Forecasting and optimisation are two major fields of operations research that are widely used in practice. These methods have contributed to each other growth in several ways. However, the nature of the relationship between these two fields and integrating them have not been explored or understood enough. We advocate the integration of these two fields and explore several problems that require both forecasting and optimisation to deal with the uncertainties. We further investigate some of the methodologies that lie at the intersection of machine learning with prediction and optimisation to address real-world problems. Finally, we provide several research directions for those interested to work in this domain.

Multi-Task Learning (MTL) is a powerful learning paradigm to improve generalization performance via knowledge sharing. However, existing studies find that MTL could sometimes hurt generalization, especially when two tasks are less correlated. One possible reason that hurts generalization is spurious correlation, i.e., some knowledge is spurious and not causally related to task labels, but the model could mistakenly utilize them and thus fail when such correlation changes. In MTL setup, there exist several unique challenges of spurious correlation. First, the risk of having non-causal knowledge is higher, as the shared MTL model needs to encode all knowledge from different tasks, and causal knowledge for one task could be potentially spurious to the other. Second, the confounder between task labels brings in a different type of spurious correlation to MTL. We theoretically prove that MTL is more prone to taking non-causal knowledge from other tasks than single-task learning, and thus generalize worse. To solve this problem, we propose Multi-Task Causal Representation Learning framework, aiming to represent multi-task knowledge via disentangled neural modules, and learn which module is causally related to each task via MTL-specific invariant regularization. Experiments show that it could enhance MTL model's performance by 5.5% on average over Multi-MNIST, MovieLens, Taskonomy, CityScape, and NYUv2, via alleviating spurious correlation problem.

In this work, we propose an Automated Machine Learning (AutoML) system to search for models not only with good prediction accuracy but also fair. We first investigate the necessity and impact of unfairness mitigation in the AutoML context. We establish the FairAutoML framework. The framework provides a novel design based on pragmatic abstractions, which makes it convenient to incorporate existing fairness definitions, unfairness mitigation techniques, and hyperparameter search methods into the model search and evaluation process. Following this framework, we develop a fair AutoML system based on an existing AutoML system. The augmented system includes a resource allocation strategy to dynamically decide when and on which models to conduct unfairness mitigation according to the prediction accuracy, fairness, and resource consumption on the fly. Extensive empirical evaluation shows that our system can achieve a good `fair accuracy' and high resource efficiency.

Federated Learning is a machine learning paradigm where we aim to train machine learning models in a distributed fashion. Many clients/edge devices collaborate with each other to train a single model on the central. Clients do not share their own datasets with each other, decoupling computation and data on the same device. In this paper, we propose yet another adaptive federated optimization method and some other ideas in the field of federated learning. We also perform experiments using these methods and showcase the improvement in the overall performance of federated learning.

Air transportation is essential for society, and it is increasing gradually due to its importance. To improve the airspace operation, new technologies are under development, such as Unmanned Aircraft Systems (UAS). In fact, in the past few years, there has been a growth in UAS numbers in segregated airspace. However, there is an interest in integrating these aircraft into the National Airspace System (NAS). The UAS is vital to different industries due to its advantages brought to the airspace (e.g., efficiency). Conversely, the relationship between UAS and Air Traffic Control (ATC) needs to be well-defined due to the impacts on ATC capacity these aircraft may present. Throughout the years, this impact may be lower than it is nowadays because the current lack of familiarity in this relationship contributes to higher workload levels. Thereupon, the primary goal of this research is to present a comprehensive review of the advancements in the integration of UAS in the National Airspace System (NAS) from different perspectives. We consider the challenges regarding simulation, final approach, and optimization of problems related to the interoperability of such systems in the airspace. Finally, we identify several open challenges in the field based on the existing state-of-the-art proposals.

No human drives a car in a vacuum; she/he must negotiate with other road users to achieve their goals in social traffic scenes. A rational human driver can interact with other road users in a socially-compatible way through implicit communications to complete their driving tasks smoothly in interaction-intensive, safety-critical environments. This paper aims to review the existing approaches and theories to help understand and rethink the interactions among human drivers toward social autonomous driving. We take this survey to seek the answers to a series of fundamental questions: 1) What is social interaction in road traffic scenes? 2) How to measure and evaluate social interaction? 3) How to model and reveal the process of social interaction? 4) How do human drivers reach an implicit agreement and negotiate smoothly in social interaction? This paper reviews various approaches to modeling and learning the social interactions between human drivers, ranging from optimization theory and graphical models to social force theory and behavioral & cognitive science. We also highlight some new directions, critical challenges, and opening questions for future research.

