Search

Ground-penetrating radar (GPR) is a mature geophysical method that has gained increasing popularity in planetary science over the past decade. GPR has been utilised both for Lunar and Martian missions providing pivotal information regarding the near surface geology of Terrestrial planets. Within that context, numerous processing pipelines have been suggested to address the unique challenges present in planetary setups. These processing pipelines often require manual tuning resulting to ambiguous outputs open to non-unique interpretations. These pitfalls combined with the large number of planetary GPR data (kilometers in magnitude), highlight the necessity for automatic, objective and advanced processing and interpretation schemes. The current paper investigates the potential of deep learning for interpreting and processing GPR data. The one-shot multi-offset configuration is investigated via a coherent numerical case study, showcasing the potential of deep learning for A) reconstructing the dielectric distribution of the the near surface of Terrestrial planets, and B) filling missing or bad-quality traces. Special care was taken for the numerical data to be both realistic and challenging. Moreover, the generated synthetic data are properly labelled and made publicly available for training future data-driven pipelines and contributing towards developing pre-trained foundation models for GPR.

In this paper, we address the challenge of heterogeneous data distributions in cross-silo federated learning by introducing a novel algorithm, which we term Cross-silo Robust Clustered Federated Learning (CS-RCFL). Our approach leverages the Wasserstein distance to construct ambiguity sets around each client's empirical distribution that capture possible distribution shifts in the local data, enabling evaluation of worst-case model performance. We then propose a model-agnostic integer fractional program to determine the optimal distributionally robust clustering of clients into coalitions so that possible biases in the local models caused by statistically heterogeneous client datasets are avoided, and analyze our method for linear and logistic regression models. Finally, we discuss a federated learning protocol that ensures the privacy of client distributions, a critical consideration, for instance, when clients are healthcare institutions. We evaluate our algorithm on synthetic and real-world healthcare data., Comment: 8 pages, 3 figures, Accepted to IEEE CDC 2024

We study the problem of searching for a target at some unknown location in $\mathbb{R}^d$ when additional information regarding the position of the target is available in the form of predictions. In our setting, predictions come as approximate distances to the target: for each point $p\in \mathbb{R}^d$ that the searcher visits, we obtain a value $\lambda(p)$ such that $|p\mathbf{t}|\le \lambda(p) \le c\cdot |p\mathbf{t}|$, where $c\ge 1$ is a fixed constant, $\mathbf{t}$ is the position of the target, and $|p\mathbf{t}|$ is the Euclidean distance of $p$ to $\mathbf{t}$. The cost of the search is the length of the path followed by the searcher. Our main positive result is a strategy that achieves $(12c)^{d+1}$-competitive ratio, even when the constant $c$ is unknown. We also give a lower bound of roughly $(c/16)^{d-1}$ on the competitive ratio of any search strategy in $\mathbb{R}^d$., Comment: 19 pages, WAOA 24

The widespread deployment of machine learning systems in critical real-world decision-making applications has highlighted the urgent need for counterfactual explainability methods that operate effectively. Global counterfactual explanations, expressed as actions to offer recourse, aim to provide succinct explanations and insights applicable to large population subgroups. Effectiveness is measured by the fraction of the population that is provided recourse, ensuring that the actions benefit as many individuals as possible. Keeping the cost of actions low ensures the proposed recourse actions remain practical and actionable. Limiting the number of actions that provide global counterfactuals is essential to maximize interpretability. The primary challenge, therefore, is balancing these trade-offs, i.e., maximizing effectiveness, minimizing cost, while maintaining a small number of actions. We introduce GLANCE, a versatile and adaptive framework, comprising two algorithms, that allows the careful balancing of the trade-offs among the three key objectives, with the size objective functioning as a tunable parameter to keep the actions few and easy to interpret. C-GLANCE employs a clustering approach that considers both the feature space and the space of counterfactual actions, thereby accounting for the distribution of points in a way that aligns with the structure of the model. T-GLANCE provides additional features to enhance flexibility. It employs a tree-based approach, that allows users to specify split features, to build a decision tree with a single counterfactual action at each node that can be used as a subgroup policy. Our extensive experimental evaluation demonstrates that our method consistently shows greater robustness and performance compared to existing methods across various datasets and models.

