7 papers
Deep Minds and Shallow Probes
Su Hyeong Lee, Risi Kondor
Neural representations are not unique objects. Even when two systems realize the same downstream computation, their hidden coordinates may differ by reparameterization. A probe fam…
Probabilistic Modeling of Latent Agentic Substructures in Deep Neural Networks
Su Hyeong Lee, Risi Kondor, Richard Ngo
We develop a theory of intelligent agency grounded in probabilistic modeling for neural models. Agents are represented as outcome distributions with epistemic utility given by log…
P-Tensors: a General Formalism for Constructing Higher Order Message Passing Networks
Andrew Hands, Tianyi Sun, Risi Kondor
Several recent papers have proposed increasing the expressive power of graph neural networks by exploiting subgraphs or other topological structures. In parallel, researchers have…
Toward Super-polynomial Quantum Speedup of Equivariant Quantum Algorithms with SU() Symmetry
Han Zheng, Zimu Li, Sergii Strelchuk +2
We introduce a framework of the equivariant convolutional quantum algorithms which is tailored for a number of machine-learning tasks on physical systems with arbitrary SU sym…
A Geometric Approach to Steerable Convolutions
Soumyabrata Kundu, Risi Kondor
In contrast to the somewhat abstract, group theoretical approach adopted by many papers, our work provides a new and more intuitive derivation of steerable convolutional neural net…
Steerable Transformers for Volumetric Data
Soumyabrata Kundu, Risi Kondor
We introduce Steerable Transformers, an extension of the Vision Transformer mechanism that maintains equivariance to the special Euclidean group . We propose an equ…