Timezone: »
Despite their overwhelming capacity to overfit, deep learning architectures tend to generalize relatively well to unseen data, allowing them to be deployed in practice. However, explaining why this is the case is still an open area of research. One standing hypothesis that is gaining popularity, e.g. \citet{hochreiter1997flat, keskar2016large}, is that the flatness of minima of the loss function found by stochastic gradient based methods results in good generalization. This paper argues that most notions of flatness are problematic for deep models and can not be directly applied to explain generalization. Specifically, when focusing on deep networks with rectifier units, we can exploit the particular geometry of parameter space induced by the inherent symmetries that these architectures exhibit to build equivalent models corresponding to arbitrarily sharper minima. Or, depending on the definition of flatness, it is the same for any given minimum. Furthermore, if we allow to reparametrize a function, the geometry of its parameters can change drastically without affecting its generalization properties.
Author Information
Laurent Dinh (University of Montreal)
Razvan Pascanu (DeepMind)
Samy Bengio (Google Brain)
Yoshua Bengio (U. Montreal)
Yoshua Bengio is recognized as one of the world’s leading experts in artificial intelligence and a pioneer in deep learning. Since 1993, he has been a professor in the Department of Computer Science and Operational Research at the Université de Montréal. He is the founder and scientific director of Mila, the Quebec Institute of Artificial Intelligence, the world’s largest university-based research group in deep learning. He is a member of the NeurIPS board and co-founder and general chair for the ICLR conference, as well as program director of the CIFAR program on Learning in Machines and Brains and is Fellow of the same institution. In 2018, Yoshua Bengio ranked as the computer scientist with the most new citations, worldwide, thanks to his many publications. In 2019, he received the ACM A.M. Turing Award, “the Nobel Prize of Computing”, jointly with Geoffrey Hinton and Yann LeCun for conceptual and engineering breakthroughs that have made deep neural networks a critical component of computing. In 2020 he was nominated Fellow of the Royal Society of London.
Related Events (a corresponding poster, oral, or spotlight)
-
2017 Poster: Sharp Minima Can Generalize For Deep Nets »
Tue Aug 8th 08:30 AM -- 12:00 PM Room Gallery
More from the Same Authors
-
2020 Workshop: Workshop on Continual Learning »
Haytham Fayek · Arslan Chaudhry · David Lopez-Paz · Eugene Belilovsky · Jonathan Schwarz · Marc Pickett · Rahaf Aljundi · Sayna Ebrahimi · Razvan Pascanu · Puneet Dokania -
2020 Poster: Stabilizing Transformers for Reinforcement Learning »
Emilio Parisotto · Francis Song · Jack Rae · Razvan Pascanu · Caglar Gulcehre · Siddhant Jayakumar · Max Jaderberg · Raphael Lopez Kaufman · Aidan Clark · Seb Noury · Matthew Botvinick · Nicolas Heess · Raia Hadsell -
2020 Poster: Improving the Gating Mechanism of Recurrent Neural Networks »
Albert Gu · Caglar Gulcehre · Thomas Paine · Matthew Hoffman · Razvan Pascanu -
2020 AffinityWorkshop: New In ML »
Zhen Xu · Sparkle Russell-Puleri · Zhengying Liu · Sinead A Williamson · Matthias W Seeger · Wei-Wei Tu · Samy Bengio · Isabelle Guyon -
2019 Workshop: Identifying and Understanding Deep Learning Phenomena »
Hanie Sedghi · Samy Bengio · Kenji Hata · Aleksander Madry · Ari Morcos · Behnam Neyshabur · Maithra Raghu · Ali Rahimi · Ludwig Schmidt · Ying Xiao -
2019 Poster: State-Reification Networks: Improving Generalization by Modeling the Distribution of Hidden Representations »
Alex Lamb · Jonathan Binas · Anirudh Goyal · Sandeep Subramanian · Ioannis Mitliagkas · Yoshua Bengio · Michael Mozer -
2019 Poster: On the Spectral Bias of Neural Networks »
Nasim Rahaman · Aristide Baratin · Devansh Arpit · Felix Draxler · Min Lin · Fred Hamprecht · Yoshua Bengio · Aaron Courville -
2019 Oral: On the Spectral Bias of Neural Networks »
Nasim Rahaman · Aristide Baratin · Devansh Arpit · Felix Draxler · Min Lin · Fred Hamprecht · Yoshua Bengio · Aaron Courville -
2019 Oral: State-Reification Networks: Improving Generalization by Modeling the Distribution of Hidden Representations »
