High dimensional black-box optimization has broad applications but remains a challenging problem to solve.

Machine learning and Bayesian optimization (BO) algorithms can significantly accelerate the optimization of chemical reactions. Transfer learning can bolster the effectiveness of BO algorithms in low-data regimes by leveraging pre-existing chemical information or data outside the direct optimization task (i.e., source data). Large language models (LLMs) have demonstrated that chemical information present in foundation training data can give them utility for processing chemical data. Furthermore, they can be augmented with and help synthesize potentially multiple modalities of source chemical data germane to the optimization task. In this work, we examine how chemical information from LLMs can be elicited and used for transfer learning to accelerate the BO of reaction conditions to maximize yield. Specifically, we show that a survey-like prompting scheme and preference learning can be used to infer a utility function which models prior chemical information embedded in LLMs over a chemical parameter space; we find that the utility function shows modest correlation to true experimental measurements (yield) over the parameter space despite operating in a zero-shot setting. Furthermore, we show that the utility function can be leveraged to focus BO efforts in promising regions of the parameter space, improving the yield of the initial BO query and enhancing optimization in 4 of the 6 datasets studied. Overall, we view this work as a step towards bridging the gap between the chemistry knowledge embedded in LLMs and the capabilities of principled BO methods to accelerate reaction optimization.

Sequential optimization methods are often confronted with the curse of dimensionality in high-dimensional spaces. Current approaches under the Gaussian process framework are still burdened by the computational complexity of tracking Gaussian process posteriors and need to partition the optimization problem into small regions to ensure exploration or assume an underlying low-dimensional structure. With the idea of transiting the candidate points towards more promising positions, we propose a new method based on Markov Chain Monte Carlo to efficiently sample from an approximated posterior. We provide theoretical guarantees of its convergence in the Gaussian process Thompson sampling setting. We also show experimentally that both the Metropolis-Hastings and the Langevin Dynamics version of our algorithm outperform state-of-the-art methods in high-dimensional sequential optimization and reinforcement learning benchmarks.

Learning-based path planning is becoming a promising robot navigation methodology due to its adaptability to various environments. However, the expensive computing and storage associated with networks impose significant challenges for their deployment on low-cost robots. Motivated by this practical challenge, we develop a lightweight neural path planning architecture with a dual input network and a hybrid sampler for resource-constrained robotic systems. Our architecture is designed with efficient task feature extraction and fusion modules to translate the given planning instance into a guidance map. The hybrid sampler is then applied to restrict the planning within the prospective regions indicated by the guide map. To enable the network training, we further construct a publicly available dataset with various successful planning instances. Numerical simulations and physical experiments demonstrate that, compared with baseline approaches, our approach has nearly an order of magnitude fewer model size and five times lower computational while achieving promising performance. Besides, our approach can also accelerate the planning convergence process with fewer planning iterations compared to sample-based methods.

Sampling-based path planning algorithms play an important role in autonomous robotics. However, a common problem among the RRT-based algorithms is that the initial path generated is not optimal and the convergence is too slow to be used in real-world applications. In this paper, we propose a novel image-based learning algorithm (CBAGAN-RRT) using a Convolutional Block Attention Generative Adversarial Network with a combination of spatial and channel attention and a novel loss function to design the heuristics, find a better optimal path, and improve the convergence of the algorithm both concerning time and speed. The probability distribution of the paths generated from our GAN model is used to guide the sampling process for the RRT algorithm. We train and test our network on the dataset generated by \cite{zhang2021generative} and demonstrate that our algorithm outperforms the previous state-of-the-art algorithms using both the image quality generation metrics like IOU Score, Dice Score, FID score, and path planning metrics like time cost and the number of nodes. We conduct detailed experiments and ablation studies to illustrate the feasibility of our study and show that our model performs well not only on the training dataset but also on the unseen test dataset. The advantage of our approach is that we can avoid the complicated preprocessing in the state space, our model can be generalized to complicated environments like those containing turns and narrow passages without loss of accuracy, and our model can be easily integrated with other sampling-based path planning algorithms.

