Publications

Beyond Gaussian Noise: A Generalized Approach to Likelihood Analysis with non-Gaussian Noise
Ronan Legin
Alexandre Adam
Yashar Hezaveh
Laurence Perreault Levasseur
Likelihood analysis is typically limited to normally distributed noise due to the difficulty of determining the probability density function… (see more) of complex, high-dimensional, non-Gaussian, and anisotropic noise. This is a major limitation for precision measurements in many domains of science, including astrophysics, for example, for the analysis of the Cosmic Microwave Background, gravitational waves, gravitational lensing, and exoplanets. This work presents Score-based LIkelihood Characterization (SLIC), a framework that resolves this issue by building a data-driven noise model using a set of noise realizations from observations. We show that the approach produces unbiased and precise likelihoods even in the presence of highly non-Gaussian correlated and spatially varying noise. We use diffusion generative models to estimate the gradient of the probability density of noise with respect to data elements. In combination with the Jacobian of the physical model of the signal, we use Langevin sampling to produce independent samples from the unbiased likelihood. We demonstrate the effectiveness of the method using real data from the Hubble Space Telescope and James Webb Space Telescope.
2023-06-05
Astrophysical Journal Letters (published)
doi.org
arxiv.org
A Functional Data Perspective and Baseline On Multi-Layer Out-of-Distribution Detection
Eduardo Dadalto Câmara Gomes
Pierre Colombo
Guillaume Staerman
Nathan Noiry
Pablo Piantanida
2023-06-05
ArXiv (preprint)
doi.org
arxiv.org
Robust Scuba Diver Tracking and Recovery in Open Water Using YOLOv7, SORT, and Spiral Search
Faraz Lotfi
Khalil Virji
Gregory Dudek
Target tracking is a classic problem in computer vision, with numerous applications in robotics. However, tracking targets underwater presen… (see more)ts additional complications due to the six degrees of freedom nature of the problem and the challenging visual environment. In this paper, we address the problem of robotic underwater tracking of scuba divers by partitioning it into two parts: vision and control. We propose a new approach that exploits a highly-maneuverable underwater robot to perform experiments in open water, coupling sensing and control for improved performance. To evaluate the temporal stability of different tracking paradigms, we introduce a new metric, frame-to-frame vari-ance, which is better suited to assess the smoothness of detections from the vision side. We implement PID controllers for control and a spiral search algorithm for target recovery in case of a tracking failure. Our approach only uses observations in the image plane, eliminating the need for robot localization or camera calibration. Using a tracking-by-detection paradigm that combines YOLOv7 for target detection, a tuned filtering technique for temporal stability, and a spiral search algorithm for target recovery, we demonstrate promising performance for long-term tracking. We evaluate our proposed paradigm on the VDD-C dataset and deploy it on an underwater robot for several experiments in open water. Our outcomes show consistency with the ones in the initial studies, and the spiral search algorithm demonstrates promising performance for recapturing a target after a tracking failure. Our approach delivers promising performance for robust underwater tracking, achieving successful open-water tracking scenarios in the presence of strong water currents.
2023-06-05
2023 20th Conference on Robots and Vision (CRV) (published)
doi.org
The Stack: 3 TB of permissively licensed source code
Denis Kocetkov
Raymond Li
Loubna Ben allal
Jia LI
Chenghao Mou
Carlos Muñoz Ferrandis
Yacine Jernite
Margaret Mitchell
Sean Hughes
Thomas Wolf
Dzmitry Bahdanau
Leandro Von Werra
Harm de Vries
Large Language Models (LLMs) play an ever-increasing role in the field of Artificial Intelligence (AI)--not only for natural language proces… (see more)sing but also for code understanding and generation. To stimulate open and responsible research on LLMs for code, we introduce The Stack, a 3.1 TB dataset consisting of permissively licensed source code in 30 programming languages. We describe how we collect the full dataset, construct a permissively licensed subset, present a data governance plan, discuss limitations, and show promising results on text2code benchmarks by training 350M-parameter decoders on different Python subsets. We find that (1) near-deduplicating the data significantly boosts performance across all experiments, and (2) it is possible to match previously reported HumanEval and MBPP performance using only permissively licensed data. We make the dataset available at https://hf.co/BigCode, provide a tool called"Am I in The Stack"(https://hf.co/spaces/bigcode/in-the-stack) for developers to search The Stack for copies of their code, and provide a process for code to be removed from the dataset by following the instructions at https://www.bigcode-project.org/docs/about/the-stack/.
