Zobrazeno 1 - 10
of 32
pro vyhledávání: '"Marcotte, Étienne"'
Autor:
Williams, Andrew Robert, Ashok, Arjun, Marcotte, Étienne, Zantedeschi, Valentina, Subramanian, Jithendaraa, Riachi, Roland, Requeima, James, Lacoste, Alexandre, Rish, Irina, Chapados, Nicolas, Drouin, Alexandre
Forecasting is a critical task in decision making across various domains. While numerical data provides a foundation, it often lacks crucial context necessary for accurate predictions. Human forecasters frequently rely on additional information, such
Externí odkaz:
http://arxiv.org/abs/2410.18959
Autor:
Monteiro, Joao, Noel, Pierre-Andre, Marcotte, Etienne, Rajeswar, Sai, Zantedeschi, Valentina, Vazquez, David, Chapados, Nicolas, Pal, Christopher, Taslakian, Perouz
Large Language Models (LLMs) are trained on vast amounts of data, most of which is automatically scraped from the internet. This data includes encyclopedic documents that harbor a vast amount of general knowledge (e.g., Wikipedia) but also potentiall
Externí odkaz:
http://arxiv.org/abs/2406.11811
Autor:
Monteiro, João, Marcotte, Étienne, Noël, Pierre-André, Zantedeschi, Valentina, Vázquez, David, Chapados, Nicolas, Pal, Christopher, Taslakian, Perouz
In-context learning (ICL) approaches typically leverage prompting to condition decoder-only language model generation on reference information. Just-in-time processing of a context is inefficient due to the quadratic cost of self-attention operations
Externí odkaz:
http://arxiv.org/abs/2404.15420
Autor:
Ashok, Arjun, Marcotte, Étienne, Zantedeschi, Valentina, Chapados, Nicolas, Drouin, Alexandre
We introduce a new model for multivariate probabilistic time series prediction, designed to flexibly address a range of tasks including forecasting, interpolation, and their combinations. Building on copula theory, we propose a simplified objective f
Externí odkaz:
http://arxiv.org/abs/2310.01327
Multivariate probabilistic time series forecasts are commonly evaluated via proper scoring rules, i.e., functions that are minimal in expectation for the ground-truth distribution. However, this property is not sufficient to guarantee good discrimina
Externí odkaz:
http://arxiv.org/abs/2304.09836
The estimation of time-varying quantities is a fundamental component of decision making in fields such as healthcare and finance. However, the practical utility of such estimates is limited by how accurately they quantify predictive uncertainty. In t
Externí odkaz:
http://arxiv.org/abs/2202.03528
Publikováno v:
Phys. Rev. E 88, 062151 (2013)
We generate and study an ensemble of isostatic jammed hard-sphere lattices. These lattices are obtained by compression of a periodic system with an adaptive unit cell containing a single sphere until the point of mechanical stability. We present deta
Externí odkaz:
http://arxiv.org/abs/1310.5971
Autor:
Marcotte, Étienne, Torquato, Salvatore
Finding the densest sphere packing in $d$-dimensional Euclidean space $\mathbb{R}^d$ is an outstanding fundamental problem with relevance in many fields, including the ground states of molecular systems, colloidal crystal structures, coding theory, d
Externí odkaz:
http://arxiv.org/abs/1304.5003