With the advent of ubiquitous deployment of smart devices and the Internet of Things, data sources for machine learning inference have increasingly moved to the edge of the network. Existing machine learning inference platforms typically assume a homogeneous infrastructure and do not take into account the more complex and tiered computing infrastructure that includes edge devices, local hubs, edge datacenters, and cloud datacenters. On the other hand, recent AutoML efforts have provided viable solutions for model compression, pruning and quantization for heterogeneous environments; for a machine learning model, now we may easily find or even generate a series of models with different tradeoffs between accuracy and efficiency. We design and implement JellyBean, a system for serving and optimizing machine learning inference workflows on heterogeneous infrastructures. Given service-level objectives (e.g., throughput, accuracy), JellyBean picks the most cost-efficient models that meet the accuracy target and decides how to deploy them across different tiers of infrastructures. Evaluations show that JellyBean reduces the total serving cost of visual question answering by up to 58%, and vehicle tracking from the NVIDIA AI City Challenge by up to 36% compared with state-of-the-art model selection and worker assignment solutions. JellyBean also outperforms prior ML serving systems (e.g., Spark on the cloud) up to 5x in serving costs.

We demonstrate how Monte Carlo Search (MCS) algorithms, namely Nested Monte Carlo Search (NMCS) and Nested Rollout Policy Adaptation (NRPA), can be used to build graphs and find counter-examples to spectral graph theory conjectures in minutes.

Robot manipulation in cluttered environments often requires complex and sequential rearrangement of multiple objects in order to achieve the desired reconfiguration of the target objects. Due to the sophisticated physical interactions involved in such scenarios, rearrangement-based manipulation is still limited to a small range of tasks and is especially vulnerable to physical uncertainties and perception noise. This paper presents a planning framework that leverages the efficiency of sampling-based planning approaches, and closes the manipulation loop by dynamically controlling the planning horizon. Our approach interleaves planning and execution to progressively approach the manipulation goal while correcting any errors or path deviations along the process. Meanwhile, our framework allows the definition of manipulation goals without requiring explicit goal configurations, enabling the robot to flexibly interact with all objects to facilitate the manipulation of the target ones. With extensive experiments both in simulation and on a real robot, we evaluate our framework on three manipulation tasks in cluttered environments: grasping, relocating, and sorting. In comparison with two baseline approaches, we show that our framework can significantly improve planning efficiency, robustness against physical uncertainties, and task success rate under limited time budgets.

We introduce a robotic assembly system that streamlines the design-to-make workflow for going from a CAD model of a product assembly to a fully programmed and adaptive assembly process. Our system captures (in the CAD tool) the intent of the assembly process for a specific robotic workcell and generates a recipe of task-level instructions. By integrating visual sensing with deep-learned perception models, the robots infer the necessary actions to assemble the design from the generated recipe. The perception models are trained directly from simulation, allowing the system to identify various parts based on CAD information. We demonstrate the system with a workcell of two robots to assemble interlocking 3D part designs. We first build and tune the assembly process in simulation, verifying the generated recipe. Finally, the real robotic workcell assembles the design using the same behavior.

The efficient, automated search for well-performing neural architectures (NAS) has drawn increasing attention in the recent past. Thereby, the predominant research objective is to reduce the necessity of costly evaluations of neural architectures while efficiently exploring large search spaces. To this aim, surrogate models embed architectures in a latent space and predict their performance, while generative models for neural architectures enable optimization-based search within the latent space the generator draws from. Both, surrogate and generative models, have the aim of facilitating query-efficient search in a well-structured latent space. In this paper, we further improve the trade-off between query-efficiency and promising architecture generation by leveraging advantages from both, efficient surrogate models and generative design. To this end, we propose a generative model, paired with a surrogate predictor, that iteratively learns to generate samples from increasingly promising latent subspaces. This approach leads to very effective and efficient architecture search, while keeping the query amount low. In addition, our approach allows in a straightforward manner to jointly optimize for multiple objectives such as accuracy and hardware latency. We show the benefit of this approach not only w.r.t. the optimization of architectures for highest classification accuracy but also in the context of hardware constraints and outperform state-of-the-art methods on several NAS benchmarks for single and multiple objectives. We also achieve state-of-the-art performance on ImageNet. The code is available at http://github.com/jovitalukasik/AG-Net .

