Bo Li

Bo Li
Harbin Institute of Technology (Shenzhen)

Doctor of Philosophy

About

16
Publications
898
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
85
Citations
Citations since 2016
15 Research Items
85 Citations
201620172018201920202021202205101520
201620172018201920202021202205101520
201620172018201920202021202205101520
201620172018201920202021202205101520
Introduction

Publications

Publications (16)
Article
Full-text available
Mean field theory has been successfully used to analyze deep neural networks (DNN) in the infinite size limit. Given the finite size of realistic DNN, we utilize the large deviation theory and path integral analysis to study the deviation of functions represented by DNN from their typical mean field solutions. The parameter perturbations investigat...
Article
Full-text available
Balancing traffic flow by influencing drivers' route choices to alleviate congestion is becoming increasingly more appealing in urban traffic planning. Here, we introduce a discrete dynamical model comprising users who make their own routing choices on the basis of local information and those who consider routing advice based on localized inducemen...
Article
Full-text available
We study the space of functions computed by random-layered machines, including deep neural networks and Boolean circuits. Investigating the distribution of Boolean functions computed on the recurrent and layer-dependent architectures, we find that it is the same in both models. Depending on the initial conditions and computing elements used, we cha...
Article
Full-text available
Infectious diseases that incorporate presymptomatic transmission are challenging to monitor, model, predict, and contain. We address this scenario by studying a variant of a stochastic susceptible-exposed-infected-recovered model on arbitrary network instances using an analytical framework based on the method of dynamic message passing. This framew...
Preprint
Full-text available
Optimizing embedded systems, where the optimization of one depends on the state of another, is a formidable computational and algorithmic challenge, that is ubiquitous in real-world systems. We study flow networks, where bilevel optimization is relevant to traffic planning, network control and design, and where flows are governed by an optimization...
Article
Optimizing embedded systems, where the optimization of one depends on the state of another, is a formidable computational and algorithmic challenge, that is ubiquitous in real world systems. We study flow networks, where bilevel optimization is relevant to traffic planning, network control, and design, and where flows are governed by an optimizatio...
Preprint
Full-text available
The multi-armed bandit (MAB) model is one of the most classical models to study decision-making in an uncertain environment. In this model, a player needs to choose one of K possible arms of a bandit machine to play at each time step, where the corresponding arm returns a random reward to the player, potentially from a specific unknown distribution...
Preprint
Infectious diseases that incorporate pre-symptomatic transmission are challenging to monitor, model, predict and contain. We address this scenario by studying a variant of stochastic susceptible-exposed-infected-recovered (SEIR) model on arbitrary network instances using an analytical framework based on the method of dynamic message-passing. This f...
Preprint
Full-text available
We study the space of Boolean functions computed by random layered machines, including deep neural networks, and Boolean circuits. Investigating recurrent and layered feed-forward architectures, we find that the spaces of functions realized by both architectures are the same. We show that, depending on the initial conditions and computing elements...
Preprint
Balancing traffic flow by influencing drivers' route choices to alleviate congestion is becoming increasingly more appealing in urban traffic planning. Here, we introduce a discrete dynamical model comprising users who make their own routing choices on the basis of local information and those who consider routing advice based on localized inducemen...
Preprint
Mean field theory has been successfully used to analyze deep neural networks (DNN) in the infinite size limit. Given the finite size of realistic DNN, we utilize the large deviation theory and path integral analysis to study the deviation of functions represented by DNN from their typical mean field solutions. The parameter perturbations investigat...
Chapter
Full-text available
Synchronization is crucial for different natural or artificial systems. In power grids, synchronization in the system is essential for stable electricity transmission. However, fluctuations in power supply and demand can destabilize synchronization, especially with the increasing deployment of renewable sources. In real-time applications, one can o...
Article
Full-text available
The function space of deep-learning machines is investigated by studying growth in the entropy of functions of a given error with respect to a reference function, realized by a deep-learning machine. Using physics-inspired methods we study both sparsely and densely-connected architectures to discover a layer-wise convergence of candidate functions,...
Article
Chimera states are manifested through the coexistence of synchronous and asynchronous dynamics and have been observed in various systems. To analyze the role of network topology in giving rise to chimera states we study a heterogeneous network model comprising two group of nodes, of high and low degrees of connectivity. The architecture facilitates...
Article
Maintaining the stability of synchronization state is crucial for the functioning of many natural and artificial systems. In this study, we develop methods to optimize the synchronization stability of the Kuramoto model by minimizing the dominant Lyapunov exponent. With the help of the recently proposed cut-set space approximation of the steady sta...
Article
Full-text available
A comprehensive coverage is crucial for communication, supply and transportation networks, yet it is limited by the requirement of extensive infrastructure and heavy energy consumption. Here we draw an analogy between spins in antiferromagnet and outlets in supply networks, and apply techniques from the studies of disordered systems to elucidate th...

Network

Cited By

Projects

Projects (3)
Project
Using tools from non-equilibrium statistical mechanics to study dynamics of information processing systems.
Project
This project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No. 835913. It aims to develop theoretical methods to better understand spreading processes, contribute to the combat of COVID-19 and apply the developed techniques to neighbouring disciplines in complex systems.