Publications

Reconstructing robust background integral field unit spectra using machine learning
Carter Lee Rhea
Julie Hlavacek-Larrondo
Justine Giroux
Auriane Thilloy
Hyunseop Choi
Laurie Rousseau-Nepton
Marie-Lou Gendron-Marsolais
Mario Pasquato
Simon Prunet
ABSTRACT In astronomy, spectroscopy consists of observing an astrophysical source and extracting its spectrum of electromagnetic radiation. … (see more)Once extracted, a model is fit to the spectra to measure the observables, leading to an understanding of the underlying physics of the emission mechanism. One crucial, and often overlooked, aspect of this model is the background emission, which contains foreground and background astrophysical sources, intervening atmospheric emission, and artefacts related to the instrument such as noise. This paper proposes an algorithmic approach to constructing a background model for SITELLE observations using statistical tools and supervised machine learning algorithms. SITELLE is an imaging Fourier transform spectrometer located at the Canada-France-Hawaii Telescope, which produces a three-dimensional data cube containing the position of the emission (two dimensions) and the spectrum of the emission. SITELLE has a wide field of view (11 arcmin × 11 arcmin), which makes the background emission particularly challenging to model. We apply a segmentation algorithm implemented in photutils to divide the data cube into background and source spaxels. After applying a principal component analysis (PCA) on the background spaxels, we train an artificial neural network to interpolate from the background to the source spaxels in the PCA coefficient space, which allows us to generate a local background model over the entire data cube. We highlight the performance of this methodology by applying it to SITELLE observations obtained of a Star-formation, Ionized Gas and Nebular Abundances Legacy Survey galaxy, NGC 4449, and the Perseus galaxy cluster of galaxies, NGC 1275. We discuss the physical interpretation of the principal components and noise reduction in the resulting PCA-based reconstructions. Additionally, we compare the fit results using our new background modelling approach with standard methods used in the literature and find that our method better captures the emission from H ii regions in NGC 4449 and the faint emission regions in NGC 1275. These methods also demonstrate that the background does change as a function of the position of the data cube. While the approach is applied explicitly to SITELLE data in this study, we argue that it can be readily adapted to any integral field unit style data, enabling the user to obtain more robust measurements on the flux of the emission lines.
2024-04-24
RAS Techniques and Instruments (published)
doi.org
Autoregressive Networks with Dependent Edges
Jinyuan Chang
Qin Fang
Eric D. Kolaczyk
Peter W. MacDonald
Qiwei Yao
2024-04-23
ArXiv (preprint)
arxiv.org
arxiv.org
Implementation of a Global Pediatric Trauma Course in an Upper Middle–Income Country: A Pilot Study
Abbie Naus
Madeleine Carroll
Ayla Gerk
David P. Mooney
Natalie L. Yanchar
Julia Ferreira
Dan Poenaru
Karen E. Gripp
Caroline Ouellet
Fabio Botelho
2024-04-23
Journal of Surgical Research (published)
doi.org
Radiation hardness of open Fabry-Pérot microcavities
Fernanda C. Rodrigues-Machado
Erika Janitz
Simon Bernard
H. Bekerat
Malcolm McEwen
James Renaud
S. Enger
Lilian Childress
Jack C Sankey
2024-04-23
Optics Express (published)
doi.org
arxiv.org
Universal Adversarial Triggers Are Not Universal
Nicholas Meade
Arkil Patel
Siva Reddy
2024-04-23
arXiv (preprint)
doi.org
arxiv.org
Fairness Incentives in Response to Unfair Dynamic Pricing
Jesse Thibodeau
Hadi Nekoei
Afaf Taïk
Janarthanan Rajendran
Golnoosh Farnadi
The use of dynamic pricing by profit-maximizing firms gives rise to demand fairness concerns, measured by discrepancies in consumer groups' … (see more)demand responses to a given pricing strategy. Notably, dynamic pricing may result in buyer distributions unreflective of those of the underlying population, which can be problematic in markets where fair representation is socially desirable. To address this, policy makers might leverage tools such as taxation and subsidy to adapt policy mechanisms dependent upon their social objective. In this paper, we explore the potential for AI methods to assist such intervention strategies. To this end, we design a basic simulated economy, wherein we introduce a dynamic social planner (SP) to generate corporate taxation schedules geared to incentivizing firms towards adopting fair pricing behaviours, and to use the collected tax budget to subsidize consumption among underrepresented groups. To cover a range of possible policy scenarios, we formulate our social planner's learning problem as a multi-armed bandit, a contextual bandit and finally as a full reinforcement learning (RL) problem, evaluating welfare outcomes from each case. To alleviate the difficulty in retaining meaningful tax rates that apply to less frequently occurring brackets, we introduce FairReplayBuffer, which ensures that our RL agent samples experiences uniformly across a discretized fairness space. We find that, upon deploying a learned tax and redistribution policy, social welfare improves on that of the fairness-agnostic baseline, and approaches that of the analytically optimal fairness-aware baseline for the multi-armed and contextual bandit settings, and surpassing it by 13.19% in the full RL setting.
