Timezone: »
We propose a new approach to the problem of neural network expressivity, which seeks to characterize how structural properties of a neural network family affect the functions it is able to compute. Our approach is based on an interrelated set of measures of expressivity, unified by the novel notion of trajectory length, which measures how the output of a network changes as the input sweeps along a one-dimensional path. Our findings show that: (1) The complexity of the computed function grows exponentially with depth (2) All weights are not equal: trained networks are more sensitive to their lower (initial) layer weights (3) Trajectory regularization is a simpler alternative to batch normalization, with the same performance.
Author Information
Maithra Raghu (Google Brain / Cornell University)
Ben Poole (Stanford University)
Surya Ganguli (Stanford)
Jon Kleinberg (Cornell University)
Jascha Sohl-Dickstein (Google Brain)
Related Events (a corresponding poster, oral, or spotlight)
-
2017 Poster: On the Expressive Power of Deep Neural Networks »
Mon. Aug 7th 08:30 AM -- 12:00 PM Room Gallery #110
More from the Same Authors
-
2022 : Pre-Training on a Data Diet: Identifying Sufficient Examples for Early Training »
Mansheej Paul · Brett Larsen · Surya Ganguli · Jonathan Frankle · Gintare Karolina Dziugaite -
2023 : A strong implicit bias in SGD dynamics towards much simpler subnetworks through stochastic collapse to invariant sets, Surya Ganguli »
Surya Ganguli -
2022 : How Neural Networks See, Learn and Forget »
Maithra Raghu -
2022 Workshop: Knowledge Retrieval and Language Models »
Maithra Raghu · Urvashi Khandelwal · Chiyuan Zhang · Matei Zaharia · Alexander Rush -
2022 Poster: Fast Finite Width Neural Tangent Kernel »
Roman Novak · Jascha Sohl-Dickstein · Samuel Schoenholz -
2022 Spotlight: Fast Finite Width Neural Tangent Kernel »
Roman Novak · Jascha Sohl-Dickstein · Samuel Schoenholz -
2022 Poster: Wide Bayesian neural networks have a simple weight posterior: theory and accelerated sampling »
Jiri Hron · Roman Novak · Jeffrey Pennington · Jascha Sohl-Dickstein -
2022 Spotlight: Wide Bayesian neural networks have a simple weight posterior: theory and accelerated sampling »
Jiri Hron · Roman Novak · Jeffrey Pennington · Jascha Sohl-Dickstein -
2021 Poster: Understanding self-supervised learning dynamics without contrastive pairs »
Yuandong Tian · Xinlei Chen · Surya Ganguli -
2021 Poster: A theory of high dimensional regression with arbitrary correlations between input features and target functions: sample complexity, multiple descent curves and a hierarchy of phase transitions »
Gabriel Mel · Surya Ganguli -
2021 Spotlight: A theory of high dimensional regression with arbitrary correlations between input features and target functions: sample complexity, multiple descent curves and a hierarchy of phase transitions »
Gabriel Mel · Surya Ganguli -
2021 Oral: Understanding self-supervised learning dynamics without contrastive pairs »
Yuandong Tian · Xinlei Chen · Surya Ganguli -
2021 Poster: Whitening and Second Order Optimization Both Make Information in the Dataset Unusable During Training, and Can Reduce or Prevent Generalization »
Neha Wadia · Daniel Duckworth · Samuel Schoenholz · Ethan Dyer · Jascha Sohl-Dickstein -
2021 Poster: Unbiased Gradient Estimation in Unrolled Computation Graphs with Persistent Evolution Strategies »
Paul Vicol · Luke Metz · Jascha Sohl-Dickstein -
2021 Spotlight: Whitening and Second Order Optimization Both Make Information in the Dataset Unusable During Training, and Can Reduce or Prevent Generalization »
Neha Wadia · Daniel Duckworth · Samuel Schoenholz · Ethan Dyer · Jascha Sohl-Dickstein -
2021 Oral: Unbiased Gradient Estimation in Unrolled Computation Graphs with Persistent Evolution Strategies »
Paul Vicol · Luke Metz · Jascha Sohl-Dickstein -
2020 Poster: Infinite attention: NNGP and NTK for deep attention networks »
Jiri Hron · Yasaman Bahri · Jascha Sohl-Dickstein · Roman Novak -
2020 Poster: Weakly-Supervised Disentanglement Without Compromises »
Francesco Locatello · Ben Poole · Gunnar Ratsch · Bernhard Schölkopf · Olivier Bachem · Michael Tschannen -
2020 Poster: Two Routes to Scalable Credit Assignment without Weight Symmetry »
Daniel Kunin · Aran Nayebi · Javier Sagastuy-Brena · Surya Ganguli · Jonathan Bloom · Daniel Yamins -
2020 Poster: On Implicit Regularization in $\beta$-VAEs »
Abhishek Kumar · Ben Poole -
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 discussion »
