6 papers
FaithformBench: Benchmarking Faithfulness of Mathematical Chain-of-Thought Autoformalisation
Rob Cornish, Iacopo Ghinassi, Po-Hung Yeh +7
Autoformalisation (AF) systems map natural language reasoning steps into formal statements in a proof assistant such as Lean. We consider how to assess the faithfulness of these sy…
Equivariant Reinforcement Learning for Clifford Quantum Circuit Synthesis
Richie Yeung, Aleks Kissinger, Rob Cornish
We consider the problem of synthesizing Clifford quantum circuits for devices with all-to-all qubit connectivity. We approach this task as a reinforcement learning problem in which…
A categorical account of the Metropolis-Hastings algorithm
Rob Cornish, Andi Q. Wang
Metropolis-Hastings (MH) is a foundational Markov chain Monte Carlo (MCMC) algorithm. In this paper, we ask whether it is possible to formulate and analyse MH in terms of categoric…
Neural Network Symmetrisation in Concrete Settings
Rob Cornish
Cornish (2024) recently gave a general theory of neural network symmetrisation in the abstract context of Markov categories. We give a high-level overview of these results, and the…
SymDiff: Equivariant Diffusion via Stochastic Symmetrisation
Leo Zhang, Kianoosh Ashouritaklimi, Yee Whye Teh +1
We propose SymDiff, a method for constructing equivariant diffusion models using the framework of stochastic symmetrisation. SymDiff resembles a learned data augmentation that is d…
Stochastic Neural Network Symmetrisation in Markov Categories
Rob Cornish
We consider the problem of symmetrising a neural network along a group homomorphism: given a homomorphism , we would like a procedure that converts -equivariant neur…