Accurate, fine-grained poverty maps remain scarce across much of the Global South. While Demographic and Health Surveys (DHS) provide high-quality socioeconomic data, their spatial coverage is limited and reported coordinates are randomly displaced for privacy, further reducing their quality. We propose a graph-based approach leveraging low-dimensional AlphaEarth satellite embeddings to predict cluster-level wealth indices across Sub-Saharan Africa. By modeling spatial relations between surveyed and unlabeled locations, and by introducing a probabilistic "fuzzy label" loss to account for coordinate displacement, we improve the generalization of wealth predictions beyond existing surveys. Our experiments on 37 DHS datasets (2017-2023) show that incorporating graph structure slightly improves accuracy compared to "image-only" baselines, demonstrating the potential of compact EO embeddings for large-scale socioeconomic mapping.

Privacy concerns have become increasingly critical in modern AI and data science applications, where sensitive information is collected, analyzed, and shared across diverse domains such as healthcare, finance, and mobility. While prior research has focused on protecting privacy in a single data release, many real-world systems operate under sequential or continuous data publishing, where the same or related data are released over time. Such sequential disclosures introduce new vulnerabilities, as temporal correlations across releases may enable adversaries to infer sensitive information that remains hidden in any individual release. In this paper, we investigate whether an attacker can compromise privacy in sequential data releases by exploiting dependencies between consecutive publications, even when each individual release satisfies standard privacy guarantees. To this end, we propose a novel attack model that captures these sequential dependencies by integrating a Hidden Markov Model with a reinforcement learning-based bi-directional inference mechanism. This enables the attacker to leverage both earlier and later observations in the sequence to infer private information. We instantiate our framework in the context of trajectory data, demonstrating how an adversary can recover sensitive locations from sequential mobility datasets. Extensive experiments on Geolife, Porto Taxi, and SynMob datasets show that our model consistently outperforms baseline approaches that treat each release independently. The results reveal a fundamental privacy risk inherent to sequential data publishing, where individually protected releases can collectively leak sensitive information when analyzed temporally. These findings underscore the need for new privacy-preserving frameworks that explicitly model temporal dependencies, such as time-aware differential privacy or sequential data obfuscation strategies.

The objective of this study is improving the location estimate of a mobile robot capable of motion on a plane and mounted with a conventional 2D LIDAR sensor, given an initial guess for its location on a 2D map of its surroundings. Documented herein is the theoretical reasoning behind solving a matching problem between two homoriented 2D scans, one derived from the robot's physical sensor and one derived by simulating its operation within the map, in a manner that does not require the establishing of correspondences between their constituting rays. Two results are proved and subsequently shown through experiments. The first is that the true position of the sensor can be recovered with arbitrary precision when the physical sensor reports faultless measurements and there is no discrepancy between the environment the robot operates in and its perception of it by the robot. The second is that when either is affected by disturbance, the location estimate is bound in a neighbourhood of the true location whose radius is proportional to the affecting disturbance.

Machine learning requires many sophisticated algorithms to learn from existing data, then apply the learnings to new data. Dynamic programming turns up in many of these algorithms. This may be because dynamic programming excels at solving problems involving "non-local" information, making greedy or divide-and-conquer algorithms ineffective. In this article, I'll explore one technique used in machine learning, Hidden Markov Models (HMMs), and how dynamic programming is used when applying this technique. After discussing HMMs, I'll show a few real-world examples where HMMs are used.

We initiate the study of mechanism design without money for common goods. Our model captures a variation of the well-known one-dimensional facility location problem if the facility is assumed to have a capacity constraint $k