publications

2023

  1. Symmetric Single Index Learning
    Aaron Zweig, and Joan Bruna
    arXiv preprint arXiv:2310.02117, 2023
    arXiv
  2. On Single-Index Models beyond Gaussian Data
    Aaron Zweig, Loucas Pillaud-Vivien, and Joan Bruna
    In Thirty-seventh Conference on Neural Information Processing Systems, 2023
    arXiv

2022

  1. Towards Antisymmetric Neural Ansatz Separation
    Aaron Zweig, and Joan Bruna
    arXiv preprint arXiv:2208.03264, 2022
    arXiv
  2. Exponential separations in symmetric neural networks
    Aaron Zweig, and Joan Bruna
    Advances in Neural Information Processing Systems, 2022
    arXiv

2021

  1. A functional perspective on learning symmetric functions with neural networks
    Aaron Zweig, and Joan Bruna
    In International Conference on Machine Learning, 2021
    arXiv

2020

  1. Neural algorithms for graph navigation
    Aaron Zweig, Nesreen Ahmed, Theodore L Willke, and Guixiang Ma
    In Learning Meets Combinatorial Algorithms at NeurIPS2020, 2020
  2. Provably efficient third-person imitation from offline observation
    Aaron Zweig, and Joan Bruna
    In Conference on Uncertainty in Artificial Intelligence, 2020
    arXiv

2019

  1. Graphite: Iterative generative modeling of graphs
    Aditya Grover, Aaron Zweig, and Stefano Ermon
    In International conference on machine learning, 2019
    arXiv

2018

  1. Stochastic Optimization of Sorting Networks via Continuous Relaxations
    Aditya Grover, Eric Wang, Aaron Zweig, and Stefano Ermon
    In International Conference on Learning Representations, 2018
    arXiv