Optimizing Integrated Information with a Prior Guided Random Search Algorithm
Integrated information theory (IIT) is a theoretical framework that provides a quantitative measure to estimate when a physical system is conscious, its degree of consciousness, and the complexity of the qualia space that the system is experiencing. Formally, IIT rests on the assumption that if a surrogate physical system can fully embed the phenomenological properties of consciousness, then the system properties must be constrained by the properties of the qualia being experienced. Following this assumption, IIT represents the physical system as a network of interconnected elements that can be thought of as a probabilistic causal graph, $\mathcal{G}$, where each node has an input-output function and all the graph is encoded in a transition probability matrix. Consequently, IIT's quantitative measure of consciousness, $\Phi$, is computed with respect to the transition probability matrix and the present state of the graph. In this paper, we provide a random search algorithm that is able to optimize $\Phi$ in order to investigate, as the number of nodes increases, the structure of the graphs that have higher $\Phi$. We also provide arguments that show the difficulties of applying more complex black-box search algorithms, such as Bayesian optimization or metaheuristics, in this particular problem. Additionally, we suggest specific research lines for these techniques to enhance the search algorithm that guarantees maximal $\Phi$.
Code (0)
등록된 구현이 없습니다.
Tasks
Bayesian OptimizationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Query-Efficient Black-box Adversarial Attacks Guided by a Transfer-based Prior
Adversarial attacks have been extensively studied in recent years since they can identify the vulnerability of deep learning models before deployed. In this paper, we consider the black-box adversarial setting, where the…
Improving Black-box Adversarial Attacks with a Transfer-based Prior
We consider the black-box adversarial setting, where the adversary has to generate adversarial perturbations without access to the target models to compute gradients. Previous methods tried to approximate the gradient ei…
Prior-guided Bayesian Optimization
While Bayesian Optimization (BO) is a very popular method for optimizing expensive black-box functions, it fails to leverage the experience of domain experts. This causes BO to waste function evaluations on bad design ch…
Bayesian OptimizationOptimizing Data-driven Causal Discovery Using Knowledge-guided Search
Learning causal relationships solely from observational data often fails to reveal the underlying causal mechanisms due to the vast search space of possible causal graphs, which can grow exponentially, especially for gre…
Causal DiscoveryOn the Convergence of Prior-Guided Zeroth-Order Optimization Algorithms
Zeroth-order (ZO) optimization is widely used to handle challenging tasks, such as query-based black-box adversarial attacks and reinforcement learning. Various attempts have been made to integrate prior information into…