Timezone: »
Talk
Equivariance Through Parameter-Sharing
Siamak Ravanbakhsh · Jeff Schneider · Barnabás Póczos
We propose to study equivariance in deep neural networks through parameter symmetries. In particular, given a group G that acts discretely on the input and output of a standard neural network layer, we show that its equivariance is linked to the symmetry group of network parameters. We then propose two parameter-sharing scheme to induce the desirable symmetry on the parameters of the neural network. Under some conditions on the action of G, our procedure for tying the parameters achieves G-equivariance and guarantees sensitivity to all other permutation groups outside of G.
Author Information
Siamak Ravanbakhsh (Carnegie Mellon University)
Jeff Schneider (CMU/Uber)
Barnabás Póczos (CMU)
Related Events (a corresponding poster, oral, or spotlight)
-
2017 Poster: Equivariance Through Parameter-Sharing »
Mon. Aug 7th 08:30 AM -- 12:00 PM Room Gallery #40
More from the Same Authors
-
2022 : Galaxies on graph neural networks: towards robust synthetic galaxy catalogs with deep generative models »
Yesukhei Jagvaral · Rachel Mandelbaum · Francois Lanusse · Siamak Ravanbakhsh · Sukhdeep Singh · Duncan Campbell -
2023 : Lie Point Symmetry and Physics Informed Networks »
Tara Akhound-Sadegh · Laurence Perreault-Levasseur · Johannes Brandstetter · Max Welling · Siamak Ravanbakhsh -
2023 Poster: Equivariance with Learned Canonicalization Functions »
Sékou-Oumar Kaba · Arnab Kumar Mondal · Yan Zhang · Yoshua Bengio · Siamak Ravanbakhsh -
2022 : Q/A: Jeff Schneider »
Jeff Schneider -
2022 : Invited Speaker: Jeff Schneider »
Jeff Schneider -
2022 : Jeff Schneider »
Jeff Schneider -
2022 Poster: EqR: Equivariant Representations for Data-Efficient Reinforcement Learning »
Arnab Kumar Mondal · Vineet Jain · Kaleem Siddiqi · Siamak Ravanbakhsh -
2022 Poster: Utility Theory for Sequential Decision Making »
Mehran Shakerinava · Siamak Ravanbakhsh -
2022 Poster: Addressing Optimism Bias in Sequence Modeling for Reinforcement Learning »
Adam Villaflor · Zhe Huang · Swapnil Pande · John Dolan · Jeff Schneider -
2022 Spotlight: Utility Theory for Sequential Decision Making »
Mehran Shakerinava · Siamak Ravanbakhsh -
2022 Spotlight: Addressing Optimism Bias in Sequence Modeling for Reinforcement Learning »
Adam Villaflor · Zhe Huang · Swapnil Pande · John Dolan · Jeff Schneider -
2022 Spotlight: EqR: Equivariant Representations for Data-Efficient Reinforcement Learning »
Arnab Kumar Mondal · Vineet Jain · Kaleem Siddiqi · Siamak Ravanbakhsh -
2021 Poster: Equivariant Networks for Pixelized Spheres »
Mehran Shakerinava · Siamak Ravanbakhsh -
2021 Spotlight: Equivariant Networks for Pixelized Spheres »
Mehran Shakerinava · Siamak Ravanbakhsh -
2020 Poster: Universal Equivariant Multilayer Perceptrons »
Siamak Ravanbakhsh -
2020 Poster: VideoOneNet: Bidirectional Convolutional Recurrent OneNet with Trainable Data Steps for Video Processing »
Zoltán Á. Milacski · Barnabás Póczos · Andras Lorincz -
2019 Poster: Myopic Posterior Sampling for Adaptive Goal Oriented Design of Experiments »
Kirthevasan Kandasamy · Willie Neiswanger · Reed Zhang · Akshay Krishnamurthy · Jeff Schneider · Barnabás Póczos -
2019 Oral: Myopic Posterior Sampling for Adaptive Goal Oriented Design of Experiments »
Kirthevasan Kandasamy · Willie Neiswanger · Reed Zhang · Akshay Krishnamurthy · Jeff Schneider · Barnabás Póczos -
2018 Poster: Transformation Autoregressive Networks »
Junier Oliva · Kumar Avinava Dubey · Manzil Zaheer · Barnabás Póczos · Ruslan Salakhutdinov · Eric Xing · Jeff Schneider -
2018 Oral: Transformation Autoregressive Networks »
Junier Oliva · Kumar Avinava Dubey · Manzil Zaheer · Barnabás Póczos · Ruslan Salakhutdinov · Eric Xing · Jeff Schneider -
2018 Poster: Gradient Descent Learns One-hidden-layer CNN: Don't be Afraid of Spurious Local Minima »
Simon Du · Jason Lee · Yuandong Tian · Aarti Singh · Barnabás Póczos -
2018 Oral: Gradient Descent Learns One-hidden-layer CNN: Don't be Afraid of Spurious Local Minima »
Simon Du · Jason Lee · Yuandong Tian · Aarti Singh · Barnabás Póczos -
2017 Poster: Multi-fidelity Bayesian Optimisation with Continuous Approximations »
kirthevasan kandasamy · Gautam Dasarathy · Barnabás Póczos · Jeff Schneider -
2017 Talk: Multi-fidelity Bayesian Optimisation with Continuous Approximations »
kirthevasan kandasamy · Gautam Dasarathy · Barnabás Póczos · Jeff Schneider -
2017 Poster: The Statistical Recurrent Unit »
Junier Oliva · Barnabás Póczos · Jeff Schneider -
2017 Poster: Nonparanormal Information Estimation »
Shashank Singh · Barnabás Póczos -
2017 Talk: Nonparanormal Information Estimation »
Shashank Singh · Barnabás Póczos -
2017 Talk: The Statistical Recurrent Unit »
Junier Oliva · Barnabás Póczos · Jeff Schneider