AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

Kernel Identification Through Transformers

Fergus Simpson, Ian Davies, Vidhi Lalchand, Alessandro Vullo, Nicolas Durrande, Carl Edward Rasmussen

NeurIPS 2021 · Architectures and efficiency › Attention and transformers · approach: Token merging and masked pretraining · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use KITT rather than AHGP for kernel selectionGaussian Process regression · UCI regression tasksnegative predictive log likelihoodImproved
Use KITT rather than greedy Automatic Statistician tree searchGaussian Process regression · UCI regression tasksnegative predictive log likelihoodNo clear effect
Use KITT instead of random selection from the kernel vocabulary (ablation)KITT · UCI regression tasksnegative predictive log likelihoodImproved
Incorporate higher-order products beyond products of two primitive kernels (ablation)KITT kernel vocabulary · Kernel recommendationperformanceNo clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy