Search Results for author:
Found 8 papers, 5 papers with code
Hyperbolic Delaunay Geometric Alignment
Hyperbolic machine learning is an emerging field aimed at representing data with a hierarchical structure.
Harmonics of Learning: Universal Fourier Features Emerge in Invariant Networks
In this work, we formally prove that, under certain conditions, if a neural network is invariant to a finite group then its weights recover the Fourier transform on that group.
Neural Lattice Reduction: A Self-Supervised Geometric Deep Learning Approach
Lattice reduction is a combinatorial optimization problem aimed at finding the most orthogonal basis in a given lattice.
Learning Geometric Representations of Objects via Interaction
We address the problem of learning representations from observations of a scene involving an agent and an external object the agent interacts with.
Equivariant Representation Learning in the Presence of Stabilizers
We introduce Equivariant Isomorphic Networks (EquIN) -- a method for learning representations that are equivariant with respect to general group actions over data.
Back to the Manifold: Recovering from Out-of-Distribution States
However, a major challenge is a distributional shift between the states in the training dataset and the ones visited by the learned policy at the test time.
Equivariant Representation Learning via Class-Pose Decomposition
We introduce a general method for learning representations that are equivariant to symmetries of data.
Active Nearest Neighbor Regression Through Delaunay Refinement
We introduce an algorithm for active function approximation based on nearest neighbor regression.
