90 citations · 514 across the 54 of their papers we have counts for
22 papers · 1 filter
Why AI Safety Requires Uncertainty, Incomplete Preferences, and Non-Archimedean Utilities
Alessio Benavoli, Alessandro Facchini, Marco Zaffalon
How can we ensure that AI systems are aligned with human values and remain safe? We can study this problem through the frameworks of the AI assistance and the AI shutdown games. Th…
Zero-shot Causal Graph Extrapolation from Text via LLMs
Alessandro Antonucci, Gregorio Piqué, Marco Zaffalon
We evaluate the ability of large language models (LLMs) to infer causal relations from natural language. Compared to traditional natural language processing and deep learning techn…
Tractable Bounding of Counterfactual Queries by Knowledge Compilation
David Huber, Yizuo Chen, Alessandro Antonucci +2
We discuss the problem of bounding partially identifiable queries, such as counterfactuals, in Pearlian structural causal models. A recently proposed iterated EM scheme yields an i…
Efficient Computation of Counterfactual Bounds
Marco Zaffalon, Alessandro Antonucci, Rafael Cabañas +2
We assume to be given structural equations over discrete variables inducing a directed acyclic graph, namely, a structural causal model, together with data about its internal nodes…
Learning to Bound Counterfactual Inference from Observational, Biased and Randomised Data
Marco Zaffalon, Alessandro Antonucci, David Huber +1
We address the problem of integrating data from multiple, possibly biased, observational and interventional studies, to eventually compute counterfactuals in structural causal mode…
Nonlinear desirability theory
Enrique Miranda, Marco Zaffalon
Desirability can be understood as an extension of Anscombe and Aumann's Bayesian decision theory to sets of expected utilities. At the core of desirability lies an assumption of li…
Information algebras of coherent sets of gambles in general possibility spaces
Juerg Kohlas, Arianna Casanova, Marco Zaffalon
In this paper, we show that coherent sets of gambles can be embedded into the algebraic structure of information algebra. This leads firstly, to a new perspective of the algebraic…
Information algebras in the theory of imprecise probabilities
Arianna Casanova, Juerg Kohlas, Marco Zaffalon
In this paper, we show that coherent sets of gambles and coherent lower and upper previsions can be embedded into the algebraic structure of information algebra. This leads firstly…
Causal Expectation-Maximisation
Marco Zaffalon, Alessandro Antonucci, Rafael Cabañas
Structural causal models are the basic modelling unit in Pearl's causal theory; in principle they allow us to solve counterfactuals, which are at the top rung of the ladder of caus…
Structural Causal Models Are (Solvable by) Credal Networks
Marco Zaffalon, Alessandro Antonucci, Rafael Cabañas
A structural causal model is made of endogenous (manifest) and exogenous (latent) variables. We show that endogenous observations induce linear constraints on the probabilities of…
Efficient Learning of Bounded-Treewidth Bayesian Networks from Complete and Incomplete Data Sets
Mauro Scanagatta, Giorgio Corani, Marco Zaffalon +2
Learning a Bayesian networks with bounded treewidth is important for reducing the complexity of the inferences. We present a novel anytime algorithm (k-MAX) method for this task, w…
Entropy-based Pruning for Learning Bayesian Networks using BIC
Cassio P. de Campos, Mauro Scanagatta, Giorgio Corani +1
For decomposable score-based structure learning of Bayesian networks, existing approaches first compute a collection of candidate parent sets for each variable and then optimize ov…
Learning Bounded Treewidth Bayesian Networks with Thousands of Variables
Mauro Scanagatta, Giorgio Corani, Cassio P. de Campos +1
We present a method for learning treewidth-bounded Bayesian networks from data sets containing thousands of variables. Bounding the treewidth of a Bayesian greatly reduces the comp…
Desirability and the birth of incomplete preferences
Marco Zaffalon, Enrique Miranda
We establish an equivalence between two seemingly different theories: one is the traditional axiomatisation of incomplete preferences on horse lotteries based on the mixture indepe…
Updating with incomplete observations
Gert de Cooman, Marco Zaffalon
Currently, there is renewed interest in the problem, raised by Shafer in 1985, of updating probabilities when observations are incomplete (or set-valued). This is a fundamental pro…
Robust Feature Selection by Mutual Information Distributions
Marco Zaffalon, Marcus Hutter
Mutual information is widely used in artificial intelligence, in a descriptive way, to measure the stochastic dependence of discrete random variables. In order to address questions…
Conservative Inference Rule for Uncertain Reasoning under Incompleteness
Marco Zaffalon, Enrique Miranda
In this paper we formulate the problem of inference under incomplete information in very general terms. This includes modelling the process responsible for the incompleteness, whic…
The Complexity of Approximately Solving Influence Diagrams
Denis D. Maua, Cassio Polpo de Campos, Marco Zaffalon
Influence diagrams allow for intuitive and yet precise description of complex situations involving decision making under uncertainty. Unfortunately, most of the problems described…
Solving Limited Memory Influence Diagrams
Denis Deratani Mauá, Cassio Polpo de Campos, Marco Zaffalon
We present a new algorithm for exactly solving decision making problems represented as influence diagrams. We do not require the usual assumptions of no forgetting and regularity;…
Epistemic irrelevance in credal nets: the case of imprecise Markov trees
Gert de Cooman, Filip Hermans, Alessandro Antonucci +1
We focus on credal nets, which are graphical models that generalise Bayesian nets to imprecise probability. We replace the notion of strong independence commonly used in credal net…
Updating beliefs with incomplete observations
Gert de Cooman, Marco Zaffalon
Currently, there is renewed interest in the problem, raised by Shafer in 1985, of updating probabilities when observations are incomplete. This is a fundamental problem in general,…
Robust Feature Selection by Mutual Information Distributions
Marco Zaffalon, Marcus Hutter
Mutual information is widely used in artificial intelligence, in a descriptive way, to measure the stochastic dependence of discrete random variables. In order to address questions…