We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
We study low-rank parameterizations of weight matrices with embedded spectral properties in the Deep Learning context. The low-rank property leads to parameter efficiency and permits taking computational shortcuts when computing mappings. Spectral properties are often subject to constraints in optimization problems, leading to better models and stability of optimization. We start by looking at the compact SVD parameterization of weight matrices and identifying redundancy sources in the parameterization. We further apply the Tensor Train (TT) decomposition to the compact SVD components, and propose a non-redundant differentiable parameterization of fixed TT-rank tensor manifolds, termed the Spectral Tensor Train Parameterization (STTP). We demonstrate the effects of neural network compression in the image classification setting and both compression and improved training stability in the generative adversarial training setting.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2103.04217")
get_code_for_paper("2103.04217")
have("2103.04217")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2103.04217.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2103.04217)
Connect an agent — have() is free.