6 papers
Prediction-Powered Active Testing
Kianoosh Ashouritaklimi, Valentin Kilian, Daolang Huang +2
Active testing provides a label--efficient approach to risk estimation by adaptively selecting which test points should be labelled. However, existing estimators fail to exploit th…
Robust Bayes-Assisted Conformal Prediction
Kianoosh Ashouritaklimi, Stefano Cortinovis, François Caron
Bayes-assisted conformal prediction combines the strengths of Bayesian modelling with exact, distribution-free frequentist coverage guarantees. Although conformal validity is prese…
Masked Language Flow Models
Iskander Azangulov, Kianoosh Ashouritaklimi, Leo Zhang +2
Masked Diffusion Models (MDMs) promise fast, parallel language generation, but their reverse transition factorises across token positions -- an approximation that breaks down in th…
Variance-Tilted Diffusion Models for Diverse Sampling
Iskander Azangulov, Leo Zhang, Kianoosh Ashouritaklimi
Diffusion models are typically sampled independently, even when the downstream objective is to obtain a diverse set of candidates. We introduce a variance-weighted batch distributi…
Active Learning with Task-Driven Representations for Messy Pools
Kianoosh Ashouritaklimi, Tom Rainforth
Active learning has the potential to be especially useful for messy, uncurated pools where datapoints vary in relevance to the target task. However, state-of-the-art approaches to…
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…