Research map / Optimization / Implicit bias and generalization
Understanding Deflation Process in Over-parametrized Tensor Decomposition
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 |
|---|---|---|---|
| Add a small regularizer and periodic reinitialization of small-norm components to gradient flow | Over-parameterized tensor decomposition · Orthogonal 4th-order tensor decomposition | Frobenius error: \|T-T^*\|_F\leq \epsilon | Helped |
| Use periodic reinitialization to reduce dependencies between epochs | Modified Gradient Flow · Orthogonal 4th-order tensor decomposition | epochs to termination: O(\log(d/\epsilon)) | Helped |
| Add a small regularizer to stabilize components aligned with already-fitted directions | Modified Gradient Flow · Orthogonal 4th-order tensor decomposition | stability of fitted components | Helped |
Closest papers by meaning
- Beyond Lazy Training for Over-parameterized Tensor Decomposition (NeurIPS 2020 · similarity 0.90)
- Implicit Regularization in Tensor Factorization (ICML 2021 · similarity 0.90)
- Expected Tensor Decomposition with Stochastic Gradient Descent (AAAI 2016 · similarity 0.89)
- Fast Tensor Completion via Approximate Richardson Iteration (ICML 2025 · similarity 0.88)
- Algorithmic Regularization in Tensor Optimization: Towards a Lifted Approach in Matrix Sensing (NeurIPS 2023 · similarity 0.88)
- Implicit Regularization for Tubal Tensor Factorizations via Gradient Descent (ICML 2025 · similarity 0.88)
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.