Multi-scale features have been proven highly effective for object detection but often come with huge and even prohibitive extra computation costs, especially for the recent Transformer-based detectors. In this paper, we propose Iterative Multi-scale Feature Aggregation (IMFA) -- a generic paradigm that enables efficient use of multi-scale features in Transformer-based object detectors. The core idea is to exploit sparse multi-scale features from just a few crucial locations, and it is achieved with two novel designs. First, IMFA rearranges the Transformer encoder-decoder pipeline so that the encoded features can be iteratively updated based on the detection predictions. Second, IMFA sparsely samples scale-adaptive features for refined detection from just a few keypoint locations under the guidance of prior detection predictions. As a result, the sampled multi-scale features are sparse yet still highly beneficial for object detection. Extensive experiments show that the proposed IMFA boosts the performance of multiple Transformer-based object detectors significantly yet with only slight computational overhead.

Vectorial Genetic Programming (Vec-GP) extends GP by allowing vectors as input features along regular, scalar features, using them by applying arithmetic operations component-wise or aggregating vectors into scalars by some aggregation function. Vec-GP also allows aggregating vectors only over a limited segment of the vector instead of the whole vector, which offers great potential but also introduces new parameters that GP has to optimize. This paper formalizes an optimization problem to analyze different strategies for optimizing a window for aggregation functions. Different strategies are presented, included random and guided sampling, where the latter leverages information from an approximated gradient. Those strategies can be applied as a simple optimization algorithm, which itself ca be applied inside a specialized mutation operator within GP. The presented results indicate, that the different random sampling strategies do not impact the overall algorithm performance significantly, and that the guided strategies suffer from becoming stuck in local optima. However, results also indicate, that there is still potential in discovering more efficient algorithms that could outperform the presented strategies.

Sampling-based path planning algorithms usually implement uniform sampling methods to search the state space. However, uniform sampling may lead to unnecessary exploration in many scenarios, such as the environment with a few dead ends. Our previous work proposes to use the promising region to guide the sampling process to address the issue. However, the predicted promising regions are often disconnected, which means they cannot connect the start and goal state, resulting in a lack of probabilistic completeness. This work focuses on enhancing the connectivity of predicted promising regions. Our proposed method regresses the connectivity probability of the edges in the x and y directions. In addition, it calculates the weight of the promising edges in loss to guide the neural network to pay more attention to the connectivity of the promising regions. We conduct a series of simulation experiments, and the results show that the connectivity of promising regions improves significantly. Furthermore, we analyze the effect of connectivity on sampling-based path planning algorithms and conclude that connectivity plays an essential role in maintaining algorithm performance.

In contrast to single-objective optimization (SOO), multi-objective optimization (MOO) requires an optimizer to find the Pareto frontier, a subset of feasible solutions that are not dominated by other feasible solutions. In this paper, we propose LaMOO, a novel multi-objective optimizer that learns a model from observed samples to partition the search space and then focus on promising regions that are likely to contain a subset of the Pareto frontier. The partitioning is based on the dominance number, which measures "how close" a data point is to the Pareto frontier among existing samples. To account for possible partition errors due to limited samples and model mismatch, we leverage Monte Carlo Tree Search (MCTS) to exploit promising regions while exploring suboptimal regions that may turn out to contain good solutions later. Theoretically, we prove the efficacy of learning space partitioning via LaMOO under certain assumptions. Empirically, on the HyperVolume (HV) benchmark, a popular MOO metric, LaMOO substantially outperforms strong baselines on multiple real-world MOO tasks, by up to 225% in sample efficiency for neural architecture search on Nasbench201, and up to 10% for molecular design. Multi-objective optimization (MOO) has been extensively used in many practical scenarios involving trade-offs between multiple objectives. For example, in automobile design (Chang, 2015), we must maximize the performance of the engine while simultaneously minimizing emissions and fuel consumption.

This document describes the generalized moving peaks benchmark (GMPB) and how it can be used to generate problem instances for continuous large-scale dynamic optimization problems. It presents a set of 15 benchmark problems, the relevant source code, and a performance indicator, designed for comparative studies and competitions in large-scale dynamic optimization. Although its primary purpose is to provide a coherent basis for running competitions, its generality allows the interested reader to use this document as a guide to design customized problem instances to investigate issues beyond the scope of the presented benchmark suite. To this end, we explain the modular structure of the GMPB and how its constituents can be assembled to form problem instances with a variety of controllable characteristics ranging from unimodal to highly multimodal, symmetric to highly asymmetric, smooth to highly irregular, and various degrees of variable interaction and ill-conditioning.