Roman Novak · Maxime Gabella · Frederic Dreyer · Siavash Golkar · Anh Tong · Irina Higgins · Mirco Milletari · Joe Antognini · Sebastian Goldt · Adín Ramírez Rivera · Roberto Bondesan · Ryo Karakida · Remi Tachet des Combes · Michael Mahoney · Nicholas Walker · Stanislav Fort · Samuel Smith · Rohan Ghosh · Aristide Baratin · Diego Granziol · Stephen Roberts · Dmitry Vetrov · Andrew Wilson · César Laurent · Valentin Thomas · Simon Lacoste-Julien · Dar Gilboa · Daniel Soudry · Anupam Gupta · Anirudh Goyal · Yoshua Bengio · Erich Elsen · Soham De · Stanislaw Jastrzebski · Charles H Martin · Samira Shabanian · Aaron Courville · Shorato Akaho · Lenka Zdeborova · Ethan Dyer · Maurice Weiler · Pim de Haan · Taco Cohen · Max Welling · Ping Luo · zhanglin peng · Nasim Rahaman · Loic Matthey · Danilo J. Rezende · Jaesik Choi · Kyle Cranmer · Lechao Xiao · Jaehoon Lee · Yasaman Bahri · Jeffrey Pennington · Greg Yang · Jiri Hron · Jascha Sohl-Dickstein · Guy Gur-Ari -
2019 : Understanding overparameterized neural networks »
Jascha Sohl-Dickstein -
2019 Workshop: Theoretical Physics for Deep Learning »
Jaehoon Lee · Jeffrey Pennington · Yasaman Bahri · Max Welling · Surya Ganguli · Joan Bruna -
2019 : Opening Remarks »
Jaehoon Lee · Jeffrey Pennington · Yasaman Bahri · Max Welling · Surya Ganguli · Joan Bruna -
2019 Poster: Understanding and correcting pathologies in the training of learned optimizers »
Luke Metz · Niru Maheswaranathan · Jeremy Nixon · Daniel Freeman · Jascha Sohl-Dickstein -
2019 Poster: Guided evolutionary strategies: augmenting random search with surrogate gradients »
Niru Maheswaranathan · Luke Metz · George Tucker · Dami Choi · Jascha Sohl-Dickstein -
2019 Poster: On Variational Bounds of Mutual Information »
Ben Poole · Sherjil Ozair · Aäron van den Oord · Alexander Alemi · George Tucker -
2019 Oral: Guided evolutionary strategies: augmenting random search with surrogate gradients »
Niru Maheswaranathan · Luke Metz · George Tucker · Dami Choi · Jascha Sohl-Dickstein -
2019 Oral: On Variational Bounds of Mutual Information »
Ben Poole · Sherjil Ozair · Aäron van den Oord · Alexander Alemi · George Tucker -
2019 Oral: Understanding and correcting pathologies in the training of learned optimizers »
Luke Metz · Niru Maheswaranathan · Jeremy Nixon · Daniel Freeman · Jascha Sohl-Dickstein -
2019 Poster: Direct Uncertainty Prediction for Medical Second Opinions »
Maithra Raghu · Katy Blumer · Rory sayres · Ziad Obermeyer · Bobby Kleinberg · Sendhil Mullainathan · Jon Kleinberg -
2019 Oral: Direct Uncertainty Prediction for Medical Second Opinions »
Maithra Raghu · Katy Blumer · Rory sayres · Ziad Obermeyer · Bobby Kleinberg · Sendhil Mullainathan · Jon Kleinberg -
2019 Poster: The Effect of Network Width on Stochastic Gradient Descent and Generalization: an Empirical Study »
Daniel Park · Jascha Sohl-Dickstein · Quoc Le · Samuel Smith -
2019 Oral: The Effect of Network Width on Stochastic Gradient Descent and Generalization: an Empirical Study »
Daniel Park · Jascha Sohl-Dickstein · Quoc Le · Samuel Smith -
2018 Poster: Can Deep Reinforcement Learning Solve Erdos-Selfridge-Spencer Games? »
Maithra Raghu · Alexander Irpan · Jacob Andreas · Bobby Kleinberg · Quoc Le · Jon Kleinberg -
2018 Oral: Can Deep Reinforcement Learning Solve Erdos-Selfridge-Spencer Games? »
Maithra Raghu · Alexander Irpan · Jacob Andreas · Bobby Kleinberg · Quoc Le · Jon Kleinberg -
2018 Poster: Dynamical Isometry and a Mean Field Theory of CNNs: How to Train 10,000-Layer Vanilla Convolutional Neural Networks »
Lechao Xiao · Yasaman Bahri · Jascha Sohl-Dickstein · Samuel Schoenholz · Jeffrey Pennington -
2018 Poster: Fixing a Broken ELBO »
Alexander Alemi · Ben Poole · Ian Fischer · Joshua V Dillon · Rif Saurous · Kevin Murphy -
2018 Oral: Dynamical Isometry and a Mean Field Theory of CNNs: How to Train 10,000-Layer Vanilla Convolutional Neural Networks »
Lechao Xiao · Yasaman Bahri · Jascha Sohl-Dickstein · Samuel Schoenholz · Jeffrey Pennington -
2018 Oral: Fixing a Broken ELBO »
Alexander Alemi · Ben Poole · Ian Fischer · Joshua V Dillon · Rif Saurous · Kevin Murphy -
2017 Poster: Continual Learning Through Synaptic Intelligence »
Friedemann Zenke · Ben Poole · Surya Ganguli -
2017 Poster: Input Switched Affine Networks: An RNN Architecture Designed for Interpretability »
Jakob Foerster · Justin Gilmer · Jan Chorowski · Jascha Sohl-Dickstein · David Sussillo -
2017 Poster: Learned Optimizers that Scale and Generalize »
Olga Wichrowska · Niru Maheswaranathan · Matthew Hoffman · Sergio Gómez Colmenarejo · Misha Denil · Nando de Freitas · Jascha Sohl-Dickstein -
2017 Talk: Input Switched Affine Networks: An RNN Architecture Designed for Interpretability »
Jakob Foerster · Justin Gilmer · Jan Chorowski · Jascha Sohl-Dickstein · David Sussillo -
2017 Talk: Continual Learning Through Synaptic Intelligence »
Friedemann Zenke · Ben Poole · Surya Ganguli -
2017 Talk: Learned Optimizers that Scale and Generalize »
Olga Wichrowska · Niru Maheswaranathan · Matthew Hoffman · Sergio Gómez Colmenarejo · Misha Denil · Nando de Freitas · Jascha Sohl-Dickstein