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.
The essential difficulty of gradient-based bilevel optimization using implicit differentiation is to estimate the inverse Hessian vector product with respect to neural network parameters. This paper proposes to tackle this problem by the Nystrom method and the Woodbury matrix identity, exploiting the low-rankness of the Hessian. Compared to existing methods using iterative approximation, such as conjugate gradient and the Neumann series approximation, the proposed method avoids numerical instability and can be efficiently computed in matrix operations without iterations. As a result, the proposed method works stably in various tasks and is faster than iterative approximations. Throughout experiments including large-scale hyperparameter optimization and meta learning, we demonstrate that the Nystrom method consistently achieves comparable or even superior performance to other approaches. The source code is available from https://github.com/moskomule/hypergrad.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2302.09726")
get_code_for_paper("2302.09726")
have("2302.09726")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2302.09726.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2302.09726)
Connect an agent — have() is free.