Zobrazeno 1 - 10
of 530
pro vyhledávání: '"Paudice, A"'
In this paper, we provide novel optimal (or near optimal) convergence rates in expectation for the last iterate of a clipped version of the stochastic subgradient method. We consider nonsmooth convex problems, over possibly unbounded domains, under h
Externí odkaz:
http://arxiv.org/abs/2410.00573
Autor:
Eldowa, Khaled, Paudice, Andrea
In this paper, we provide novel tail bounds on the optimization error of Stochastic Mirror Descent for convex and Lipschitz objectives. Our analysis extends the existing tail bounds from the classical light-tailed Sub-Gaussian noise case to heavier-t
Externí odkaz:
http://arxiv.org/abs/2312.07142
The fat-shattering dimension characterizes the uniform convergence property of real-valued functions. The state-of-the-art upper bounds feature a multiplicative squared logarithmic factor on the sample complexity, leaving an open gap with the existin
Externí odkaz:
http://arxiv.org/abs/2307.06644
Autor:
Bressan, Marco, Cesa-Bianchi, Nicolò, Lattanzi, Silvio, Paudice, Andrea, Thiessen, Maximilian
We study exact active learning of binary and multiclass classifiers with margin. Given an $n$-point set $X \subset \mathbb{R}^m$, we want to learn any unknown classifier on $X$ whose classes have finite strong convex hull margin, a new notion extendi
Externí odkaz:
http://arxiv.org/abs/2209.03996
We analyze the cumulative regret of the Dyadic Search algorithm of Bachoc et al. [2022].
Comment: arXiv admin note: substantial text overlap with arXiv:2208.06720
Comment: arXiv admin note: substantial text overlap with arXiv:2208.06720
Externí odkaz:
http://arxiv.org/abs/2209.00885
In this work we study high probability bounds for stochastic subgradient methods under heavy tailed noise. In this setting the noise is only assumed to have finite variance as opposed to a sub-Gaussian distribution for which it is known that standard
Externí odkaz:
http://arxiv.org/abs/2208.08567
This paper studies a natural generalization of the problem of minimizing a univariate convex function $f$ by querying its values sequentially. At each time-step $t$, the optimizer can invest a budget $b_t$ in a query point $X_t$ of their choice to ob
Externí odkaz:
http://arxiv.org/abs/2208.06720
Autor:
Parrella, Veronica1 (AUTHOR) veronicaparrella19@gmail.com, Paudice, Michele1,2 (AUTHOR) michele.paudice@unige.it, Pittaluga, Michela3 (AUTHOR) michelapittaluga11@gmail.com, Allodi, Alessandra4 (AUTHOR) alessandra.allodi@hsanmartino.it, Fulcheri, Ezio1,5 (AUTHOR) ezio.fulcheri@fastwebnet.it, Buffelli, Francesca5 (AUTHOR), Barra, Fabio6 (AUTHOR) fabio.barra@icloud.com, Ferrero, Simone7,8 (AUTHOR) simone.ferrero@me.com, Arioni, Cesare4 (AUTHOR) cesare.arioni@hsanmartino.it, Vellone, Valerio Gaetano1,5 (AUTHOR) valerio.vellone@unige.it
Publikováno v:
Diagnostics (2075-4418). Jun2024, Vol. 14 Issue 11, p1157. 10p.
Autor:
Angerilli, Valentina, Vanoli, Alessandro, Celin, Giulia, Ceccon, Carlotta, Gasparello, Jessica, Sabbadin, Marianna, De Lisi, Giuseppe, Paudice, Michele, Lenti, Marco Vincenzo, Rovedatti, Laura, Di Sabatino, Antonio, Bazzocchi, Francesca, Lonardi, Sara, Savarino, Edoardo, Luchini, Claudio, Parente, Paola, Grillo, Federica, Mastracci, Luca, Fassan, Matteo
Publikováno v:
In Modern Pathology June 2024 37(6)
We study an active cluster recovery problem where, given a set of $n$ points and an oracle answering queries like "are these two points in the same cluster?", the task is to recover exactly all clusters using as few queries as possible. We begin by i
Externí odkaz:
http://arxiv.org/abs/2106.04913