no code implementations • 3 Oct 2023 • Aaron Zweig, Joan Bruna
Learning this model with SGD is relatively well-understood, whereby the so-called information exponent of the link function governs a polynomial sample complexity rate.
no code implementations • 28 Jul 2023 • Joan Bruna, Loucas Pillaud-Vivien, Aaron Zweig
Sparse high-dimensional functions have arisen as a rich framework to study the behavior of gradient-descent methods using shallow neural networks, showcasing their ability to perform feature learning beyond linear models.
no code implementations • 5 Aug 2022 • Aaron Zweig, Joan Bruna
We study separations between two fundamental models (or \emph{Ans\"atze}) of antisymmetric functions, that is, functions $f$ of the form $f(x_{\sigma(1)}, \ldots, x_{\sigma(N)}) = \text{sign}(\sigma)f(x_1, \ldots, x_N)$, where $\sigma$ is any permutation.
no code implementations • 2 Jun 2022 • Aaron Zweig, Joan Bruna
In this work we demonstrate a novel separation between symmetric neural network architectures.
no code implementations • NeurIPS Workshop LMCA 2020 • Aaron Zweig, Nesreen Ahmed, Theodore L. Willke, Guixiang Ma
The application of deep reinforcement learning (RL) to graph learning and meta-learning admits challenges from both topics.
no code implementations • 16 Aug 2020 • Aaron Zweig, Joan Bruna
Symmetric functions, which take as input an unordered, fixed-size set, are known to be universally representable by neural networks that enforce permutation invariance.
no code implementations • 27 Feb 2020 • Aaron Zweig, Joan Bruna
Domain adaptation in imitation learning represents an essential step towards improving generalizability.
1 code implementation • ICLR 2019 • Aditya Grover, Eric Wang, Aaron Zweig, Stefano Ermon
Sorting input objects is an important step in many machine learning pipelines.
1 code implementation • 28 Mar 2018 • Aditya Grover, Aaron Zweig, Stefano Ermon
Graphs are a fundamental abstraction for modeling relational data.
Ranked #8 on Link Prediction on Citeseer