In this paper we examine algorithmic fairness from the perspective of law aiming to identify best practices and strategies for the specification and adoption of fairness definitions and algorithms in real-world systems and use cases. We start by providing a brief introduction of current anti-discrimination law in the European Union and the United States and discussing the concepts of bias and fairness from an legal and ethical viewpoint. We then proceed by presenting a set of algorithmic fairness definitions by example, aiming to communicate their objectives to non-technical audiences. Then, we introduce a set of core criteria that need to be taken into account when selecting a specific fairness definition for real-world use case applications. Finally, we enumerate a set of key considerations and best practices for the design and employment of fairness methods on real-world AI applications, Comment: Preprint. Accepted in Fairness in AI Workshop @ ICDE 2024

Fairness is steadily becoming a crucial requirement of Machine Learning (ML) systems. A particularly important notion is subgroup fairness, i.e., fairness in subgroups of individuals that are defined by more than one attributes. Identifying bias in subgroups can become both computationally challenging, as well as problematic with respect to comprehensibility and intuitiveness of the finding to end users. In this work we focus on the latter aspects; we propose an explainability method tailored to identifying potential bias in subgroups and visualizing the findings in a user friendly manner to end users. In particular, we extend the ALE plots explainability method, proposing FALE (Fairness aware Accumulated Local Effects) plots, a method for measuring the change in fairness for an affected population corresponding to different values of a feature (attribute). We envision FALE to function as an efficient, user friendly, comprehensible and reliable first-stage tool for identifying subgroups with potential bias issues., Comment: Presented in Uncertainty meets Explainability Workshop @ ECML/PKDD 2023

In this paper we present a deep learning pipeline for next day fire prediction. The next day fire prediction task consists in learning models that receive as input the available information for an area up until a certain day, in order to predict the occurrence of fire for the next day. Starting from our previous problem formulation as a binary classification task on instances (daily snapshots of each area) represented by tabular feature vectors, we reformulate the problem as a semantic segmentation task on images; there, each pixel corresponds to a daily snapshot of an area, while its channels represent the formerly tabular training features. We demonstrate that this problem formulation, built within a thorough pipeline achieves state of the art results., Comment: Accepted in MACLEAN@ECML/PKDD 2023

Extreme ultraviolet (EUV) lithography is the leading lithography technique in CMOS mass production, moving towards the sub-10 nm half-pitch (HP) regime with the ongoing development of the next generation high-numerical aperture (high-NA) EUV scanners. Hitherto, EUV interference lithography (EUV-IL) utilizing transmission gratings has been a powerful patterning tool for the early development of EUV resists and related processes, playing a key role in exploring and pushing the boundaries of photon-based lithography. However, achieving pattering with HPs well below 10 nm using this method presents significant challenges. In response, our study introduces a novel EUV-IL setup that employs mirror-based technology and circumvents the limitations of diffraction efficiency towards the diffraction limit that is inherent in conventional grating-based approaches. We present line/space patterning of HSQ resist down to HP 5 nm using the standard EUV wavelength 13.5 nm, and the compatibility of the tool with shorter wavelengths beyond EUV. The mirror-based interference lithography tool paves the way towards the ultimate photon-based resolution at EUV wavelengths and beyond. This advancement is vital for scientific and industrial research, addressing the increasingly challenging needs of nanoscience and technology and future technology nodes of CMOS manufacturing in the few-nanometer HP regime.

