Nonlocal, integral operators have become an efficient surrogate for bottom-up homogenization, due to their ability to represent long-range dependence and multiscale effects. However, the nonlocal homogenized model has unavoidable discrepancy from the microscale model. Such errors accumulate and propagate in long-term simulations, making the resultant prediction unreliable. To develop a robust and reliable bottom-up homogenization framework, we propose a new framework, which we coin Embedded Nonlocal Operator Regression (ENOR), to learn a nonlocal homogenized surrogate model and its structural model error. This framework provides discrepancy-adaptive uncertainty quantification for homogenized material response predictions in long-term simulations. The method is built on Nonlocal Operator Regression (NOR), an optimization-based nonlocal kernel learning approach, together with an embedded model error term in the trainable kernel. Then, Bayesian inference is employed to infer the model error term parameters together with the kernel parameters. To make the problem computationally feasible, we use a multilevel delayed acceptance Markov chain Monte Carlo (MLDA-MCMC) method, enabling efficient Bayesian model calibration and model error estimation. We apply this technique to predict long-term wave propagation in a heterogeneous one-dimensional bar, and compare its performance with additive noise models. Owing to its ability to capture model error, the learned ENOR achieves improved estimation of posterior predictive uncertainty.

Efficiently processing structured point cloud data while preserving multiscale information is a key challenge across domains, from graphics to atomistic modeling. Using a curated dataset of simulated galaxy positions and properties, represented as point clouds, we benchmark the ability of graph neural networks to simultaneously capture local clustering environments and long-range correlations. Given the homogeneous and isotropic nature of the Universe, the data exhibits a high degree of symmetry. We therefore focus on evaluating the performance of Euclidean symmetry-preserving ($E(3)$-equivariant) graph neural networks, showing that they can outperform non-equivariant counterparts and domain-specific information extraction techniques in downstream performance as well as simulation-efficiency. However, we find that current architectures fail to capture information from long-range correlations as effectively as domain-specific baselines, motivating future work on architectures better suited for extracting long-range information.

One of the major challenges in training SAEs is the substantial storage and throughput required for latent activations. While text data requires only 2 bytes per token, latent activations occupy 8K bytes per token--resulting in a 4,096x increase in both storage needs and disk throughput. This, combined with the relatively fast training steps of shallow SAEs, means that data loading quickly becomes the main bottleneck in the training process. Due to these infrastructure constraints, we do not save activations in advance but instead generate them on-the-fly. This contrasts with the approach taken by Lieberum et al. (2024); Templeton et al. (2024b), where activations are pre-saved and a high-speed dataloading pipeline is built to keep up with training. To manage this, we adopt a producer-consumer model. Language Models (LMs) generate activations and store them in an activation buffer, while the SAEs consume the activations in random order. The process is serialized: once the buffer is full, SAE training begins, and when half the buffer is consumed, the LMs refill it. Each time the buffer is refilled, we shuffle it to introduce randomness into the training data without needing to save and shuffle all activations at once.

In light of the recent success of Graph Neural Networks (GNNs) and their ability to perform inference on complex data structures, many studies apply GNNs to the task of text classification. In most previous methods, a heterogeneous graph, containing both word and document nodes, is constructed using the entire corpus and a GNN is used to classify document nodes. In this work, we explore a new Discriminative Graph of Words Graph Neural Network (DGoW-GNN) approach encapsulating both a novel discriminative graph construction and model to classify text. In our graph construction, containing only word nodes and no document nodes, we split the training corpus into disconnected subgraphs according to their labels and weight edges by the pointwise mutual information of the represented words. Our graph construction, for which we provide theoretical motivation, allows us to reformulate the task of text classification as the task of walk classification. We also propose a new model for the graph-based classification of text, which combines a GNN and a sequence model. We evaluate our approach on seven benchmark datasets and find that it is outperformed by several state-of-the-art baseline models. We analyse reasons for this performance difference and hypothesise under which conditions it is likely to change.

Eighty years after the International Monetary Fund and the World Bank were created to stabilize the global economy in the wake of World War II, the role of those organizations and the guiding principles behind their creation has largely fallen out of fashion. The I.M.F. and World Bank were designed to embrace a new system of economic order and international cooperation, one that would stitch the world economy together and allow rich nations to help poorer ones through trade and investment. But today, those who espouse such "neoliberal" notions of open markets are increasingly lonely voices. They could soon become even more isolated if former President Donald J. Trump is re-elected. Mr. Trump is promising to upend the rules of international commerce by ratcheting up the kind of trade wars and protectionist policies that characterized his first term.

It's been exactly 40 years since The Terminator hit the big screen, shocking cinemagoers with its terrifying depiction of a post-apocalyptic future. In James Cameron's epic sci-fi blockbuster, billions of people are killed when self-aware machines trigger a global nuclear war around the start of the 21st century. Arnold Schwarzenegger stars as the eponymous robotic assassin sent back in time from 2029 to 1984 to eliminate the threat of a human resistance. Famously, the Terminator, which looks just like an adult human, 'absolutely will not stop … until you are dead', as one character puts it. While this sounds like pure sci-fi, academic and industry figures – including Elon Musk – fear that humanity will indeed be annihilated by AI. But when exactly will this happen?

