Identifying arbitrary topologies of power networks in real time is a computationally hard problem due to the number of hypotheses that grows exponentially with the network size. The potential of recovering the topology of a grid using only the publicly available data (e.g., market data) provides an effective approach to learning the topology of the grid based on the dynamically changing and up-to-date data. This enables learning and tracking the changes in the topology of the grid in a timely fashion. A major advantage of this method is that the labeled data used for training and inference is available in an arbitrarily large amount fast and at very little cost. As a result, the power of offline training is fully exploited to learn very complex classifiers for effective real-time topology identification.