AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

Gradient-Based Diversity Optimization with Differentiable Top-$k$ Objective

Tianyi Zhou, Sebastian Dalleiger, Ece Calikus, Aristides Gionis

ICLR 2026 · Architectures and efficiency › Pruning and efficient tuning · approach: Low-rank compression and merging · 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
fine-tune NMF with DDT (direct diversity objective)NMF · Yahoo-R2diversity: 0.09 -> 0.98Improved
fine-tune NMF with DDTNMF · MovieLensdiversity: 0.62 -> 1.00Improved
fine-tune NMF with DDTNMF · Netflixrelevance: 0.88 -> 0.97Improved
add MDR implicit reweightingNMF · Netflixdiversity: 0.84 -> 0.98Improved
use DDT instead of post-hoc DPP rerankingNMF · Yahoo-R2relevance: 0.58 -> 0.85Improved
use DDT instead of DGRecDGRec · KuaiRecrelevance: 0.18 -> 0.95Improved
use DDT instead of MDR with neural network model (ablation)NCF · MovieLens/NetflixdiversityImproved
vary static beta toward diversity (lower beta) (ablation)DDT/MDR · Netflix, MovieLensrecallNo clear effect
use adaptive beta instead of static (ablation)DDT · MovieLens (NCF)relevance and diversityImproved
fine-tune pretrained model instead of training from scratch (ablation)NCF · MovieLensrelevanceImproved
apply DDT with k=10 on Yahoo-R2 (NMF)NMF · Yahoo-R2in-objective diversity gain: 77.4 (8.7)Improved
apply DDT to NMF on Coat for items k+1~2kNMF · Coatout-of-objective diversity gain: -0.5 (4.7) at k=5No 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