In this work, we present Fairness Aware Counterfactuals for Subgroups (FACTS), a framework for auditing subgroup fairness through counterfactual explanations. We start with revisiting (and generalizing) existing notions and introducing new, more refined notions of subgroup fairness. We aim to (a) formulate different aspects of the difficulty of individuals in certain subgroups to achieve recourse, i.e. receive the desired outcome, either at the micro level, considering members of the subgroup individually, or at the macro level, considering the subgroup as a whole, and (b) introduce notions of subgroup fairness that are robust, if not totally oblivious, to the cost of achieving recourse. We accompany these notions with an efficient, model-agnostic, highly parameterizable, and explainable framework for evaluating subgroup fairness. We demonstrate the advantages, the wide applicability, and the efficiency of our approach through a thorough experimental evaluation of different benchmark datasets.

We study the problem of $k$-means clustering in the space of straight-line segments in $\mathbb{R}^{2}$ under the Hausdorff distance. For this problem, we give a $(1+\epsilon)$-approximation algorithm that, for an input of $n$ segments, for any fixed $k$, and with constant success probability, runs in time $O(n+ \epsilon^{-O(k)} + \epsilon^{-O(k)}\cdot \log^{O(k)} (\epsilon^{-1}))$. The algorithm has two main ingredients. Firstly, we express the $k$-means objective in our metric space as a sum of algebraic functions and use the optimization technique of Vigneron~\cite{Vigneron14} to approximate its minimum. Secondly, we reduce the input size by computing a small size coreset using the sensitivity-based sampling framework by Feldman and Langberg~\cite{Feldman11, Feldman2020}. Our results can be extended to polylines of constant complexity with a running time of $O(n+ \epsilon^{-O(k)})$., Comment: 18 pages, 3 figures

This paper studies algorithmic fairness when the protected attribute is location. To handle protected attributes that are continuous, such as age or income, the standard approach is to discretize the domain into predefined groups, and compare algorithmic outcomes across groups. However, applying this idea to location raises concerns of gerrymandering and may introduce statistical bias. Prior work addresses these concerns but only for regularly spaced locations, while raising other issues, most notably its inability to discern regions that are likely to exhibit spatial unfairness. Similar to established notions of algorithmic fairness, we define spatial fairness as the statistical independence of outcomes from location. This translates into requiring that for each region of space, the distribution of outcomes is identical inside and outside the region. To allow for localized discrepancies in the distribution of outcomes, we compare how well two competing hypotheses explain the observed outcomes. The null hypothesis assumes spatial fairness, while the alternate allows different distributions inside and outside regions. Their goodness of fit is then assessed by a likelihood ratio test. If there is no significant difference in how well the two hypotheses explain the observed outcomes, we conclude that the algorithm is spatially fair.

This article belongs to the area of geometric tomography, which is the study of geometric properties of solids based on data about their sections and projections. We describe a new direction in geometric tomography where different volumetric results are considered in a more general setting, with volume replaced by an arbitrary measure. Surprisingly, such a general approach works for a number of volumetric results. In particular, we discuss the Busemann-Petty problem on sections of convex bodies for arbitrary measures and the slicing problem for arbitrary measures. We present generalizations of these questions to the case of functions. A number of generalizations of questions related to projections, such as the problem of Shephard, are also discussed as well as some questions in discrete tomography.

Soiling is the accumulation of dirt in solar panels which leads to a decreasing trend in solar energy yield and may be the cause of vast revenue losses. The effect of soiling can be reduced by washing the panels, which is, however, a procedure of non-negligible cost. Moreover, soiling monitoring systems are often unreliable or very costly. We study the problem of estimating the soiling ratio in photo-voltaic (PV) modules, i.e., the ratio of the real power output to the power output that would be produced if solar panels were clean. A key advantage of our algorithms is that they estimate soiling, without needing to train on labelled data, i.e., periods of explicitly monitoring the soiling in each park, and without relying on generic analytical formulas which do not take into account the peculiarities of each installation. We consider as input a time series comprising a minimum set of measurements, that are available to most PV park operators. Our experimental evaluation shows that we significantly outperform current state-of-the-art methods for estimating soiling ratio., Comment: 12 pages, 4 figures