Zobrazeno 1 - 10
of 130
pro vyhledávání: '"Ponti, Andrea"'
Autor:
Ponti, Andrea
Graphs are ubiquitous in various fields, and deep learning methods have been successful applied in graph classification tasks. However, building large and diverse graph datasets for training can be expensive. While augmentation techniques exist for s
Externí odkaz:
http://arxiv.org/abs/2404.08376
Autor:
Sabbatella, Antonio, Ponti, Andrea, Candelieri, Antonio, Giordani, Ilaria, Archetti, Francesco
A prompt is a sequence of symbol or tokens, selected from a vocabulary according to some rule, which is prepended/concatenated to a textual query. A key problem is how to select the sequence of tokens: in this paper we formulate it as a combinatorial
Externí odkaz:
http://arxiv.org/abs/2312.00471
Gaussian Process regression is a kernel method successfully adopted in many real-life applications. Recently, there is a growing interest on extending this method to non-Euclidean input spaces, like the one considered in this paper, consisting of pro
Externí odkaz:
http://arxiv.org/abs/2212.01310
Optimal resource allocation is gaining a renewed interest due its relevance as a core problem in managing, over time, cloud and high-performance computing facilities. Semi-Bandit Feedback (SBF) is the reference method for efficiently solving this pro
Externí odkaz:
http://arxiv.org/abs/2210.05977
There is a consensus that focusing only on accuracy in searching for optimal machine learning models amplifies biases contained in the data, leading to unfair predictions and decision supports. Recently, multi-objective hyperparameter optimization ha
Externí odkaz:
http://arxiv.org/abs/2205.08835
The main objective of this paper is to outline a theoretical framework to characterise humans' decision-making strategies under uncertainty, in particular active learning in a black-box optimization task and trading-off between information gathering
Externí odkaz:
http://arxiv.org/abs/2112.06292
Autor:
Ponti, Andrea
The multi-task learning (MTL) paradigm can be traced back to an early paper of Caruana (1997) in which it was argued that data from multiple tasks can be used with the aim to obtain a better performance over learning each task independently. A soluti
Externí odkaz:
http://arxiv.org/abs/2112.04891
Optimal sensor placement (SP) usually minimizes an impact measure, such as the amount of contaminated water or the number of inhabitants affected before detection. The common choice is to minimize the minimum detection time (MDT) averaged over a set
Externí odkaz:
http://arxiv.org/abs/2103.04862
The main objective of this paper is to outline a theoretical framework to analyse how humans' decision-making strategies under uncertainty manage the trade-off between information gathering (exploration) and reward seeking (exploitation). A key obser
Externí odkaz:
http://arxiv.org/abs/2102.07647
Resilience is meant as the capability of a networked infrastructure to provide its service even if some components fail: in this paper we focus on how resilience depends both on net-wide measures of connectivity and the role of a single component. Th
Externí odkaz:
http://arxiv.org/abs/2006.14622