233 citations · 531 across the 32 of their papers we have counts for
9 papers · 1 filter
Exact Dynamics and Finite-Sample Trajectory Recovery of Linear Recursive Feature Machines
Andrew Cheng, Bobak T. Kiani, Yue M. Lu +1
Recursive feature machines (RFMs) learn representations of data by alternating between fitting a predictor to a dataset and updating features of that predictor using the average gr…
Unitary convolutions for learning on graphs and groups
Bobak T. Kiani, Lukas Fesser, Melanie Weber
Data with geometric structure is ubiquitous in machine learning often arising from fundamental symmetries in a domain, such as permutation-invariance in graphs and translation-inva…
Hardness of Learning Neural Networks under the Manifold Hypothesis
Bobak T. Kiani, Jason Wang, Melanie Weber
The manifold hypothesis presumes that high-dimensional data lies on or near a low-dimensional manifold. While the utility of encoding geometric structure has been demonstrated empi…
On the hardness of learning under symmetries
Bobak T. Kiani, Thien Le, Hannah Lawrence +2
We study the problem of learning equivariant neural networks via gradient descent. The incorporation of known symmetries ("equivariance") into neural nets has empirically improved…
Self-Supervised Learning with Lie Symmetries for Partial Differential Equations
Grégoire Mialon, Quentin Garrido, Hannah Lawrence +3
Machine learning for differential equations paves the way for computationally efficient alternatives to numerical solvers, with potentially broad impacts in science and engineering…
Equivariant Polynomials for Graph Neural Networks
Omri Puny, Derek Lim, Bobak T. Kiani +2
Graph Neural Networks (GNN) are inherently limited in their expressive power. Recent seminal works (Xu et al., 2019; Morris et al., 2019b) introduced the Weisfeiler-Lehman (WL) hie…
Joint Embedding Self-Supervised Learning in the Kernel Regime
Bobak T. Kiani, Randall Balestriero, Yubei Chen +2
The fundamental goal of self-supervised learning (SSL) is to produce useful representations of data without access to any labels for classifying the data. Modern methods in SSL, wh…
projUNN: efficient method for training deep networks with unitary matrices
Bobak Kiani, Randall Balestriero, Yann LeCun +1
In learning with recurrent or very deep feed-forward networks, employing unitary matrices in each layer can be very effective at maintaining long-range stability. However, restrict…
Implicit Bias of Linear Equivariant Networks
Hannah Lawrence, Kristian Georgiev, Andrew Dienes +1
Group equivariant convolutional neural networks (G-CNNs) are generalizations of convolutional neural networks (CNNs) which excel in a wide range of technical applications by explic…