Research map / Optimization / Optimizers
Expected Tensor Decomposition with Stochastic Gradient Descent
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 changed | Where | Measured | Effect |
|---|---|---|---|
| use second-order (block-diagonal Hessian) update, 2SGD/SALS instead of SGD | expected CP decomposition · synthetic 30x40x50 rank-5 tensor, fixed step 1/(1+t) | RMSE vs samples | Helped |
| use 2SGD/SALS with grid-searched step size instead of SGD, SLM, SCGD, SQN | expected CP decomposition · synthetic 30x40x50 rank-5 tensor | RMSE vs samples | Helped |
| cyclic update (SALS) instead of simultaneous update (2SGD) (ablation) | 2SGD · synthetic tensor | RMSE | No clear effect |
| stochastic SALS instead of full-tensor ALS | CP decomposition · Amazon reviews tensors | memory used: 118GB -> 6GB | Helped |
| SALS vs ALS late in convergence | CP decomposition · Amazon reviews tensors | convergence/loss | Mixed |
Closest papers by meaning
- Understanding Deflation Process in Over-parametrized Tensor Decomposition (NeurIPS 2021 · similarity 0.89)
- On Tensor Train Rank Minimization : Statistical Efficiency and Scalable Algorithm (NeurIPS 2017 · similarity 0.89)
- Beyond Lazy Training for Over-parameterized Tensor Decomposition (NeurIPS 2020 · similarity 0.89)
- Nonparametric Decomposition of Sparse Tensors (ICML 2021 · similarity 0.89)
- Fast Tensor Completion via Approximate Richardson Iteration (ICML 2025 · similarity 0.87)
- Efficient Leverage Score Sampling for Tensor Train Decomposition (NeurIPS 2024 · similarity 0.87)
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.