes power iteration, belief propagation and approximate message passing, and many forms of gradient descent. When the input is a random matrix with i.i.d. entries, we use Boolean F

Externí odkaz: http://arxiv.org/abs/2404.07881

Zobrazit plný text záznamu