With the rapid upsurge of deep learning tasks at the network edge, effective edge artificial intelligence (AI) inference becomes critical to provide low-latency intelligent services for mobile users via leveraging the edge computing capability. In such scenarios, energy efficiency becomes a primary concern. In this paper, we present a joint inference task selection and downlink beamforming strategy to achieve energy-efficient edge AI inference through minimizing the overall power consumption consisting of both computation and transmission power consumption, yielding a mixed combinatorial optimization problem. By exploiting the inherent connections between the set of task selection and group sparsity structural transmit beamforming vector, we reformulate the optimization as a group sparse beamforming problem. To solve this challenging problem, we propose a log-sum function based three-stage approach. By adopting the log-sum function to enhance the group sparsity, a proximal iteratively reweighted algorithm is developed. Furthermore, we establish the global convergence analysis and provide the ergodic worst-case convergence rate for this algorithm. Simulation results will demonstrate the effectiveness of the proposed approach for improving energy efficiency in edge AI inference systems.

To operate effectively in the real world, artificial agents must act from raw sensory input such as images and achieve diverse goals across long time-horizons. On the one hand, recent strides in deep reinforcement and imitation learning have demonstrated impressive ability to learn goal-conditioned policies from high-dimensional image input, though only for short-horizon tasks. On the other hand, classical graphical methods like A* search are able to solve long-horizon tasks, but assume that the graph structure is abstracted away from raw sensory input and can only be constructed with task-specific priors. We wish to combine the strengths of deep learning and classical planning to solve long-horizon tasks from raw sensory input. To this end, we introduce Sparse Graphical Memory (SGM), a new data structure that stores observations and feasible transitions in a sparse memory. SGM can be combined with goal-conditioned RL or imitative agents to solve long-horizon tasks across a diverse set of domains. We show that SGM significantly outperforms current state of the art methods on long-horizon, sparse-reward visual navigation tasks. Project video and code are available at https://mishalaskin.github.io/sgm/

The increasing scale of distributed learning problems necessitates the development of compression techniques for reducing the information exchange between compute nodes. The level of accuracy in existing compression techniques is typically chosen before training, meaning that they are unlikely to adapt well to the problems that they are solving without extensive hyper-parameter tuning. In this paper, we propose dynamic tuning rules that adapt to the communicated gradients at each iteration. In particular, our rules optimize the communication efficiency at each iteration by maximizing the improvement in the objective function that is achieved per communicated bit. Our theoretical results and experiments indicate that the automatic tuning strategies significantly increase communication efficiency on several state-of-the-art compression schemes.

Agile satellites with advanced attitude maneuvering capability are the new generation of Earth observation satellites (EOSs). The continuous improvement in satellite technology and decrease in launch cost have boosted the development of agile EOSs (AEOSs). To efficiently employ the increasing orbiting AEOSs, the AEOS scheduling problem (AEOSSP) aiming to maximize the entire observation profit while satisfying all complex operational constraints, has received much attention over the past 20 years. The objectives of this paper are thus to summarize current research on AEOSSP, identify main accomplishments and highlight potential future research directions. To this end, general definitions of AEOSSP with operational constraints are described initially, followed by its three typical variations including different definitions of observation profit, multi-objective function and autonomous model. A detailed literature review from 1997 up to 2019 is then presented in line with four different solution methods, i.e., exact method, heuristic, metaheuristic and machine learning. Finally, we discuss a number of topics worth pursuing in the future.

The problem of representative selection amounts to sampling few informative exemplars from large datasets. This paper presents MOSAIC, a novel representative selection approach from high-dimensional data that may exhibit non-linear structures. Resting upon a novel quadratic formulation, Our method advances a multi-criteria selection approach that maximizes the global representation power of the sampled subset, ensures diversity, and rejects disruptive information by effectively detecting outliers. Through theoretical analyses we characterize the obtained sketch and reveal that the sampled representatives maximize a well-defined notion of data coverage in a transformed space. In addition, we present a highly scalable randomized implementation of the proposed algorithm shown to bring about substantial speedups. MOSAIC's superiority in achieving the desired characteristics of a representative subset all at once while exhibiting remarkable robustness to various outlier types is demonstrated via extensive experiments conducted on both real and synthetic data with comparisons to state-of-the-art algorithms.

