Giancarlo Kerg

Publication Activity (10 Years)

Years Active: 2018-2022
Publications (10 Years): 12

Top Topics

Optimization Strategies

Top Venues

Publications

Tristan Deleu, David Kanaa, Leo Feng, Giancarlo Kerg, Yoshua Bengio, Guillaume Lajoie, Pierre-Luc Bacon
Continuous-Time Meta-Learning with Forward Mode Differentiation. CoRR (2022)
Tristan Deleu, David Kanaa, Leo Feng, Giancarlo Kerg, Yoshua Bengio, Guillaume Lajoie, Pierre-Luc Bacon
Continuous-Time Meta-Learning with Forward Mode Differentiation. ICLR (2022)
Giancarlo Kerg, Sarthak Mittal, David Rolnick, Yoshua Bengio, Blake A. Richards, Guillaume Lajoie
On Neural Architecture Inductive Biases for Relational Tasks. CoRR (2022)
Stanislaw Jastrzebski, Devansh Arpit, Oliver Åstrand, Giancarlo Kerg, Huan Wang, Caiming Xiong, Richard Socher, Kyunghyun Cho, Krzysztof J. Geras
Catastrophic Fisher Explosion: Early Phase Fisher Matrix Impacts Generalization. ICML (2021)
Stanislaw Jastrzebski, Devansh Arpit, Oliver Åstrand, Giancarlo Kerg, Huan Wang, Caiming Xiong, Richard Socher, Kyunghyun Cho, Krzysztof J. Geras
Catastrophic Fisher Explosion: Early Phase Fisher Matrix Impacts Generalization. CoRR (2020)
Giancarlo Kerg, Bhargav Kanuparthi, Anirudh Goyal, Kyle Goyette, Yoshua Bengio, Guillaume Lajoie
Untangling tradeoffs between recurrence and self-attention in neural networks. CoRR (2020)
Victor Geadah, Giancarlo Kerg, Stefan Horoi, Guy Wolf, Guillaume Lajoie
Advantages of biologically-inspired adaptive neural activation in RNNs during learning. CoRR (2020)
Giancarlo Kerg, Bhargav Kanuparthi, Anirudh Goyal, Kyle Goyette, Yoshua Bengio, Guillaume Lajoie
Untangling tradeoffs between recurrence and self-attention in artificial neural networks. NeurIPS (2020)
Giancarlo Kerg, Kyle Goyette, Maximilian Puelma Touzel, Gauthier Gidel, Eugene Vorontsov, Yoshua Bengio, Guillaume Lajoie
Non-normal Recurrent Neural Network (nnRNN): learning long time dependencies while improving expressivity with transient dynamics. CoRR (2019)
Bhargav Kanuparthi, Devansh Arpit, Giancarlo Kerg, Nan Rosemary Ke, Ioannis Mitliagkas, Yoshua Bengio
h-detach: Modifying the LSTM Gradient Towards Better Optimization. ICLR (Poster) (2019)
Giancarlo Kerg, Kyle Goyette, Maximilian Puelma Touzel, Gauthier Gidel, Eugene Vorontsov, Yoshua Bengio, Guillaume Lajoie
Non-normal Recurrent Neural Network (nnRNN): learning long time dependencies while improving expressivity with transient dynamics. NeurIPS (2019)
Devansh Arpit, Bhargav Kanuparthi, Giancarlo Kerg, Nan Rosemary Ke, Ioannis Mitliagkas, Yoshua Bengio
h-detach: Modifying the LSTM Gradient Towards Better Optimization. CoRR (2018)