2024-04-21
ArXiv (preprint)
doi.org
arxiv.org
Learning Control Barrier Functions and their application in Reinforcement Learning: A Survey
Maeva Guerrier
Hassan Fouad
Giovanni Beltrame
Reinforcement learning is a powerful technique for developing new robot behaviors. However, typical lack of safety guarantees constitutes a … (see more)hurdle for its practical application on real robots. To address this issue, safe reinforcement learning aims to incorporate safety considerations, enabling faster transfer to real robots and facilitating lifelong learning. One promising approach within safe reinforcement learning is the use of control barrier functions. These functions provide a framework to ensure that the system remains in a safe state during the learning process. However, synthesizing control barrier functions is not straightforward and often requires ample domain knowledge. This challenge motivates the exploration of data-driven methods for automatically defining control barrier functions, which is highly appealing. We conduct a comprehensive review of the existing literature on safe reinforcement learning using control barrier functions. Additionally, we investigate various techniques for automatically learning the Control Barrier Functions, aiming to enhance the safety and efficacy of Reinforcement Learning in practical robot applications.
2024-04-21
ArXiv (preprint)
doi.org
arxiv.org
Foliar spectra accurately distinguish most temperate tree species and show strong phylogenetic signal
Florence Blanchard
Anne Bruneau
Étienne Laliberté
2024-04-19
American-Eurasian journal of botany (published)
doi.org
BACS: Background Aware Continual Semantic Segmentation
Mostafa Elaraby
Ali Harakeh
Liam Paull
Semantic segmentation plays a crucial role in enabling comprehensive scene understanding for robotic systems. However, generating annotation… (see more)s is challenging, requiring labels for every pixel in an image. In scenarios like autonomous driving, there's a need to progressively incorporate new classes as the operating environment of the deployed agent becomes more complex. For enhanced annotation efficiency, ideally, only pixels belonging to new classes would be annotated. This approach is known as Continual Semantic Segmentation (CSS). Besides the common problem of classical catastrophic forgetting in the continual learning setting, CSS suffers from the inherent ambiguity of the background, a phenomenon we refer to as the"background shift'', since pixels labeled as background could correspond to future classes (forward background shift) or previous classes (backward background shift). As a result, continual learning approaches tend to fail. This paper proposes a Backward Background Shift Detector (BACS) to detect previously observed classes based on their distance in the latent space from the foreground centroids of previous steps. Moreover, we propose a modified version of the cross-entropy loss function, incorporating the BACS detector to down-weight background pixels associated with formerly observed classes. To combat catastrophic forgetting, we employ masked feature distillation alongside dark experience replay. Additionally, our approach includes a transformer decoder capable of adjusting to new classes without necessitating an additional classification head. We validate BACS's superior performance over existing state-of-the-art methods on standard CSS benchmarks.
