AI Paper Atlas

Research map / Learning theory and algorithms / Matrix and tensor methods

Scalable Robust Matrix Factorization with Nonconvex Loss

Quanming Yao, James Kwok

NeurIPS 2018 · Learning theory and algorithms › Matrix and tensor methods · approach: Nonconvex low-rank and sparse optimization · 5 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 nonconvex LSP loss rather than the convex loss in RMF-MMMatrix factorization · Synthetic data, m=250, m=500, and m=1000RMSE: 0.194$\pm$0.032 -> 0.110$\pm$0.004; 0.145$\pm$0.009 -> 0.073$\pm$0.001; 0.122$\pm$0.004 -> 0.047$\pm$0.002Improved
Use nonconvex LSP loss rather than the convex loss in RMF-MMMatrix factorization · MovieLens-100KRMSE: 0.901$\pm$0.003 -> 0.885$\pm$0.006Improved
Use nonconvex LSP loss rather than the convex loss in RMF-MMMatrix factorization · MovieLens-1M and MovieLens-10MRMSEImproved
Use nonconvex LSP loss rather than the convex loss in RMF-MM(heuristic)Matrix factorization · Dinosaur D1, D2, and D3MAE: 0.374$\pm$0.031 -> 0.323$\pm$0.012; 0.381$\pm$0.022 -> 0.332$\pm$0.005; 0.382$\pm$0.034 -> 0.316$\pm$0.006Improved
Exploit data sparsity in surrogate optimization (ablation)RMFNL · Synthetic m=1000CPU time: 490.1$\pm$91.9 -> 24.6$\pm$3.2Improved
Replace APG with LADMPSAP for surrogate optimization (ablation)RMFNL · Synthetic m=1000CPU time: 24.6$\pm$3.2 -> 950.8$\pm$138.8Hurt
Replace APG with APG(dense) for surrogate optimization (ablation)RMFNL · Synthetic m=1000RMSE: 0.45$\pm$0.006 -> 0.45$\pm$0.007No clear effect
Replace LSP loss with Geman or Laplace loss (ablation)RMFNL · Synthetic data and MovieLensRMSENo clear effect
Gradually increase the diagonal entries of the surrogate weighting matrices (ablation)RMF-MM · Dinosaur D1, D2, and D3MAE: 0.442$\pm$0.096 -> 0.374$\pm$0.031; 0.458$\pm$0.043 -> 0.381$\pm$0.022; 0.466$\pm$0.072 -> 0.382$\pm$0.034Improved

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