AI Paper Atlas

Research map / Learning theory and algorithms / Combinatorial and search optimization

DB-KSVD: Scalable Alternating Optimization for Disentangling High-Dimensional Embedding Spaces

Romeo Valentin, Sydney Michelle Katz, Vincent Vanhoucke, Mykel Kochenderfer

ICML 2026 · Learning theory and algorithms › Combinatorial and search optimization · approach: Constrained neural network optimization · 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 DB-KSVD instead of classic KSVD (scalable matching pursuit, batched updates, Lanczos)KSVD · Gemma-2-2B embeddings, 2.6M samples, m=4096, k=20runtime to converge: over 30 days -> approximately 8 minutesImproved
add Matryoshka structuring to DB-KSVD (ablation)DB-KSVD · Gemma-2-2B SAEBench (m=4096)autointerpretability and absorptionImproved
add Matryoshka structuring to DB-KSVD (ablation)DB-KSVD · Gemma-2-2B SAEBench (m=4096)loss recovered and SCRHurt
add Matryoshka structuring to DB-KSVD (ablation)DB-KSVD · Gemma-2-2B dictionaries (m=4096)dictionary coherenceImproved
use DB-KSVD instead of Standard ReLU SAEGemma-2-2B dictionary (m=4096) · SAEBenchSAEBench metricsMixed
use DB-KSVD instead of SAE on DINOv2-Bdictionary learning · DINOv2-B ImageNet-1k, k=32sparse probing accuracy: 0.932 -> 0.893Hurt
use DB-KSVD instead of SAE on DINOv2-Bdictionary learning · DINOv2-B ImageNet-1k, k=32variance explained: 0.794 -> 0.817Improved
offload matrix products to GPU (CPU+GPU vs CPU only) (ablation)DB-KSVD · Gemma-2-2B, m=4096, k=20runtime (s): 5.47 -> 11.43Hurt
increase sparsity k from 40 to 80 at small dictionary size (ablation)DB-KSVD (CPU) · Gemma-2-2B, m=4096runtime (s): 10.86 -> 337.63Hurt

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