5 papers
Accelerating Speculative Diffusions via Block Verification
Alexander Soen, Hisham Husain, Valentin De Bortoli +1
Speculative decoding speeds up LLM inference by using a draft model to generate tokens, with an acceptance-rejection scheme that ensures that the output matches the target distribu…
Density-Ratio Losses for Post-Hoc Learning to Defer
Alexander Soen, Ragnar Thobaben, Joakim Jaldén +1
We study post-hoc Learning to Defer (L2D) through the lens of ideal distributions: divergence-regularized reweightings of the data distribution under which a model attains low loss…
A Connection Between Learning to Reject and Bhattacharyya Divergences
Alexander Soen
Learning to reject provide a learning paradigm which allows for our models to abstain from making predictions. One way to learn the rejector is to learn an ideal marginal distribut…
Rejection via Learning Density Ratios
Alexander Soen, Hisham Husain, Philip Schulz +1
Classification with rejection emerges as a learning paradigm which allows models to abstain from making predictions. The predominant approach is to alter the supervised learning pi…
Domain Adaptation and Entanglement: an Optimal Transport Perspective
Okan Koç, Alexander Soen, Chao-Kai Chiang +1
Current machine learning systems are brittle in the face of distribution shifts (DS), where the target distribution that the system is tested on differs from the source distributio…