Robin Walters
(he/him)
Assistant Professor
Research interests
- Deep learning
- Equivariant neural networks
- Representation theory
- Algebraic geometry
Education
- PhD in Mathematics, University of Chicago
- AB in Mathematics, Harvard University
Biography
Robin Walters is an assistant professor in the Khoury College of Computer Sciences at Northeastern University, based in Boston.
Walters’ research focuses on the role of symmetry in deep learning. By exploring ways of building a problem’s symmetry into a deep learning model as hard mathematical constraints, Walters has discovered it’s possible to improve not just that model’s data efficiency, but its generalization and trustworthiness as well. Now, as director of the Geometric Learning Lab, Walters is pushing the limits of these methods, making use of approximate symmetry and exploring everything from the theory of underlying symmetry in neural network structure to the subject’s range of practical applications.
Walters also brings his background as a mathematician into the classroom, where he teaches computational theory. He enjoys watching his students develop the ability to think rigorously and communicate clearly about the complex topic, and he particularly enjoys mentoring graduate students. Walters is a visiting fellow at the Boston Dynamics AI Institute, where he develops equivariant neural networks for sample efficient robot perception and manipulation.
In his free time, Walters enjoys sailing, hiking, swimming, playing board games, and spending time with his partner, Angela, and two children, Sidney and Sally.
Recent publications
-
Improving Convergence and Generalization Using Parameter Symmetries
Citation: Bo Zhao, Robert M. Gower, Robin Walters , Rose Yu. (2024). Improving Convergence and Generalization Using Parameter Symmetries ICLR. https://openreview.net/forum?id=L0r0GphlIL -
Discovering Symmetry Breaking in Physical Systems with Relaxed Group Convolution
Citation: Rui Wang , Elyssa F. Hofgard, Hang Gao , Robin Walters , Tess E. Smidt. (2024). Discovering Symmetry Breaking in Physical Systems with Relaxed Group Convolution ICML. https://openreview.net/forum?id=59oXyDTLJv -
Latent Space Symmetry Discovery
Citation: Jianke Yang, Nima Dehmamy, Robin Walters , Rose Yu. (2024). Latent Space Symmetry Discovery ICML. https://openreview.net/forum?id=qstt2OguvM -
Fourier Transporter: Bi-Equivariant Robotic Manipulation in 3D
Citation: Haojie Huang, Owen Howell, Dian Wang , Xupeng Zhu, Robert Platt , Robin Walters . (2024). Fourier Transporter: Bi-Equivariant Robotic Manipulation in 3D ICLR. https://openreview.net/forum?id=UulwvAU1W0 -
SEIL: Simulation-augmented Equivariant Imitation Learning
Citation: Mingxi Jia, Dian Wang , Guanang Su, David Klee, Xupeng Zhu, Robin Walters, Robert Platt. (2023). SEIL: Simulation-augmented Equivariant Imitation Learning ICRA, 1845-1851. https://doi.org/10.1109/ICRA48891.2023.10161252 -
Edge Grasp Network: A Graph-Based SE(3)-invariant Approach to Grasp Detection
Citation: Haojie Huang, Dian Wang , Xupeng Zhu, Robin Walters, Robert Platt. (2023). Edge Grasp Network: A Graph-Based SE(3)-invariant Approach to Grasp Detection ICRA, 3882-3888. https://doi.org/10.1109/ICRA48891.2023.10160728 -
Image to Sphere: Learning Equivariant Features for Efficient Pose Prediction
Citation: David Klee, Ondrej Biza, Robert Platt, Robin Walters. (2023). Image to Sphere: Learning Equivariant Features for Efficient Pose Prediction ICLR. https://openreview.net/pdf?id=_2bDpAtr7PI -
Generative Adversarial Symmetry Discovery
Citation: Jianke Yang, Robin Walters, Nima Dehmamy, Rose Yu. (2023). Generative Adversarial Symmetry Discovery CoRR, abs/2302.00236. https://doi.org/10.48550/arXiv.2302.00236 -
Symmetries, Flat Minima, and the Conserved Quantities of Gradient Flow
Citation: Bo Zhao, Iordan Ganev, Robin Walters, Rose Yu, Nima Dehmamy. (2023). Symmetries, Flat Minima, and the Conserved Quantities of Gradient Flow ICLR. https://openreview.net/pdf?id=9ZpciCOunFb -
The Surprising Effectiveness of Equivariant Models in Domains with Latent Symmetry
Citation: Dian Wang , Jung Yeon Park, Neel Sortur, Lawson L. S. Wong, Robin Walters, Robert Platt. (2023). The Surprising Effectiveness of Equivariant Models in Domains with Latent Symmetry ICLR. https://openreview.net/pdf?id=P4MUGRM4Acu -
Integrating Symmetry into Differentiable Planning with Steerable Convolutions
Citation: Linfeng Zhao, Xupeng Zhu, Lingzhi Kong, Robin Walters, Lawson L. S. Wong. (2023). Integrating Symmetry into Differentiable Planning with Steerable Convolutions ICLR. https://openreview.net/pdf?id=n7CPzMPKQl -
Probabilistic Symmetry for Multi-Agent Dynamics
Citation: Sophia Huiwen Sun, Robin Walters, Jinxi Li, Rose Yu. (2023). Probabilistic Symmetry for Multi-Agent Dynamics L4DC, 1231-1244. https://proceedings.mlr.press/v211/sun23a.html -
Trajectory Prediction using Equivariant Continuous Convolution
Citation: Walters, R.*, Li, J.*, Yu R. (2021). Trajectory Prediction using Equivariant Continuous Convolution. International Conference on Learning Representations (ICLR).