2024-04-18
ArXiv (preprint)
doi.org
arxiv.org
BLIS-Net: Classifying and Analyzing Signals on Graphs
Charles Xu
Laney Goldman
Valentina Guo
Benjamin Hollander-Bodie
Maedee Trank-Greene
Ian Adelstein
Edward De Brouwer
Rex Ying
Smita Krishnaswamy
Michael Perlmutter
Graph neural networks (GNNs) have emerged as a powerful tool for tasks such as node classification and graph classification. However, much l… (see more)ess work has been done on signal classification, where the data consists of many functions (referred to as signals) defined on the vertices of a single graph. These tasks require networks designed differently from those designed for traditional GNN tasks. Indeed, traditional GNNs rely on localized low-pass filters, and signals of interest may have intricate multi-frequency behavior and exhibit long range interactions. This motivates us to introduce the BLIS-Net (Bi-Lipschitz Scattering Net), a novel GNN that builds on the previously introduced geometric scattering transform. Our network is able to capture both local and global signal structure and is able to capture both low-frequency and high-frequency information. We make several crucial changes to the original geometric scattering architecture which we prove increase the ability of our network to capture information about the input signal and show that BLIS-Net achieves superior performance on both synthetic and real-world data sets based on traffic flow and fMRI data.
2024-04-17
Proceedings of The 27th International Conference on Artificial Intelligence and Statistics (published)
doi.org
proceedings.mlr.press
Categorical Generative Model Evaluation via Synthetic Distribution Coarsening
Florence Regol
Mark J. Coates
As we expect to see a rapid integration of generative models in our day to day lives, the development of rigorous methods of evaluation and … (see more)analysis for generative models has never been more pressing. Multiple works have highlighted the shortcomings of widely used metrics and exposed how they fail to behave as expected in some settings. So far, the response has been to use a variety of metrics that target different desirable and interpretable properties such as fidelity, diversity, and authenticity, to obtain a clearer picture of a generative model’s capabilities. These methods mainly focus on ordinal data and they all suffer from the same unavoidable issues stemming from estimating quantities of high-dimensional data from a limited number of samples. We propose to take an alternative approach and to return to the synthetic data setting where the ground truth is explicit and known. We focus on nominal categorical data and introduce an evaluation method that can scale to the high-dimensional settings often encountered in practice. Our method involves successively binning the large space to obtain smaller probability spaces and coarser distributions where meaningful statistical estimates can be obtained. This allows us to provide probabilistic guarantees and sample complexities and we illustrate how our method can be applied to distinguish between the capabilities of several state-of-the-art categorical models.
2024-04-17
Proceedings of The 27th International Conference on Artificial Intelligence and Statistics (published)
proceedings.mlr.press
proceedings.mlr.press
Identifying Spurious Biases Early in Training through the Lens of Simplicity Bias
Yu Yang
Eric Gan
Gintare Karolina Dziugaite
Baharan Mirzasoleiman
Neural networks trained with (stochastic) gradient descent have an inductive bias towards learning simpler solutions. This makes them highly… (see more) prone to learning spurious correlations in the training data, that may not hold at test time. In this work, we provide the first theoretical analysis of the effect of simplicity bias on learning spurious correlations. Notably, we show that examples with spurious features are provably separable based on the model's output early in training. We further illustrate that if spurious features have a small enough noise-to-signal ratio, the network's output on the majority of examples is almost exclusively determined by the spurious features, leading to poor worst-group test accuracy. Finally, we propose SPARE, which identifies spurious correlations early in training and utilizes importance sampling to alleviate their effect. Empirically, we demonstrate that SPARE outperforms state-of-the-art methods by up to 21.1% in worst-group accuracy, while being up to 12x faster. We also show that SPARE is a highly effective but lightweight method to discover spurious correlations.
2024-04-17
Proceedings of The 27th International Conference on Artificial Intelligence and Statistics (published)
doi.org
proceedings.mlr.press