Hydrodynamic flood modeling improves hydrologic and hydraulic prediction of storm events. However, the computationally intensive numerical solutions required for high-resolution hydrodynamics have historically prevented their implementation in near-real-time flood forecasting. This study examines whether several Deep Neural Network (DNN) architectures are suitable for optimizing hydrodynamic flood models. Several pluvial flooding events were simulated in a low-relief high-resolution urban environment using a 2D HEC-RAS hydrodynamic model. These simulations were assembled into a training set for the DNNs, which were then used to forecast flooding depths and velocities. The DNNs' forecasts were compared to the hydrodynamic flood models, and showed good agreement, with a median RMSE of around 2 mm for cell flooding depths in the study area. The DNNs also improved forecast computation time significantly, with the DNNs providing forecasts between 34.2 and 72.4 times faster than conventional hydrodynamic models. The study area showed little change between HEC-RAS' Full Momentum Equations and Diffusion Equations, however, important numerical stability considerations were discovered that impact equation selection and DNN architecture configuration. Overall, the results from this study show that DNNs can greatly optimize hydrodynamic flood modeling, and enable near-real-time hydrodynamic flood forecasting.

We propose a methodology for improving the accuracy of surrogate models of the observable response of physical systems as a function of the systems' spatially heterogeneous parameter fields with applications to uncertainty quantification and parameter estimation in high-dimensional problems. Practitioners often formulate finite-dimensional representations of spatially heterogeneous parameter fields using truncated unconditional Karhunen-Lo\'{e}ve expansions (KLEs) for a certain choice of unconditional covariance kernel and construct surrogate models of the observable response with respect to the random variables in the KLE. When direct measurements of the parameter fields are available, we propose improving the accuracy of these surrogate models by representing the parameter fields via conditional Karhunen-Lo\'{e}ve expansions (CKLEs). CKLEs are constructed by conditioning the covariance kernel of the unconditional expansion on the direct measurements via Gaussian process regression and then truncating the corresponding KLE. We apply the proposed methodology to constructing surrogate models via the Basis Adaptation (BA) method of the stationary hydraulic head response, measured at spatially discrete observation locations, of a groundwater flow model of the Hanford Site, as a function of the 1,000-dimensional representation of the model's log-transmissivity field. We find that BA surrogate models of the hydraulic head based on CKLEs are more accurate than BA surrogate models based on unconditional expansions for forward uncertainty quantification tasks. Furthermore, we find that inverse estimates of the hydraulic transmissivity field computed using CKLE-based BA surrogate models are more accurate than those computed using unconditional BA surrogate models.

Robots are notoriously difficult to design because of complex interdependencies between their physical structure, sensory and motor layouts, and behavior. Despite this, almost every detail of every robot built to date has been manually determined by a human designer after several months or years of iterative ideation, prototyping, and testing. Inspired by evolutionary design in nature, the automated design of robots using evolutionary algorithms has been attempted for two decades, but it too remains inefficient: days of supercomputing are required to design robots in simulation that, when manufactured, exhibit desired behavior. Here we show for the first time de-novo optimization of a robot's structure to exhibit a desired behavior, within seconds on a single consumer-grade computer, and the manufactured robot's retention of that behavior. Unlike other gradient-based robot design methods, this algorithm does not presuppose any particular anatomical form; starting instead from a randomly-generated apodous body plan, it consistently discovers legged locomotion, the most efficient known form of terrestrial movement. If combined with automated fabrication and scaled up to more challenging tasks, this advance promises near instantaneous design, manufacture, and deployment of unique and useful machines for medical, environmental, vehicular, and space-based tasks.

Recent work has proposed a power law relationship, referred to as ``scaling laws,'' between the performance of artificial intelligence (AI) models and aspects of those models' design (e.g., dataset size). In other words, as the size of a dataset (or model parameters, etc) increases, the performance of a given model trained on that dataset will correspondingly increase. However, while compelling in the aggregate, this scaling law relationship overlooks the ways that metrics used to measure performance may be precarious and contested, or may not correspond with how different groups of people may perceive the quality of models' output. In this paper, we argue that as the size of datasets used to train large AI models grows, the number of distinct communities (including demographic groups) whose data is included in a given dataset is likely to grow, each of whom may have different values. As a result, there is an increased risk that communities represented in a dataset may have values or preferences not captured by (or in the worst case, at odds with) the metrics used to evaluate model performance for scaling laws. We end the paper with implications for AI scaling laws -- that models may not, in fact, continue to improve as the datasets get larger -- at least not for all people or communities impacted by those models.

