Deep model compression has been extensively studied, and state-of-the-art methods can now achieve high compression ratios with minimal accuracy loss. Previous literature suggested that the goals of robustness and compactness might sometimes contradict. We propose a novel Adversarially Trained Model Compression (ATMC) framework. ATMC constructs a unified constrained optimization formulation, where existing compression means (pruning, factorization, quantization) are all integrated into the constraints. An efficient algorithm is then developed.

Proximal policy optimization (PPO) is one of the most popular deep reinforcement learning (RL) methods, achieving state-of-the-art performance across a wide range of challenging tasks. However, as a model-free RL method, the success of PPO relies heavily on the effectiveness of its exploratory policy search. In this paper, we give an in-depth analysis on the exploration behavior of PPO, and show that PPO is prone to suffer from the risk of lack of exploration especially under the case of bad initialization, which may lead to the failure of training or being trapped in bad local optima. To address these issues, we proposed a novel policy optimization method, named Trust Region-Guided PPO (TRGPPO), which adaptively adjusts the clipping range within the trust region. We formally show that this method not only improves the exploration ability within the trust region but enjoys a better performance bound compared to the original PPO as well.

We study the effect of the stochastic gradient noise on the training of generative adversarial networks (GANs) and show that it can prevent the convergence of standard game optimization methods, while the batch version converges. We address this issue with a novel stochastic variance-reduced extragradient (SVRE) optimization algorithm, which for a large class of games improves upon the previous convergence rates proposed in the literature. We observe empirically that SVRE performs similarly to a batch method on MNIST while being computationally cheaper, and that SVRE yields more stable GAN training on standard datasets. Papers published at the Neural Information Processing Systems Conference.

Motivated by the change in mobility patterns, we present a new modeling approach for the vehicle-sharing problem. We aim at assigning vehicles to user-trips so as to maximize savings compared to other modes of transport. We base our formulations on the minimum-cost and the multi-commodity flow problem. These formulations make the problem applicable in daily operations. In the analysis we discuss an optimal composition of a shared fleet, restricted sets of modes of transport, and variations of the objective function.

In real life, providing security for a set of large areas by covering the area with Unmanned Aerial Vehicles (UAVs) is a difficult problem that consist of multiple objectives. These difficulties are even greater if the area coverage must continue throughout a specific time window. We address this by considering a Vehicle Routing Problem with Time Windows (VRPTW) variation in which capacity of agents is one and each customer (target area) must be supplied with more than one vehicles simultaneously without violating time windows. In this problem, our aim is to find a way to cover all areas with the necessary number of UAVs during the time windows, minimize the total distance traveled, and provide a fast solution by satisfying the additional constraint that each agent has limited fuel. We present a novel algorithm that relies on clustering the target areas according to their time windows, and then incrementally generating transportation problems with each cluster and the ready UAVs. Then we solve transportation problems with the simplex algorithm to generate the solution. The performance of the proposed algorithm and other implemented algorithms to compare the solution quality is evaluated on example scenarios with practical problem sizes.

This paper presents unifying results for subspace identification (SID) and dynamic mode decomposition (DMD) for autonomous dynamical systems. We observe that SID seeks to solve an optimization problem to estimate an extended observability matrix and a state sequence that minimizes the prediction error for the state-space model. Moreover, we observe that DMD seeks to solve a rank-constrained matrix regression problem that minimizes the prediction error of an extended autoregressive model. We prove that existence conditions for perfect (error-free) state-space and low-rank extended autoregressive models are equivalent and that the SID and DMD optimization problems are equivalent. We exploit these results to propose a SID-DMD algorithm that delivers a provably optimal model and that is easy to implement. We demonstrate our developments using a case study that aims to build dynamical models directly from video data.

Crew pairing optimization (CPO) is critically important for any airline, since its crew operating costs are second-largest, next to the fuel-cost. CPO aims at generating a set of flight sequences (crew pairings) covering a flight-schedule, at minimum-cost, while satisfying several legality constraints. For large-scale complex flight networks, billion-plus legal pairings (variables) are possible, rendering their offline enumeration intractable and an exhaustive search for their minimum-cost full flight-coverage subset impractical. Even generating an initial feasible solution (IFS: a manageable set of legal pairings covering all flights), which could be subsequently optimized is a difficult (NP-complete) problem. Though, as part of a larger project the authors have developed a crew pairing optimizer (AirCROP), this paper dedicatedly focuses on IFS-generation through a novel heuristic based on divide-and-cover strategy and Integer Programming. For real-world large and complex flight network datasets (including over 3200 flights and 15 crew bases) provided by GE Aviation, the proposed heuristic shows upto a ten-fold speed improvement over another state-of-the-art approach. Unprecedentedly, this paper presents an empirical investigation of the impact of IFS-cost on the final (optimized) solution-cost, revealing that too low an IFS-cost does not necessarily imply faster convergence for AirCROP or even lower cost for the optimized solution.

While real-world decisions involve many competing objectives, algorithmic decisions are often evaluated with a single objective function. In this paper, we study algorithmic policies which explicitly trade off between a private objective (such as profit) and a public objective (such as social welfare). We analyze a natural class of policies which trace an empirical Pareto frontier based on learned scores, and focus on how such decisions can be made in noisy or data-limited regimes. Our theoretical results characterize the optimal strategies in this class, bound the Pareto errors due to inaccuracies in the scores, and show an equivalence between optimal strategies and a rich class of fairness-constrained profit-maximizing policies. We then present empirical results in two different contexts --- online content recommendation and sustainable abalone fisheries --- to underscore the applicability of our approach to a wide range of practical decisions. Taken together, these results shed light on inherent trade-offs in using machine learning for decisions that impact social welfare.

Agile satellites are the new generation of Earth observation satellites (EOSs) with stronger attitude maneuvering capability. Since optical remote sensing instruments equipped on satellites cannot see through the cloud, the cloud coverage has a significant influence on the satellite observation missions. We are the first to address multiple agile EOSs scheduling problem under cloud coverage uncertainty where the objective aims to maximize the entire observation profit. The chance constraint programming model is adopted to describe the uncertainty initially, and the observation profit under cloud coverage uncertainty is then calculated via sample approximation method. Subsequently, an improved simulated annealing based heuristic combining a fast insertion strategy is proposed for large-scale observation missions. The experimental results show that the improved simulated annealing heuristic outperforms other algorithms for the multiple AEOSs scheduling problem under cloud coverage uncertainty, which verifies the efficiency and effectiveness of the proposed algorithm.

The multidimensional knapsack problem is a well-known constrained optimization problem with many real-world engineering applications. In order to solve this NPhard problem, a new modified Imperialist Competitive Algorithm with Constrained Assimilation (ICAwICA) is presented. The proposed algorithm introduces the concept of colony independence - a free will to choose between classical ICA assimilation to empire's imperialist or any other imperialist in the population. Furthermore, a constrained assimilation process has been implemented that combines classical ICA assimilation and revolution operators, while maintaining population diversity. This work investigates the performance of the proposed algorithm across 101 Multidimensional Knapsack Problem (MKP) benchmark instances. Experimental results show that the algorithm is able to obtain an optimal solution in all small instances and presents very competitive results for large MKP instances.