Electric vehicles (EVs) are being rapidly adopted due to their economic and societal benefits. Autonomous mobility-on-demand (AMoD) systems also embrace this trend. However, the long charging time and high recharging frequency of EVs pose challenges to efficiently managing EV AMoD systems. The complicated dynamic charging and mobility process of EV AMoD systems makes the demand and supply uncertainties significant when designing vehicle balancing algorithms. In this work, we design a data-driven distributionally robust optimization (DRO) approach to balance EVs for both the mobility service and the charging process. The optimization goal is to minimize the worst-case expected cost under both passenger mobility demand uncertainties and EV supply uncertainties. We then propose a novel distributional uncertainty sets construction algorithm that guarantees the produced parameters are contained in desired confidence regions with a given probability. To solve the proposed DRO AMoD EV balancing problem, we derive an equivalent computationally tractable convex optimization problem. Based on real-world EV data of a taxi system, we show that with our solution the average total balancing cost is reduced by 14.49%, and the average mobility fairness and charging fairness are improved by 15.78% and 34.51%, respectively, compared to solutions that do not consider uncertainties.

In this paper, we examine the concept of the predict and optimise problem with specific reference to the third Technical Challenge of the IEEE Computational Intelligence Society. In this competition, entrants were asked to forecast building energy use and solar generation at six buildings and six solar installations, and then use their forecast to optimize energy cost while scheduling classes and batteries over a month. We examine the possible effect of underforecasting and overforecasting and asymmetric errors on the optimisation cost. We explore the different nature of loss functions for the prediction and optimisation phase and propose to adjust the final forecasts for a better optimisation cost. We report that while there is a positive correlation between these two, more appropriate loss functions can be used to optimise the costs associated with final decisions.

Decision-focused learning (DFL) was recently proposed for stochastic optimization problems that involve unknown parameters. By integrating predictive modeling with an implicitly differentiable optimization layer, DFL has shown superior performance to the standard two-stage predict-then-optimize pipeline. However, most existing DFL methods are only applicable to convex problems or a subset of nonconvex problems that can be easily relaxed to convex ones. Further, they can be inefficient in training due to the requirement of solving and differentiating through the optimization problem in every training iteration. We propose SO-EBM, a general and efficient DFL method for stochastic optimization using energy-based models. Instead of relying on KKT conditions to induce an implicit optimization layer, SO-EBM explicitly parameterizes the original optimization problem using a differentiable optimization layer based on energy functions. To better approximate the optimization landscape, we propose a coupled training objective that uses a maximum likelihood loss to capture the optimum location and a distribution-based regularizer to capture the overall energy landscape. Finally, we propose an efficient training procedure for SO-EBM with a self-normalized importance sampler based on a Gaussian mixture proposal. We evaluate SO-EBM in three applications: power scheduling, COVID-19 resource allocation, and non-convex adversarial security game, demonstrating the effectiveness and efficiency of SO-EBM.

Transformer models have achieved state-of-the-art performance on various domains of applications and gradually becomes the foundations of the advanced large deep learning (DL) models. However, how to train these models over multiple GPUs efficiently is still challenging due to a large number of parallelism choices. Existing DL systems either rely on manual efforts to make distributed training plans or apply parallelism combinations within a very limited search space. In this approach, we propose Galvatron, a new system framework that incorporates multiple popular parallelism dimensions and automatically finds the most efficient hybrid parallelism strategy. To better explore such a rarely huge search space, we 1) involve a decision tree to make decomposition and pruning based on some reasonable intuitions, and then 2) design a dynamic programming search algorithm to generate the optimal plan. Evaluations on four representative Transformer workloads show that Galvatron could perform automatically distributed training with different GPU memory budgets. Among all evluated scenarios, Galvatron always achieves superior system throughput compared to previous work with limited parallelism.