Entity matching (EM) is a challenging problem studied by different communities for over half a century. Algorithmic fairness has also become a timely topic to address machine bias and its societal impacts. Despite extensive research on these two topics, little attention has been paid to the fairness of entity matching. Towards addressing this gap, we perform an extensive experimental evaluation of a variety of EM techniques in this paper. We generated two social datasets from publicly available datasets for the purpose of auditing EM through the lens of fairness. Our findings underscore potential unfairness under two common conditions in real-world societies: (i) when some demographic groups are overrepresented, and (ii) when names are more similar in some groups compared to others. Among our many findings, it is noteworthy to mention that while various fairness definitions are valuable for different settings, due to EM's class imbalance nature, measures such as positive predictive value parity and true positive rate parity are, in general, more capable of revealing EM unfairness.

Transitive proxy voting (or "liquid democracy") is a novel form of collective decision making, often framed as an attractive hybrid of direct and representative democracy. Although the ideas behind liquid democracy have garnered widespread support, there have been relatively few attempts to model it formally. This paper makes three main contributions. First, it proposes a new social choice-theoretic model of liquid democracy, which is distinguished by taking a richer formal perspective on the process by which a voter chooses a proxy. Second, it examines the model from an axiomatic perspective, proving (a) a proxy vote analogue of May's Theorem and (b) an impossibility result concerning monotonicity properties in a proxy vote setting. Third, it explores the topic of manipulation in transitive proxy votes. Two forms of manipulation specific to the proxy vote setting are defined, and it is shown that manipulation occurs in strictly more cases in proxy votes than in classical votes.

The surveillance of a pandemic is a challenging task, especially when crucial data is distributed and stakeholders cannot or are unwilling to share. To overcome this obstacle, federated methodologies should be developed to incorporate less sensitive evidence that entities are willing to provide. This study aims to explore the feasibility of pushing hypothesis tests behind each custodian's firewall and then meta-analysis to combine the results, and to determine the optimal approach for reconstructing the hypothesis test and optimizing the inference. We propose a hypothesis testing framework to identify a surge in the indicators and conduct power analyses and experiments on real and semi-synthetic data to showcase the properties of our proposed hypothesis test and suggest suitable methods for combining $p$-values. Our findings highlight the potential of using $p$-value combination as a federated methodology for pandemic surveillance and provide valuable insights into integrating available data sources.

Large language models trained for safety and harmlessness remain susceptible to adversarial misuse, as evidenced by the prevalence of "jailbreak" attacks on early releases of ChatGPT that elicit undesired behavior. Going beyond recognition of the issue, we investigate why such attacks succeed and how they can be created. We hypothesize two failure modes of safety training: competing objectives and mismatched generalization. Competing objectives arise when a model's capabilities and safety goals conflict, while mismatched generalization occurs when safety training fails to generalize to a domain for which capabilities exist. We use these failure modes to guide jailbreak design and then evaluate state-of-the-art models, including OpenAI's GPT-4 and Anthropic's Claude v1.3, against both existing and newly designed attacks. We find that vulnerabilities persist despite the extensive red-teaming and safety-training efforts behind these models. Notably, new attacks utilizing our failure modes succeed on every prompt in a collection of unsafe requests from the models' red-teaming evaluation sets and outperform existing ad hoc jailbreaks. Our analysis emphasizes the need for safety-capability parity -- that safety mechanisms should be as sophisticated as the underlying model -- and argues against the idea that scaling alone can resolve these safety failure modes.

The recent advances in machine learning in various fields of applications can be largely attributed to the rise of deep learning (DL) methods and architectures. Despite being a key technology behind autonomous cars, image processing, speech recognition, etc., a notorious problem remains the lack of theoretical understanding of DL and related interpretability and (adversarial) robustness issues. Understanding the specifics of DL, as compared to, say, other forms of nonlinear regression methods or statistical learning, is interesting from a mathematical perspective, but at the same time it is of crucial importance in practice: treating neural networks as mere black boxes might be sufficient in certain cases, but many applications require waterproof performance guarantees and a deeper understanding of what could go wrong and why it could go wrong. It is probably fair to say that, despite being mathematically well founded as a method to approximate complicated functions, DL is mostly still more like modern alchemy that is firmly in the hands of engineers and computer scientists. Nevertheless, it is evident that certain specifics of DL that could explain its success in applications demands systematic mathematical approaches. In this work, we review robustness issues of DL and particularly bridge concerns and attempts from approximation theory to statistical learning theory. Further, we review Bayesian Deep Learning as a means for uncertainty quantification and rigorous explainability.

Providing accurate uncertainty estimations is essential for producing reliable machine learning models, especially in safety-critical applications such as accelerator systems. Gaussian process models are generally regarded as the gold standard method for this task, but they can struggle with large, high-dimensional datasets. Combining deep neural networks with Gaussian process approximation techniques have shown promising results, but dimensionality reduction through standard deep neural network layers is not guaranteed to maintain the distance information necessary for Gaussian process models. We build on previous work by comparing the use of the singular value decomposition against a spectral-normalized dense layer as a feature extractor for a deep neural Gaussian process approximation model and apply it to a capacitance prediction problem for the High Voltage Converter Modulators in the Oak Ridge Spallation Neutron Source. Our model shows improved distance preservation and predicts in-distribution capacitance values with less than 1% error.