Modeling of real-world biological multi-agents is a fundamental problem ...
We propose a neural network-based model for nonlinear dynamics in contin...
We propose a data-driven method for controlling the frequency and conver...
Weight-tied models have attracted attention in the modern development of...
Evaluation of intervention in a multi-agent system, e.g., when humans sh...
Offline reinforcement learning leverages large datasets to train policie...
Extracting the interaction rules of biological agents from moving sequen...
Most modern reinforcement learning algorithms optimize a cumulative
sing...
In this work we discuss the incorporation of quadratic neurons into poli...
Extracting coherent patterns is one of the standard approaches towards
u...
Koopman spectral analysis has attracted attention for nonlinear dynamica...
Kernel methods have been among the most popular techniques in machine
le...
Koopman spectral analysis has attracted attention for understanding nonl...
Kernel mean embedding (KME) is a powerful tool to analyze probability
me...
Extracting the rules of real-world biological multi-agent behaviors is a...
Stable invariant sets are an essential notion in the analysis and applic...
Anomaly localization is an essential problem as anomaly detection is. Be...
Kernel methods have been among the most popular techniques in machine
le...
Operator-theoretic analysis of nonlinear dynamical systems has attracted...
The development of a metric on structural data-generating mechanisms is
...
Understanding complex network dynamics is a fundamental issue in various...
When approaching to problems in computer science, we often encounter
sit...
Generative modeling is a fundamental problem in machine learning with ma...
The submodular function maximization is an attractive optimization model...
Understanding nonlinear dynamical systems (NLDSs) is challenging in a va...
The development of a metric for structural data is a long-term problem i...
Spectral decomposition of the Koopman operator is attracting attention a...
Structural equation models and Bayesian networks have been widely used t...
Discovering causal relations among observed variables in a given data se...
A number of discrete and continuous optimization problems in machine lea...
As an increasing number of genome-wide association studies reveal the
li...
Discovering causal relations among observed variables in a given data se...
Structural equation models and Bayesian networks have been widely used t...