no code implementations • 24 May 2024 • Hancheng Min, René Vidal
The implicit bias of gradient-based training algorithms has been considered mostly beneficial as it leads to trained networks that often generalize well.
no code implementations • 26 Feb 2024 • Yan Jiang, Hancheng Min, Baosen Zhang
Frequency security assessment following major disturbances has long been one of the central tasks in power system operations.
no code implementations • 23 Jan 2024 • Agustin Castellano, Hancheng Min, Juan Andrés Bazerque, Enrique Mallada
To that end, we study the properties of the binary safety critic associated with a deterministic dynamical system that seeks to avoid reaching an unsafe region.
no code implementations • 24 Jul 2023 • Hancheng Min, Enrique Mallada, René Vidal
Our analysis shows that, during the early phase of training, neurons in the first layer try to align with either the positive data or the negative data, depending on its corresponding weight on the second layer.
no code implementations • 16 Feb 2023 • Hancheng Min, Richard Pates, Enrique Mallada
Network coherence generally refers to the emergence of simple aggregated dynamical behaviours, despite heterogeneity in the dynamics of the subsystems that constitute the network.
no code implementations • 28 Nov 2022 • Hancheng Min, Enrique Mallada
We propose a structure-preserving model-reduction methodology for large-scale dynamic networks with tightly-connected components.
no code implementations • 27 Sep 2022 • Hancheng Min, Enrique Mallada
We propose a novel model-reduction methodology for large-scale dynamic networks with tightly-connected components.
no code implementations • 9 Dec 2021 • Agustin Castellano, Hancheng Min, Juan Bazerque, Enrique Mallada
We argue that stationary policies are not sufficient for solving this problem, and that a rich class of policies can be found by endowing the controller with a scalar quantity, so called budget, that tracks how close the agent is to violating the constraint.
no code implementations • 18 May 2021 • Agustin Castellano, Hancheng Min, Juan Bazerque, Enrique Mallada
Our analysis further highlights a trade-off between the time lag for the underlying MDP necessary to detect unsafe actions, and the level of exposure to unsafe events.
no code implementations • 13 May 2021 • Hancheng Min, Salma Tarmoun, Rene Vidal, Enrique Mallada
Firstly, we show that the squared loss converges exponentially to its optimum at a rate that depends on the level of imbalance and the margin of the initialization.
no code implementations • 4 Jan 2021 • Hancheng Min, Richard Pates, Enrique Mallada
More precisely, for a networked system with linear dynamics and coupling, we show that, as the network connectivity grows, the system transfer matrix converges to a rank-one transfer matrix representing the coherent behavior.
no code implementations • 1 Jan 2021 • Hancheng Min, Salma Tarmoun, Rene Vidal, Enrique Mallada
In this paper, we present a novel analysis of overparametrized single-hidden layer linear networks, which formally connects initialization, optimization, and overparametrization with generalization performance.