Alex Lamb · Jonathan Binas · Anirudh Goyal · Sandeep Subramanian · Ioannis Mitliagkas · Yoshua Bengio · Michael Mozer -
2019 Poster: Area Attention »
Yang Li · Lukasz Kaiser · Samy Bengio · Si Si -
2019 Poster: Manifold Mixup: Better Representations by Interpolating Hidden States »
Vikas Verma · Alex Lamb · Christopher Beckham · Amir Najafi · Ioannis Mitliagkas · David Lopez-Paz · Yoshua Bengio -
2019 Poster: GMNN: Graph Markov Neural Networks »
Meng Qu · Yoshua Bengio · Jian Tang -
2019 Oral: Area Attention »
Yang Li · Lukasz Kaiser · Samy Bengio · Si Si -
2019 Oral: GMNN: Graph Markov Neural Networks »
Meng Qu · Yoshua Bengio · Jian Tang -
2019 Oral: Manifold Mixup: Better Representations by Interpolating Hidden States »
Vikas Verma · Alex Lamb · Christopher Beckham · Amir Najafi · Ioannis Mitliagkas · David Lopez-Paz · Yoshua Bengio -
2018 Poster: Progress & Compress: A scalable framework for continual learning »
Jonathan Schwarz · Wojciech Czarnecki · Jelena Luketina · Agnieszka Grabska-Barwinska · Yee Teh · Razvan Pascanu · Raia Hadsell -
2018 Poster: Mix & Match - Agent Curricula for Reinforcement Learning »
Wojciech Czarnecki · Siddhant Jayakumar · Max Jaderberg · Leonard Hasenclever · Yee Teh · Nicolas Heess · Simon Osindero · Razvan Pascanu -
2018 Poster: Mutual Information Neural Estimation »
Mohamed Belghazi · Aristide Baratin · Sai Rajeswar · Sherjil Ozair · Yoshua Bengio · R Devon Hjelm · Aaron Courville -
2018 Oral: Progress & Compress: A scalable framework for continual learning »
Jonathan Schwarz · Wojciech Czarnecki · Jelena Luketina · Agnieszka Grabska-Barwinska · Yee Teh · Razvan Pascanu · Raia Hadsell -
2018 Oral: Mix & Match - Agent Curricula for Reinforcement Learning »
Wojciech Czarnecki · Siddhant Jayakumar · Max Jaderberg · Leonard Hasenclever · Yee Teh · Nicolas Heess · Simon Osindero · Razvan Pascanu -
2018 Oral: Mutual Information Neural Estimation »
Mohamed Belghazi · Aristide Baratin · Sai Rajeswar · Sherjil Ozair · Yoshua Bengio · R Devon Hjelm · Aaron Courville -
2018 Poster: Focused Hierarchical RNNs for Conditional Sequence Processing »
Rosemary Nan Ke · Konrad Zolna · Alessandro Sordoni · Zhouhan Lin · Adam Trischler · Yoshua Bengio · Joelle Pineau · Laurent Charlin · Christopher Pal -
2018 Poster: Fast Decoding in Sequence Models Using Discrete Latent Variables »
Lukasz Kaiser · Samy Bengio · Aurko Roy · Ashish Vaswani · Niki Parmar · Jakob Uszkoreit · Noam Shazeer -
2018 Oral: Fast Decoding in Sequence Models Using Discrete Latent Variables »
Lukasz Kaiser · Samy Bengio · Aurko Roy · Ashish Vaswani · Niki Parmar · Jakob Uszkoreit · Noam Shazeer -
2018 Oral: Focused Hierarchical RNNs for Conditional Sequence Processing »
Rosemary Nan Ke · Konrad Zolna · Alessandro Sordoni · Zhouhan Lin · Adam Trischler · Yoshua Bengio · Joelle Pineau · Laurent Charlin · Christopher Pal -
2018 Poster: Been There, Done That: Meta-Learning with Episodic Recall »
Samuel Ritter · Jane Wang · Zeb Kurth-Nelson · Siddhant Jayakumar · Charles Blundell · Razvan Pascanu · Matthew Botvinick -
2018 Oral: Been There, Done That: Meta-Learning with Episodic Recall »
Samuel Ritter · Jane Wang · Zeb Kurth-Nelson · Siddhant Jayakumar · Charles Blundell · Razvan Pascanu · Matthew Botvinick -
2017 Workshop: Reproducibility in Machine Learning Research »
Rosemary Nan Ke · Anirudh Goyal · Alex Lamb · Joelle Pineau · Samy Bengio · Yoshua Bengio -
2017 Poster: Device Placement Optimization with Reinforcement Learning »
Azalia Mirhoseini · Hieu Pham · Quoc Le · benoit steiner · Mohammad Norouzi · Rasmus Larsen · Yuefeng Zhou · Naveen Kumar · Samy Bengio · Jeff Dean -
2017 Talk: Device Placement Optimization with Reinforcement Learning »
Azalia Mirhoseini · Hieu Pham · Quoc Le · benoit steiner · Mohammad Norouzi · Rasmus Larsen · Yuefeng Zhou · Naveen Kumar · Samy Bengio · Jeff Dean -
2017 Poster: A Closer Look at Memorization in Deep Networks »
David Krueger · Yoshua Bengio · Stanislaw Jastrzebski · Maxinder S. Kanwal · Nicolas Ballas · Asja Fischer · Emmanuel Bengio · Devansh Arpit · Tegan Maharaj · Aaron Courville · Simon Lacoste-Julien -
2017 Talk: A Closer Look at Memorization in Deep Networks »
David Krueger · Yoshua Bengio · Stanislaw Jastrzebski · Maxinder S. Kanwal · Nicolas Ballas · Asja Fischer · Emmanuel Bengio · Devansh Arpit · Tegan Maharaj · Aaron Courville · Simon Lacoste-Julien