Seawater intrusion into coastal aquifers poses a significant threat to groundwater resources, especially with rising sea levels due to climate change. Accurate modeling and uncertainty quantification of this process are crucial but are often hindered by the high computational costs of traditional numerical simulations. In this work, we develop GeoFUSE, a novel deep-learning-based surrogate framework that integrates the U-Net Fourier Neural Operator (U-FNO) with Principal Component Analysis (PCA) and Ensemble Smoother with Multiple Data Assimilation (ESMDA). GeoFUSE enables fast and efficient simulation of seawater intrusion while significantly reducing uncertainty in model predictions. We apply GeoFUSE to a 2D cross-section of the Beaver Creek tidal stream-floodplain system in Washington State. Using 1,500 geological realizations, we train the U-FNO surrogate model to approximate salinity distribution and accumulation. The U-FNO model successfully reduces the computational time from hours (using PFLOTRAN simulations) to seconds, achieving a speedup of approximately 360,000 times while maintaining high accuracy. By integrating measurement data from monitoring wells, the framework significantly reduces geological uncertainty and improves the predictive accuracy of the salinity distribution over a 20-year period. Our results demonstrate that GeoFUSE improves computational efficiency and provides a robust tool for real-time uncertainty quantification and decision making in groundwater management. Future work will extend GeoFUSE to 3D models and incorporate additional factors such as sea-level rise and extreme weather events, making it applicable to a broader range of coastal and subsurface flow systems.

Delivering prompt information and guidance to farmers is critical in agricultural decision-making. Farmers helpline centres are heavily reliant on the expertise and availability of call centre agents, leading to inconsistent quality and delayed responses. To this end, this article presents Kisan Query Response System (KisanQRS), a Deep Learning-based robust query-response framework for the agriculture sector. KisanQRS integrates semantic and lexical similarities of farmers queries and employs a rapid threshold-based clustering method. The clustering algorithm is based on a linear search technique to iterate through all queries and organize them into clusters according to their similarity. For query mapping, LSTM is found to be the optimal method. Our proposed answer retrieval method clusters candidate answers for a crop, ranks these answer clusters based on the number of answers in a cluster, and selects the leader of each cluster. The dataset used in our analysis consists of a subset of 34 million call logs from the Kisan Call Centre (KCC), operated under the Government of India. We evaluated the performance of the query mapping module on the data of five major states of India with 3,00,000 samples and the quantifiable outcomes demonstrate that KisanQRS significantly outperforms traditional techniques by achieving 96.58% top F1-score for a state. The answer retrieval module is evaluated on 10,000 samples and it achieves a competitive NDCG score of 96.20%. KisanQRS is useful in enabling farmers to make informed decisions about their farming practices by providing quick and pertinent responses to their queries.

Participatory budgeting (PB) is a voting paradigm for distributing a divisible resource, usually called a budget, among a set of projects by aggregating the preferences of individuals over these projects. It is implemented quite extensively for purposes such as government allocating funds to public projects and funding agencies selecting research proposals to support. This PhD dissertation studies the welfare-related and fairness-related objectives for different PB models. Our contribution lies in proposing and exploring novel PB rules that maximize welfare and promote fairness, as well as, in introducing and investigating a range of novel utility notions, axiomatic properties, and fairness notions, effectively filling the gaps in the existing literature for each PB model. The thesis is divided into two main parts, the first focusing on dichotomous and the second focusing on ordinal preferences. Each part considers two cases: (i) the cost of each project is restricted to a single value and partial funding is not permitted and (ii) the cost of each project is flexible and may assume multiple values.

Regulatory frameworks for the use of AI are emerging. However, they trail behind the fast-evolving malicious AI technologies that can quickly cause lasting societal damage. In response, we introduce a pioneering Assistive AI framework designed to enhance human decision-making capabilities. This framework aims to establish a trust network across various fields, especially within legal contexts, serving as a proactive complement to ongoing regulatory efforts. Central to our framework are the principles of privacy, accountability, and credibility. In our methodology, the foundation of reliability of information and information sources is built upon the ability to uphold accountability, enhance security, and protect privacy. This approach supports, filters, and potentially guides communication, thereby empowering individuals and communities to make well-informed decisions based on cutting-edge advancements in AI. Our framework uses the concept of Boards as proxies to collectively ensure that AI-assisted decisions are reliable, accountable, and in alignment with societal values and legal standards. Through a detailed exploration of our framework, including its main components, operations, and sample use cases, the paper shows how AI can assist in the complex process of decision-making while maintaining human oversight. The proposed framework not only extends regulatory landscapes but also highlights the synergy between AI technology and human judgement, underscoring the potential of AI to serve as a vital instrument in discerning reality from fiction and thus enhancing the decision-making process. Furthermore, we provide domain-specific use cases to highlight the applicability of our framework.