Many science, engineering, and design optimization problems require balancing the trade-offs between several conflicting objectives. The objectives are often black-box functions whose evaluations are time-consuming and costly. Multi-objective Bayesian optimization can be used to automate the process of discovering the set of optimal solutions, called Pareto-optimal, while minimizing the number of performed evaluations. To further reduce the evaluation time in the optimization process, testing of several samples in parallel can be deployed. We propose a novel multi-objective Bayesian optimization algorithm that iteratively selects the best batch of samples to be evaluated in parallel. Our algorithm approximates and analyzes a piecewise-continuous Pareto set representation. This representation allows us to introduce a batch selection strategy that optimizes for both hypervolume improvement and diversity of selected samples in order to efficiently advance promising regions of the Pareto front. Experiments on both synthetic test functions and real-world benchmark problems show that our algorithm predominantly outperforms relevant state-of-the-art methods.

Agent-based modeling (ABM) is a principal approach for studying complex systems. By decomposing a system into simpler, interacting agents, agent-based modeling (ABM) allows researchers to observe the emergence of complex phenomena. High-performance array computing libraries like JAX can help scale such computational models to a large number of agents by using automatic vectorization and just-in-time (JIT) compilation. One of the caveats of using JAX to achieve such scaling is that the shapes of arrays used in the computational model should remain immutable throughout the simulation. In the context of agent-based modeling (ABM), this can pose constraints on certain agent manipulation operations that require flexible data structures. A subset of which is represented by the ability to update a dynamically selected number of agents by applying distinct changes to them during a simulation. To this effect, we introduce ABMax, an ABM framework based on JAX that implements multiple just-in-time (JIT) compilable algorithms to provide this functionality. On the canonical predation model benchmark, ABMax achieves runtime performance comparable to state-of-the-art implementations. Further, we show that this functionality can also be vectorized, making it possible to run many similar agent-based models in parallel. We also present two examples in the form of a traffic-flow model and a financial market model to show the use case of ABMax

It's not the first time AI has been used to join up the missing dots in Roman history. Dr Sommerschield developed Aeneas along with her co-research leader Dr Yannis Assael, an AI specialist at Google DeepMind. It automates the process of contextualising based on parallels, in the blink of an eye. Aeneas draws on a vast database of of 176,000 Roman inscriptions including images and uses a carefully designed AI system to pull up a range of relevant historical parallels, to support the work of historians, according to Dr Assael. "What the historian can't do is assess these parallels in a matter of seconds across tens of thousands of inscriptions, and that is where AI can come in as an assistant."

As the basis of generative AI, an autoregressive model requires the generation of a new token depending on all the previously generated tokens, which brings high quality but also restricts the model to generate tokens one by one, forming a bottleneck limiting the generation speed. In this paper, we propose a new decoder architecture that efficiently generates text in parallel for context-aware generation tasks. Our proposed pipelined decoder initiates the generation of multiple subsequences simultaneously, and, at each time-step, it generates a new token for each subsequence to realize parallelism. Experiments on multiple text generation tasks, including question answering, text summarization, and keyphrase generation, show that our pipelined decoder significantly improves the generation speed without a significant loss of generation quality or additional memory consumption.

Summary and Contributions: Update after author response: I would like to thank the authors for the detailed response. I am changing my score from 4 to 5 based on the reviewer discussion and the author response. Some more detailed thoughts follow. While I agree that the negative results here are quite interesting and a step towards slowing the trickle of overreaching conclusions, I am still unconvinced about the positive results. Essentially, a network trained for a simple task does well on the task, and fails to generalize in a robust manner.

Many science, engineering, and design optimization problems require balancing the trade-offs between several conflicting objectives. The objectives are often black-box functions whose evaluations are time-consuming and costly. Multi-objective Bayesian optimization can be used to automate the process of discovering the set of optimal solutions, called Pareto-optimal, while minimizing the number of performed evaluations. To further reduce the evaluation time in the optimization process, testing of several samples in parallel can be deployed. We propose a novel multi-objective Bayesian optimization algorithm that iteratively selects the best batch of samples to be evaluated in parallel.

We consider a large-scale multi-robot path planning problem in a cluttered environment. Our approach achieves real-time replanning by dividing the workspace into cells and utilizing a hierarchical planner. Specifically, we propose novel multi-commodity flow-based high-level planners that route robots through cells with reduced congestion, along with an anytime low-level planner that computes collision-free paths for robots within each cell in parallel. A highlight of our method is a significant improvement in computation time. Specifically, we show empirical results of a 500-times speedup in computation time compared to the baseline multi-agent pathfinding approach on the environments we study. We account for the robot's embodiment and support non-stop execution with continuous replanning. We demonstrate the real-time performance of our algorithm with up to 142 robots in simulation, and a representative 32 physical Crazyflie nano-quadrotor experiment.

Adjusting the control actions of a wheeled robot to eliminate oscillations and ensure smoother motion is critical in applications requiring accurate and soft movements. Fuzzy controllers enable a robot to operate smoothly while accounting for uncertainties in the system. This work uses fuzzy theories and parallel distributed compensation to establish a robust controller for wheeled mobile robots. The use of fuzzy logic type I and type II controllers are covered in the study, and their performance is compared with a PID controller. Experimental results demonstrate that fuzzy logic type II outperforms type I and the classic controller. Further, we deploy parallel distributed compensation, sector of nonlinearity, and local approximation strategy in our design. These strategies help analyze the stability of each rule of the fuzzy controller separately and map the if-then rules of the fuzzy box into parallel distributed compensation using Linear Matrix Inequalities (LMI) analysis. Also, they help manage the uncertainty flow in the equations that exist in the kinematic model of a robot. Last, we propose a Bezier curve to represent the different pathways for the wheeled mobile robot.

The authors propose a parallel algorithm for the DPMM that parallelizes a RJMCMC sampler that jumps between finite models. While the parallelization and the RJMCMC sampler are proposed together, I will separate them for the purpose of this review, in order to ask questions about each part separately. First, the RJMCMC algorithm (by which I mean, the algorithm we would have on a single cluster). Here, we use a reversible-jump MCMC algorithm to jump between finite-dimensional Dirichlet distributions. As an aside, since \bar{\pi}_{K 1} is not used in the mixture model (the mixture model is defined on the renormalized occupied K components), it would seem to make more sense to define a K-dimensional, rather than a K-1 - dimensional, Dirichlet distribution; this is valid under marginalization properties of the Dirichlet distribution, since equation 10 samples from a distribution proportional to \pi_1 ... \pi_K To jump between model dimensionalities, the authors propose a split/merge RJMCMC step that is reminiscent of that of Green and Richardson.

We are frequently called upon to perform multiple tasks that com(cid:173) pete for our attention and resource. Often we know the optimal solution to each task in isolation; in this paper, we describe how this knowledge can be exploited to efficiently find good solutions for doing the tasks in parallel. We formulate this problem as that of dynamically merging multiple Markov decision processes (MDPs) into a composite MDP, and present a new theoretically-sound dy(cid:173) namic programming algorithm for finding an optimal policy for the composite MDP. We analyze various aspects of our algorithm and illustrate its use on a simple merging problem. Every day, we are faced with the problem of doing mUltiple tasks in parallel, each of which competes for our attention and resource.