Due to the massive size of the neural network models and training datasets used in machine learning today, it is imperative to distribute stochastic gradient descent (SGD) by splitting up tasks such as gradient evaluation across multiple worker nodes. However, running distributed SGD can be prohibitively expensive because it may require specialized computing resources such as GPUs for extended periods of time. We propose cost-effective strategies to exploit volatile cloud instances that are cheaper than standard instances, but may be interrupted by higher priority workloads. To the best of our knowledge, this work is the first to quantify how variations in the number of active worker nodes (as a result of preemption) affects SGD convergence and the time to train the model. By understanding these trade-offs between preemption probability of the instances, accuracy, and training time, we are able to derive practical strategies for configuring distributed SGD jobs on volatile instances such as Amazon EC2 spot instances and other preemptible cloud instances. Experimental results show that our strategies achieve good training performance at substantially lower cost.

The Artificial Bee Colony (ABC) algorithm is an evolutionary optimization algorithm based on swarm intelligence and inspired by the honey bees' food search behavior. Since the ABC algorithm has been developed to achieve optimal solutions by searching in the continuous search space, modification is required to apply this method to binary optimization problems. In this paper, we improve the ABC algorithm to solve binary optimization problems and call it the improved binary Artificial Bee Colony (ibinABC). The proposed method consists of an update mechanism based on fitness values and processing different number of decision variables. Thus, we aim to prevent the ABC algorithm from getting stuck in a local minimum by increasing its exploration ability. We compare the ibinABC algorithm with three variants of the ABC and other meta-heuristic algorithms in the literature. For comparison, we use the wellknown OR-Library dataset containing 15 problem instances prepared for the uncapacitated facility location problem. Computational results show that the proposed method is superior to other methods in terms of convergence speed and robustness. The source code of the algorithm will be available on GitHub after reviewing process

Non-polynomial hard (NP-hard) problems are challenging because no polynomial-time algorithm has yet been discovered to solve them in polynomial time. The Bacteria Foraging Optimization (BFO) algorithm is one of the metaheuristics algorithms that is mostly used for NP-hard problems. BFO is inspired by the behavior of the bacteria foraging such as Escherichia coli (E-coli). The aim of BFO is to eliminate those bacteria that have weak foraging properties and maintain those bacteria that have breakthrough foraging properties toward the optimum. Despite the strength of this algorithm, most of the problems reaching optimal solutions are time-demanding or impossible. In this paper, we modified single objective BFO by adding a mutation operator and multi-objective BFO (MOBFO) by adding mutation and crossover from genetic algorithm operators to update the solutions in each generation, and local tabu search algorithm to reach the local optimum solution. Additionally, we used a fast nondominated sort algorithm in MOBFO to find the best-nondominated solutions in each generation. We evaluated the performance of the proposed algorithms through a number of single and multi-objective Quadratic Assignment Problem (QAP) instances. The experimental results show that our approaches outperform some previous optimization algorithms in both convergent and divergent solutions.

In the optimization of dynamic systems, the variables typically have constraints. Such problems can be modeled as a constrained Markov Decision Process (MDP). This paper considers a model-free approach to the problem, where the transition probabilities are not known. In the presence of peak constraints, the agent has to choose the policy to maximize the long-term average reward as well as satisfy the constraints at each time. We propose modifications to the standard Q-learning problem for unconstrained optimization to come up with an algorithm with peak constraints. The proposed algorithm is shown to achieve $O(T^{1/2+\gamma})$ regret bound for the obtained reward, and $O(T^{1-\gamma})$ regret bound for the constraint violation for any $\gamma \in(0,1/2)$ and time-horizon $T$. We note that these are the first results on regret analysis for constrained MDP, where the transition problems are not known apriori. We demonstrate the proposed algorithm on an energy harvesting problem where it outperforms state-of-the-art and performs close to the theoretical upper bound of the studied optimization problem.

A framework based on iterative coordinate minimization (CM) is developed for stochastic convex optimization. Given that exact coordinate minimization is impossible due to the unknown stochastic nature of the objective function, the crux of the proposed optimization algorithm is an optimal control of the minimization precision in each iteration. We establish the optimal precision control and the resulting order-optimal regret performance for strongly convex and separably nonsmooth functions. An interesting finding is that the optimal progression of precision across iterations is independent of the low-dimensional CM routine employed, suggesting a general framework for extending low-dimensional optimization routines to high-dimensional problems. The proposed algorithm is amenable to online implementation and inherits the scalability and parallelizability properties of CM for large-scale optimization. Requiring only a sublinear order of message exchanges, it also lends itself well to distributed computing as compared with the alternative approach of coordinate gradient descent.