We lifted 7 functions out of this paper's own repositories and ran 7 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| apourchot/to_share_or_not_to_share | canonical | 7 of 7 |
| Function | Status | Where it lives |
|---|---|---|
| eval_model | Ran | apourchot/to_share_or_not_to_share/training.py code served (permissive licence) · get_code("cf07dd413f297eb9") |
| get_criterion | Ran | apourchot/to_share_or_not_to_share/utils.py code served (permissive licence) · get_code("23f701d112f0a43c") |
| get_next_nodes | Ran | apourchot/to_share_or_not_to_share/models/graph_utils.py code served (permissive licence) · get_code("3ae0139825452ef8") |
| get_optimizer | Ran | apourchot/to_share_or_not_to_share/utils.py code served (permissive licence) · get_code("f39eacca39245d60") |
| get_prev_nodes | Ran | apourchot/to_share_or_not_to_share/models/graph_utils.py code served (permissive licence) · get_code("45c62416d255378d") |
| get_reaching_nodes | Ran | apourchot/to_share_or_not_to_share/models/graph_utils.py code served (permissive licence) · get_code("94bb2ff67302c3d5") |
| get_scheduler | Ran | apourchot/to_share_or_not_to_share/utils.py code served (permissive licence) · get_code("e816f750ceeb6df0") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Weight-sharing (WS) has recently emerged as a paradigm to accelerate the automated search for efficient neural architectures, a process dubbed Neural Architecture Search (NAS). Although very appealing, this framework is not without drawbacks and several works have started to question its capabilities on small hand-crafted benchmarks. In this paper, we take advantage of the \nasbench dataset to challenge the efficiency of WS on a representative search space. By comparing a SOTA WS approach to a plain random search we show that, despite decent correlations between evaluations using weight-sharing and standalone ones, WS is only rarely significantly helpful to NAS. In particular we highlight the impact of the search space itself on the benefits.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2002.04289")
get_code_for_paper("2002.04289")
have("2002.04289")
Connect an agent — have() is free.