We consider time-optimal motion planning for dynamical systems that are translation-invariant, a property that holds for many mobile robots, such as differential-drives, cars, airplanes, and multirotors. Our key insight is that we can extend graph-search algorithms to the continuous case when used symbiotically with optimization. For the graph search, we introduce discontinuity-bounded A* (db-A*), a generalization of the A* algorithm that uses concepts and data structures from sampling-based planners. Db-A* reuses short trajectories, so-called motion primitives, as edges and allows a maximum user-specified discontinuity at the vertices. These trajectories are locally repaired with trajectory optimization, which also provides new improved motion primitives. Our novel kinodynamic motion planner, kMP-db-A*, has almost surely asymptotic optimal behavior and computes near-optimal solutions quickly. For our empirical validation, we provide the first benchmark that compares search-, sampling-, and optimization-based time-optimal motion planning on multiple dynamical systems in different settings. Compared to the baselines, kMP-db-A* consistently solves more problem instances, finds lower-cost initial solutions, and converges more quickly.

This volume contains the Late-Breaking Abstracts accepted at Evo* 2022 Conference, held in Madrid (Spain), from 20 to 22 of April. They were also presented as short talks as well as at the conference's poster session. The works present ongoing research and preliminary results investigating on the application of different approaches of Evolutionary Computation and other Nature-Inspired techniques to different problems, most of them real world ones. These are very promising contributions, since they outline some of the incoming advances and applications in the area of nature-inspired methods, mainly Evolutionary Algorithms.

Diversity maximization is a fundamental problem with wide applications in data summarization, web search, and recommender systems. Given a set $X$ of $n$ elements, it asks to select a subset $S$ of $k \ll n$ elements with maximum \emph{diversity}, as quantified by the dissimilarities among the elements in $S$. In this paper, we focus on the diversity maximization problem with fairness constraints in the streaming setting. Specifically, we consider the max-min diversity objective, which selects a subset $S$ that maximizes the minimum distance (dissimilarity) between any pair of distinct elements within it. Assuming that the set $X$ is partitioned into $m$ disjoint groups by some sensitive attribute, e.g., sex or race, ensuring \emph{fairness} requires that the selected subset $S$ contains $k_i$ elements from each group $i \in [1,m]$. A streaming algorithm should process $X$ sequentially in one pass and return a subset with maximum \emph{diversity} while guaranteeing the fairness constraint. Although diversity maximization has been extensively studied, the only known algorithms that can work with the max-min diversity objective and fairness constraints are very inefficient for data streams. Since diversity maximization is NP-hard in general, we propose two approximation algorithms for fair diversity maximization in data streams, the first of which is $\frac{1-\varepsilon}{4}$-approximate and specific for $m=2$, where $\varepsilon \in (0,1)$, and the second of which achieves a $\frac{1-\varepsilon}{3m+2}$-approximation for an arbitrary $m$. Experimental results on real-world and synthetic datasets show that both algorithms provide solutions of comparable quality to the state-of-the-art algorithms while running several orders of magnitude faster in the streaming setting.

Since MIP linear problems include both continuous and integer variables, they are proved to belong to the NP-hard class (see [38] for a more detailed analysis), meaning that they are not solvable in polynomial time. The complete exploration of the integer feasible set, whose cardinality grows exponentially with the number of variables, is yet possible to achieve the optimal solution, but for most of the practically significant instances, it would require unacceptable computational effort. In fact, the only way to solve to optimality any mixed-integer problem is to apply some of the well-known Branch and Bound techniques. However, despite combinatorial optimization community provided a great deal of these algorithms, for which the reader should refer to [31, 34, 16], MIP problems complexity is inherent with their belonging to NP-hard class. Therefore, when tackling MIP problems, one either seeks particular structures allowing to bring down the complexity, such as the availability, for a given class of problems, of the optimal formulation or exploits cutting plane generation to dramatically reduce the feasible region dimension. However, we often encounter MIP problems without having any prior knowledge of possible structures and, thus, pursuing the globally optimal solution could be in practice impossible or inefficient, since for our purpose a sub-optimal approximation is considered to be good enough. This makes heuristics one of the most widespread and feasible ways to achieve sub-optimal solutions of MIP problems within an affordable computational time. For the purpose of highlighting the perspective of our research, we can define two classes of MIP heuristics: improvement heuristics and start heuristics.

Multi-agent path finding (MAPF) is an active area in artificial intelligence, which has many real-world applications such as warehouse management, traffic control, robotics, etc. Recently, M* and its variants have greatly improved the ability to solve the MAPF problem. Although subdimensional expansion used in those approaches significantly decreases the dimensionality of the joint search space and reduces the branching factor, they do not make full use of the possible non-uniqueness of the optimal path of each agent. As a result, the updating of the collision sets may bring a large number of redundant computation. In this paper, the idea of bypass is introduced into subdimensional expansion to reduce the redundant computation. Specifically, we propose the BPM* algorithm, which is an implementation of subdimensional expansion with bypass in M*. In the experiments, we show that BPM* outperforms the state-of-the-art in solving several MAPF benchmark problems.