AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

Value Compression of Pattern Databases

Nathan Sturtevant, Ariel Felner, Malte Helmert

AAAI 2017 · Architectures and efficiency › Pruning and efficient tuning · approach: Joint pruning and quantization · 6 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
compress PDB 2x with VC (4 bits) instead of EC 2xIDA* with max of three 8-token PDBs · (18,4)-TopSpinnodes expanded: 7.11M -> 3.88MImproved
compress PDB 4x with VC (2 bits) instead of EC 4xIDA* with BPMX · (18,4)-TopSpinnodes expanded: 13.75M -> 10.39MImproved
compress 2x with VC to 4 bits versus no compressionIDA* with BPMX · (18,4)-TopSpinnodes expanded: 3.88M -> 3.88MNo clear effect
compress further to 3 bits (2.66x) with VCIDA* with BPMX · (18,4)-TopSpinnodes expanded: 3.88M -> 4.03MNo clear effect
compress to 2 bits (4x) with VC rather than 4 bitsIDA* with BPMX · (18,4)-TopSpinnodes expanded: 3.88M -> 10.39MHurt
remove BPMX (ablation)IDA* with VC 2-bit · (18,4)-TopSpinnodes expandedHurt
train VC on static distribution (4s) versus EC 2xIDA* · (18,2)-TopSpinnodes expanded: 416,014 -> 3,645,502Hurt
train VC on dynamic distribution (4d) instead of static (4s) (ablation)IDA* with VC 4 bits · (18,2)-TopSpinnodes expanded: 3,645,502 -> 684,846Improved
manually tuned range selection (4c) versus EC 2xIDA* with VC 4 bits · (18,2)-TopSpinnodes expanded: 416,014 -> 394,603Improved
compress 2x with VC instead of ECMM · (18,4)-TopSpinnodes expanded: 3.55M -> 2.07MImproved
compress 4x with VC (2 bits) instead of EC 4xMM · (18,4)-TopSpinnodes expanded: 5.42M -> 4.63MImproved
combine EC 2x and VC 2x instead of VC 4x alone at 0.25 memory (ablation)MM · (18,4)-TopSpinnodes expanded: 4.63M -> 3.55MImproved

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