2023-06-05
TMLR (accepted)
doi.org
openreview.net
AHA!: Facilitating AI Impact Assessment by Generating Examples of Harms
Zana Buçinca
Chau Minh Pham
Maurice Jakesch
Marco Túlio Ribeiro
A.R. Olteanu
Saleema Amershi
While demands for change and accountability for harmful AI consequences mount, foreseeing the downstream effects of deploying AI systems rem… (see more)ains a challenging task. We developed AHA! (Anticipating Harms of AI), a generative framework to assist AI practitioners and decision-makers in anticipating potential harms and unintended consequences of AI systems prior to development or deployment. Given an AI deployment scenario, AHA! generates descriptions of possible harms for different stakeholders. To do so, AHA! systematically considers the interplay between common problematic AI behaviors as well as their potential impacts on different stakeholders, and narrates these conditions through vignettes. These vignettes are then filled in with descriptions of possible harms by prompting crowd workers and large language models. By examining 4113 harms surfaced by AHA! for five different AI deployment scenarios, we found that AHA! generates meaningful examples of harms, with different problematic AI behaviors resulting in different types of harms. Prompting both crowds and a large language model with the vignettes resulted in more diverse examples of harms than those generated by either the crowd or the model alone. To gauge AHA!'s potential practical utility, we also conducted semi-structured interviews with responsible AI professionals (N=9). Participants found AHA!'s systematic approach to surfacing harms important for ethical reflection and discovered meaningful stakeholders and harms they believed they would not have thought of otherwise. Participants, however, differed in their opinions about whether AHA! should be used upfront or as a secondary-check and noted that AHA! may shift harm anticipation from an ideation problem to a potentially demanding review problem. Drawing on our results, we discuss design implications of building tools to help practitioners envision possible harms.
2023-06-04
ArXiv (preprint)
doi.org
arxiv.org
GUILGET: GUI Layout GEneration with Transformer
Andrey Sobolevsky
Guillaume-Alexandre Bilodeau
Jinghui Cheng
Jin L.C. Guo
2023-06-04
Proceedings of the Canadian Conference on Artificial Intelligence (published)
doi.org
arxiv.org
High-Throughput Edge Inference for BERT Models via Neural Architecture Search and Pipeline.
Hung-Yang Chang
Seyyed Hasan Mozafari
James J. Clark
Brett H. Meyer
Warren J. Gross
There has been growing interest in improving the BERT inference throughput on resource-constrained edge devices for a satisfactory user expe… (see more)rience. One methodology is to employ heterogeneous computing, which utilizes multiple processing elements to accelerate inference. Another methodology is to deploy Neural Architecture Search (NAS) to find optimal solutions in accuracy-throughput design space. In this paper, for the first time, we incorporate NAS with pipelining for BERT models. We show that performing NAS with pipelining achieves on average 53% higher throughput, compared to NAS with a homogeneous system. Additionally, we propose a NAS algorithm that incorporates hardware performance feedback to accelerate the NAS process. Our proposed NAS algorithm speeds up the search process by ~4x, and 5.5x on the design space of the BERT and CNNs, respectively. Also, by exploring the accuracy-throughput design space of BERT models, we demonstrate that performing pipelining then NAS (Pipeline-then-NAS) can lead to solutions with up to 9x higher inference throughput, compared to running homogeneous inference on the BERT-base model, with only a 1.3% decrease in accuracy.
2023-06-04
Proceedings of the Great Lakes Symposium on VLSI 2023 (published)
doi.org
PAC-Bayesian Learning of Aggregated Binary Activated Neural Networks with Probabilities over Representations
Louis Fortier-Dubois
Gaël Letarte
Benjamin Leblanc
Franccois Laviolette
Pascal Germain
2023-06-04
Proceedings of the Canadian Conference on Artificial Intelligence (published)
doi.org
arxiv.org
Spatial variations in aromatic hydrocarbon emission in a dust-rich galaxy
Justin S. Spilker
Kedar A. Phadke
Manuel Aravena
Melanie Archipley
Matthew B. Bayliss
Jack E. Birkin
Matthieu Bethermin
James Burgoyne
Jared Cathey
Scott C. Chapman
Hakon Dahle
Anthony H. Gonzalez
Gayathri Gururajan
Christopher C. Hayward
Yashar D. Hezaveh
Ryley Hill
Taylor A. Hutchison
Keunho J. Kim
Seonwoo Kim
David Law … (see 18 more)
Ronan Legin
Matthew A. Malkan
Daniel P. Marrone
Eric J. Murphy
Desika Narayanan
Alex Navarre
Grace M. Olivier
Jeffrey A. Rich
Jane R. Rigby
Cassie Reuter
James E. Rhoads
Keren Sharon
J. D. T. Smith
Manuel Solimano
Nikolaus Sulzenauer
Joaquin D. Vieira
Axel Weiss
Katherine E. Whitaker
Dust grains absorb half of the radiation emitted by stars throughout the history of the universe, re-emitting this energy at infrared wavele… (see more)ngths. Polycyclic aromatic hydrocarbons (PAHs) are large organic molecules that trace millimeter-size dust grains and regulate the cooling of the interstellar gas within galaxies. Observations of PAH features in very distant galaxies have been difficult due to the limited sensitivity and wavelength coverage of previous infrared telescopes. Here we present JWST observations that detect the 3.3um PAH feature in a galaxy observed less than 1.5 billion years after the Big Bang. The high equivalent width of the PAH feature indicates that star formation, rather than black hole accretion, dominates the infrared emission throughout the galaxy. The light from PAH molecules, large dust grains, and stars and hot dust are spatially distinct from one another, leading to order-of-magnitude variations in the PAH equivalent width and the ratio of PAH to total infrared luminosity across the galaxy. The spatial variations we observe suggest either a physical offset between the PAHs and large dust grains or wide variations in the local ultraviolet radiation field. Our observations demonstrate that differences in the emission from PAH molecules and large dust grains are a complex result of localized processes within early galaxies.
2023-06-04
Nature (published)
doi.org
arxiv.org
Dialogue System with Missing Observation
Djallel Bouneffouf
Mayank Agarwal
Irina Rish
Within the domain of dialogue, the ability to orchestrate multiple independently trained dialogue agents to create a unified system is of pa… (see more)rticular importance. Where we define orchestration as the task of selecting a subset of skills which most appropriately answer a user input using features extracted from both the user input and the individual skills. In this work, we study the task of online dialogue orchestration where the user feedback associated with the dialogue agent may not always be observed. In order to address the missing feedback setting, we propose to combine the attentive contextual bandit approach with an unsupervised learning mechanism such as clustering. By leveraging clustering to estimate missing reward, we are able to learn from each incoming event, even those with missing rewards. Promising empirical results are obtained on proprietary conversational datasets.
2023-06-03
ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (published)
doi.org
Evaluation of Categorical Generative Models - Bridging the Gap Between Real and Synthetic Data
Florence Regol
Anja Kroon
Mark J. Coates
The machine learning community has mainly relied on real data to benchmark algorithms as it provides compelling evidence of model applicabil… (see more)ity. Evaluation on synthetic datasets can be a powerful tool to provide a better understanding of a model’s strengths, weaknesses and overall capabilities. Gaining these insights can be particularly important for generative modeling as the target quantity is completely unknown. Multiple issues related to the evaluation of generative models have been reported in the literature. We argue those problems can be avoided by an evaluation based on ground truth. General criticisms of synthetic experiments are that they are too simplified and not representative of practical scenarios. As such, our experimental setting is tailored to a realistic generative task. We focus on categorical data and introduce an appropriately scalable evaluation method. Our method involves tasking a generative model to learn a distribution in a high-dimensional setting. We then successively bin the large space to obtain smaller probability spaces where meaningful statistical tests can be applied. We consider increasingly large probability spaces, which correspond to increasingly difficult modeling tasks, and compare the generative models based on the highest task difficulty they can reach before being detected as being too far from the ground truth. We validate our evaluation procedure with synthetic experiments on both synthetic generative models and current state-of-the-art categorical generative models.
2023-06-03
ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (published)
doi.org
arxiv.org
Fine-Tuning Strategies for Faster Inference Using Speech Self-Supervised Models: A Comparative Study
Salah Zaiem
Robin Algayres
Titouan Parcollet
Slim Essid
Mirco Ravanelli
Self-supervised learning (SSL) has allowed substantial progress in Automatic Speech Recognition (ASR) performance in low-resource settings. … (see more)In this context, it has been demonstrated that larger self-supervised feature extractors are crucial for achieving lower downstream ASR error rates. Thus, better performance might be sanctioned with longer inferences. This article explores different approaches that may be deployed during the fine-tuning to reduce the computations needed in the SSL encoder, leading to faster inferences. We adapt a number of existing techniques to common ASR settings and benchmark them, displaying performance drops and gains in inference times. Interestingly, we found that given enough downstream data, a simple downsampling of the input sequences outperforms the other methods with both low performance drops and high computational savings, reducing computations by 61.3% with an WER increase of only 0.81. Finally, we analyze the robustness of the comparison to changes in dataset conditions, revealing sensitivity to dataset size.
2023-06-03
2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW) (published)
doi.org
arxiv.org