25 March 2019 in IEEE Transactions on Automatic Control
This paper proposes TriPD, a new primal-dual algorithm for minimizing the sum of a Lipschitz-differentiable convex function and two possibly nonsmooth convex functions, one of which is composed with a linear mapping. We devise a randomized block-coordinate version of the algorithm which converges under the same stepsize conditions as the full algorithm. It is shown that both the original as well as the block-coordinate scheme feature linear convergence rate when the functions involved are either piecewise linear-quadratic, or when they satisfy a certain quadratic growth condition (which is weaker than strong convexity). Moreover, we apply the developed algorithms to the problem of multi-agent optimization on a graph, thus obtaining novel synchronous and asynchronous distributed methods. The proposed algorithms are fully distributed in the sense that the updates and the stepsizes of each agent only depend on local information. In fact, no prior global coordination is required. Finally, we showcase an application of our algorithm in distributed formation control.
6 December 2024 in Device
22 December 2020 in IEEE Transactions on Neural Networks and Learning Systems
In this article, we study a multiplayer Stackelberg-Nash game (SNG) pertaining to a nonlinear dynamical system, including one leader and multiple followers. At the higher level, the leader makes its decision preferentially with consideration of the reaction functions of all followers, while, at the lower level, each of the followers reacts optimally to the leader's strategy simultaneously by playing a Nash game. First, the optimal strategies for the leader and the followers are derived from down to the top, and these strategies are further shown to constitute the Stackelberg-Nash equilibrium points. Subsequently, to overcome the difficulty in calculating the equilibrium points analytically, we develop a novel two-level value iteration-based integral reinforcement learning (VI-IRL) algorithm that relies only upon partial information of system dynamics. We establish that the proposed method converges asymptotically to the equilibrium strategies under the weak coupling conditions. Moreover, we introduce effective termination criteria to guarantee the admissibility of the policy (strategy) profile obtained from a finite number of iterations of the proposed algorithm. In the implementation of our scheme, we employ neural networks (NNs) to approximate the value functions and invoke the least-squares methods to update the involved weights. Finally, the effectiveness of the developed algorithm is verified by two simulation examples.
20 March 2020 in IEEE Transactions on Power Systems
This paper proposes a data-driven algorithm for locating the source of forced oscillations and suggests a physical interpretation for the method. By leveraging the sparsity of forced oscillations along with the low-rank nature of synchrophasor data, the problem of source localization under resonance conditions is cast as computing the sparse and low-rank components using Robust Principal Component Analysis (RPCA), which can be efficiently solved by the exact Augmented Lagrange Multiplier method. Based on this problem formulation, an efficient and practically implementable algorithm is proposed to pinpoint the forced oscillation source during real-time operation. Furthermore, theoretical insights are provided for the efficacy of the proposed approach, by use of physical model-based analysis, specifically by highlighting the low-rank nature of the resonance component matrix. Without the availability of system topology information, the proposed method can achieve high localization accuracy in synthetic cases based on benchmark systems and real-world forced oscillations in the power grid of Texas.
8 March 2023 in IEEE Transactions on Neural Networks and Learning Systems
Filter pruning is advocated for accelerating deep neural networks without dedicated hardware or libraries, while maintaining high prediction accuracy. Several works have cast pruning as a variant of $\ell_1$ -regularized training, which entails two challenges: 1) the $\ell_1$ -norm is not scaling-invariant (i.e., the regularization penalty depends on weight values) and 2) there is no rule for selecting the penalty coefficient to trade off high pruning ratio for low accuracy drop. To address these issues, we propose a lightweight pruning method termed adaptive sensitivity-based pruning (ASTER) which: 1) achieves scaling-invariance by refraining from modifying unpruned filter weights and 2) dynamically adjusts the pruning threshold concurrently with the training process. ASTER computes the sensitivity of the loss to the threshold on the fly (without retraining); this is carried efficiently by an application of L-BFGS solely on the batch normalization (BN) layers. It then proceeds to adapt the threshold so as to maintain a fine balance between pruning ratio and model capacity. We have conducted extensive experiments on a number of state-of-the-art CNN models on benchmark datasets to illustrate the merits of our approach in terms of both FLOPs reduction and accuracy. For example, on ILSVRC-2012 our method reduces more than 76% FLOPs for ResNet-50 with only 2.0% Top-1 accuracy degradation, while for the MobileNet v2 model it achieves 46.6% FLOPs Drop with a Top-1 Acc. Drop of only 2.77%. Even for a very lightweight classification model like MobileNet v3-small, ASTER saves 16.1% FLOPs with a negligible Top-1 accuracy drop of 0.03%.