Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Caballero, Ethan"'
Autor:
Caballero, Ethan
Le principe d’invariance par rapport à la causalité est au coeur d’approches notables telles que la minimisation du risque invariant (IRM) qui cherchent à résoudre les échecs de généralisation hors distribution (OOD). Malgré la théorie p
Externí odkaz:
http://hdl.handle.net/1866/27473
Publikováno v:
International Conference on Learning Representations (ICLR), 2023
We present a smoothly broken power law functional form (that we refer to as a Broken Neural Scaling Law (BNSL)) that accurately models & extrapolates the scaling behaviors of deep neural networks (i.e. how the evaluation metric of interest varies as
Externí odkaz:
http://arxiv.org/abs/2210.14891
Empirical science of neural scaling laws is a rapidly growing area of significant importance to the future of machine learning, particularly in the light of recent breakthroughs achieved by large-scale pre-trained models such as GPT-3, CLIP and DALL-
Externí odkaz:
http://arxiv.org/abs/2110.06990
Autor:
Ahuja, Kartik, Caballero, Ethan, Zhang, Dinghuai, Gagnon-Audet, Jean-Christophe, Bengio, Yoshua, Mitliagkas, Ioannis, Rish, Irina
The invariance principle from causality is at the heart of notable approaches such as invariant risk minimization (IRM) that seek to address out-of-distribution (OOD) generalization failures. Despite the promising theory, invariance principle-based a
Externí odkaz:
http://arxiv.org/abs/2106.06607
Autor:
Dziugaite, Gintare Karolina, Drouin, Alexandre, Neal, Brady, Rajkumar, Nitarshan, Caballero, Ethan, Wang, Linbo, Mitliagkas, Ioannis, Roy, Daniel M.
One of the principal scientific challenges in deep learning is explaining generalization, i.e., why the particular way the community now trains networks to achieve small training error also leads to small error on held-out data from the same populati
Externí odkaz:
http://arxiv.org/abs/2010.11924
Autor:
Krueger, David, Caballero, Ethan, Jacobsen, Joern-Henrik, Zhang, Amy, Binas, Jonathan, Zhang, Dinghuai, Priol, Remi Le, Courville, Aaron
Distributional shift is one of the major obstacles when transferring machine learning prediction systems from the lab to the real world. To tackle this problem, we assume that variation across training domains is representative of the variation we mi
Externí odkaz:
http://arxiv.org/abs/2003.00688
Autor:
Caballero, Ethan
Question Answering (QA) is fundamental to natural language processing in that most nlp problems can be phrased as QA (Kumar et al., 2015). Current weakly supervised memory network models that have been proposed so far struggle at answering questions
Externí odkaz:
http://arxiv.org/abs/1511.06420