37 citations · 77 across the 8 of their papers we have counts for
8 papers
Symmetric Single Index Learning
Aaron Zweig, Joan Bruna
Few neural architectures lend themselves to provable learning with gradient based methods. One popular model is the single-index model, in which labels are produced by composing an…
On Single Index Models beyond Gaussian Data
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 perfo…
Towards Antisymmetric Neural Ansatz Separation
Aaron Zweig, Joan Bruna
We study separations between two fundamental models (or \emph{Ansätze}) of antisymmetric functions, that is, functions of the form $f(x_{σ(1)}, \ldots, x_{σ(N)}) = \text{sign}(…
Exponential Separations in Symmetric Neural Networks
Aaron Zweig, Joan Bruna
In this work we demonstrate a novel separation between symmetric neural network architectures. Specifically, we consider the Relational Network~\parencite{santoro2017simple} archit…
A Functional Perspective on Learning Symmetric Functions with Neural Networks
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. These archi…
Provably Efficient Third-Person Imitation from Offline Observation
Aaron Zweig, Joan Bruna
Domain adaptation in imitation learning represents an essential step towards improving generalizability. However, even in the restricted setting of third-person imitation where tra…
Stochastic Optimization of Sorting Networks via Continuous Relaxations
Aditya Grover, Eric Wang, Aaron Zweig +1
Sorting input objects is an important step in many machine learning pipelines. However, the sorting operator is non-differentiable with respect to its inputs, which prohibits end-t…
Graphite: Iterative Generative Modeling of Graphs
Aditya Grover, Aaron Zweig, Stefano Ermon
Graphs are a fundamental abstraction for modeling relational data. However, graphs are discrete and combinatorial in nature, and learning representations suitable for machine learn…