Publications

Gap Minimization for Knowledge Sharing and Transfer

Boyu Wang

Jorge A. Mendez

Changjian Shui

Fan Zhou

Di Wu

Gezheng Xu

Christian Gagné

Eric R. Eaton

Learning from multiple related tasks by knowledge sharing and transfer has become increasingly relevant over the last two decades. In order … (voir plus)to successfully transfer information from one task to another, it is critical to understand the similarities and differences between the domains. In this paper, we introduce the notion of \emph{performance gap}, an intuitive and novel measure of the distance between learning tasks. Unlike existing measures which are used as tools to bound the difference of expected risks between tasks (e.g.,

General Purpose AI Systems in the AI Act: Trying to Fit a Square Peg Into a Round Hole

Claire Boine

David Rolnick

2023-01-01

SSRN Electronic Journal (publié)

Generating QM1B with PySCF$_{\text{IPU}}$

Alexander Mathiasen

Hatem Helal

Kerstin Klaser

Paul Balanca

Josef Dean

Carlo Luschi

Dominique Beaini

Andrew William Fitzgibbon

Dominic Masters

Generating QM1B with PySCFIPU

Alexander Mathiasen

Hatem Helal

Kerstin Klaser

Paul Balanca

Josef Dean

Carlo Luschi

Dominique Beaini

Andrew William Fitzgibbon

Dominic Masters

2023-01-01

NeurIPS (publié)

GEODESIC SINKHORN FOR FAST AND ACCURATE OPTIMAL TRANSPORT ON MANIFOLDS

Guillaume Huguet

Alexander Tong

María Ramos Zapatero

Christopher J. Tape

Guy Wolf

Smita Krishnaswamy

Efficient computation of optimal transport distance between distributions is of growing importance in data science. Sinkhorn-based methods a… (voir plus)re currently the state-of-the-art for such computations, but require O(n2) computations. In addition, Sinkhorn-based methods commonly use an Euclidean ground distance between datapoints. However, with the prevalence of manifold structured scientific data, it is often desirable to consider geodesic ground distance. Here, we tackle both issues by proposing Geodesic Sinkhorn—based on diffusing a heat kernel on a manifold graph. Notably, Geodesic Sinkhorn requires only O(n log n) computation, as we approximate the heat kernel with Chebyshev polynomials based on the sparse graph Laplacian. We apply our method to the computation of barycenters of several distributions of high dimensional single cell data from patient samples undergoing chemotherapy. In particular, we define the barycentric distance as the distance between two such barycenters. Using this definition, we identify an optimal transport distance and path associated with the effect of treatment on cellular data.

2023-01-01

2023 IEEE 33rd International Workshop on Machine Learning for Signal Processing (MLSP) (publié)

GFlowNet Foundations

Edward J. Hu

Mo Tiwari

GFlowNet Foundations

Edward J Hu

Mo Tiwari

Emmanuel Bengio

GFlowNets for AI-Driven Scientific Discovery

Moksh J. Jain

Tristan Deleu

Jason Hartford

Cheng-Hao Liu

Alex Hernandez-Garcia

Yoshua Bengio

Tackling the most pressing problems for humanity, such as the climate crisis and the threat of global pandemics, requires accelerating the p… (voir plus)ace of scientific discovery. While science has traditionally relied...

2023-01-01

Digital Discovery (publié)

GFlowOut: Dropout with Generative Flow Networks

Dianbo Liu

Moksh J. Jain

Bonaventure F. P. Dossou

Qianli Shen

Anirudh Goyal

Xu Ji

Kenji Kawaguchi

Yoshua Bengio

2023-01-01

ICML (publié)

GFlowOut: Dropout with Generative Flow Networks

Dianbo Liu

Moksh J. Jain

Bonaventure F. P. Dossou

Qianli Shen

Anirudh Goyal

Xu Ji

Kenji Kawaguchi

Yoshua Bengio

2023-01-01

ICML (publié)

GitHub Copilot AI pair programmer: Asset or Liability?

Arghavan Moradi Dakhel

Vahid Majdinasab

Amin Nikanjam

Foutse Khomh

Michel C. Desmarais

Z. Jiang

Automatic program synthesis is a long-lasting dream in software engineering. Recently, a promising Deep Learning (DL) based solution, called… (voir plus) Copilot, has been proposed by OpenAI and Microsoft as an industrial product. Although some studies evaluate the correctness of Copilot solutions and report its issues, more empirical evaluations are necessary to understand how developers can benefit from it effectively. In this paper, we study the capabilities of Copilot in two different programming tasks: (i) generating (and reproducing) correct and efficient solutions for fundamental algorithmic problems, and (ii) comparing Copilot's proposed solutions with those of human programmers on a set of programming tasks. For the former, we assess the performance and functionality of Copilot in solving selected fundamental problems in computer science, like sorting and implementing data structures. In the latter, a dataset of programming problems with human-provided solutions is used. The results show that Copilot is capable of providing solutions for almost all fundamental algorithmic problems, however, some solutions are buggy and non-reproducible. Moreover, Copilot has some difficulties in combining multiple methods to generate a solution. Comparing Copilot to humans, our results show that the correct ratio of humans' solutions is greater than Copilot's suggestions, while the buggy solutions generated by Copilot require less effort to be repaired.

2023-01-01

J. Syst. Softw. (publié)