3 papers
cs.LG2026
Localising Dropout Variance in Twin Networks
Cooper Doyle
Accurate individual treatment-effect estimation demands not only reliable point predictions but also uncertainty measures that help practitioners \emph{locate} the source of model…
cs.LG2026
Learning Adapter Rank via Symmetry Breaking
Cooper Doyle, Andy Hu, Rebecca Chan +1
Low-rank adaptation is effective partly because downstream updates lie in a low-dimensional subspace, but the latent rank coordinates of LoRA are not identifiable: any invertible r…
cs.CL2025
Your Absorbing Discrete Diffusion Secretly Models the Bayesian Posterior
Cooper Doyle
Discrete diffusion language models learn to reconstruct text from randomly masked inputs, yet under mild assumptions their denoiser already implements the exact Bayesian posterior…