Portrait de Gavin McCracken n'est pas disponible

Gavin McCracken

Alumni

Publications

Unifying Mechanistic Interpretations of Neural Networks Trained on Modular Addition
Gabriela Moisescu-Pareja
Gavin McCracken
Vincent Létourneau
Doina Precup
Jonathan Love
2025-09-22
NeurIPS.cc/2025/Workshop/WiML (publié)
openreview.net
openreview.net
Uncovering a Universal Abstract Algorithm for Modular Addition in Neural Networks
Gavin McCracken
Gabriela Moisescu-Pareja
Vincent Létourneau
Doina Precup
Jonathan Love
We propose a testable universality hypothesis, asserting that seemingly disparate neural network solutions observed in the simple task of mo… (voir plus)dular addition are unified under a common abstract algorithm. While prior work interpreted variations in neuron-level representations as evidence for distinct algorithms, we demonstrate - through multi-level analyses spanning neurons, neuron clusters, and entire networks - that multilayer perceptrons and transformers universally implement the abstract algorithm we call the approximate Chinese Remainder Theorem. Crucially, we introduce approximate cosets and show that neurons activate exclusively on them. Furthermore, our theory works for deep neural networks (DNNs). It predicts that universally learned solutions in DNNs with trainable embeddings or more than one hidden layer require only O(log n) features, a result we empirically confirm. This work thus provides the first theory-backed interpretation of multilayer networks solving modular addition. It advances generalizable interpretability and opens a testable universality hypothesis for group multiplication beyond modular addition.
2025-05-23
ArXiv (prépublication)
arxiv.org
arxiv.org
Uncovering a Universal Abstract Algorithm for Modular Addition in Neural Networks
Gavin McCracken
Gabriela Moisescu-Pareja
Vincent Létourneau
Doina Precup
Jonathan Love
We propose a testable universality hypothesis, asserting that seemingly disparate neural network solutions observed in the simple task of mo… (voir plus)dular addition are unified under a common abstract algorithm. While prior work interpreted variations in neuron-level representations as evidence for distinct algorithms, we demonstrate - through multi-level analyses spanning neurons, neuron clusters, and entire networks - that multilayer perceptrons and transformers universally implement the abstract algorithm we call the approximate Chinese Remainder Theorem. Crucially, we introduce approximate cosets and show that neurons activate exclusively on them. Furthermore, our theory works for deep neural networks (DNNs). It predicts that universally learned solutions in DNNs with trainable embeddings or more than one hidden layer require only O(log n) features, a result we empirically confirm. This work thus provides the first theory-backed interpretation of multilayer networks solving modular addition. It advances generalizable interpretability and opens a testable universality hypothesis for group multiplication beyond modular addition.
2025-05-01
arXiv (publié)
doi.org
arxiv.org
A Study of Policy Gradient on a Class of Exactly Solvable Models
Gavin McCracken
Colin Daniels
Rosie Zhao
Anna M. Brandenberger
Prakash Panangaden
Doina Precup
Policy gradient methods are extensively used in reinforcement learning as a way to optimize expected return. In this paper, we explore the e… (voir plus)volution of the policy parameters, for a special class of exactly solvable POMDPs, as a continuous-state Markov chain, whose transition probabilities are determined by the gradient of the distribution of the policy's value. Our approach relies heavily on random walk theory, specifically on affine Weyl groups. We construct a class of novel partially observable environments with controllable exploration difficulty, in which the value distribution, and hence the policy parameter evolution, can be derived analytically. Using these environments, we analyze the probabilistic convergence of policy gradient to different local maxima of the value function. To our knowledge, this is the first approach developed to analytically compute the landscape of policy gradient in POMDPs for a class of such environments, leading to interesting insights into the difficulty of this problem.
2020-11-03
ArXiv (prépublication)
arxiv.org
arxiv.org