SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1906.02341 · 2019

How to Initialize your Network? Robust Initialization for WeightNorm & ResNets

arXiv · PDF · Open in the Atlas

Code that ran

10 of 10 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 9 have no contract verdict; 0 failures of our instrument; 0 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/1906.02341.json · badge: /api/ran/1906.02341.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
victorcampos7/weightnorm-init canonical (classifier label)
classifier basis: census
10 ran · 0 no recorded run
FunctionStatusWhere it lives
choose_left Ran
ran on a synthesized input
victorcampos7/weightnorm-init/src/util/schedules.py
pointer only (licence: MIT) · get_code("557aa71e0848bed0")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, victorcampos7/weightnorm-init, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

create_optimizer Ran
ran on a synthesized input
victorcampos7/weightnorm-init/src/util/graph_def.py
pointer only (licence: MIT) · get_code("17e87ddd51cd5ba2")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, victorcampos7/weightnorm-init, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

data_dependent_weight_norm_g_init Ran
ran on a synthesized input
victorcampos7/weightnorm-init/src/models/init.py
pointer only (licence: MIT) · get_code("fc6b085641ffab5e")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, victorcampos7/weightnorm-init, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_config_path Ran
ran on a synthesized input
victorcampos7/weightnorm-init/src/util/misc.py
pointer only (licence: MIT) · get_code("1cec52b5952e109a")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, victorcampos7/weightnorm-init, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_input_size Ran
ran on a synthesized input
victorcampos7/weightnorm-init/src/util/graph_def.py
pointer only (licence: MIT) · get_code("a23f08f7da4b2c36")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, victorcampos7/weightnorm-init, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_log_path Ran
ran on a synthesized input
victorcampos7/weightnorm-init/src/util/misc.py
pointer only (licence: MIT) · get_code("0f17d5f12485b857")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, victorcampos7/weightnorm-init, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_model_dir Ran
ran on a synthesized input
victorcampos7/weightnorm-init/src/util/misc.py
pointer only (licence: MIT) · get_code("ac5e4caf2614e958")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, victorcampos7/weightnorm-init, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

hessian_spectral_norm_approx Ran
ran on a synthesized input
victorcampos7/weightnorm-init/src/util/hessian.py
pointer only (licence: MIT) · get_code("bdbb021a27680d79")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, victorcampos7/weightnorm-init, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

init_and_maybe_normalize_layer Ran
ran on a synthesized input
victorcampos7/weightnorm-init/src/models/init.py
pointer only (licence: MIT) · get_code("6b4b313f3974194b")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, victorcampos7/weightnorm-init, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

linear_interpolation Ran
ran, honoured the contract we drafted
victorcampos7/weightnorm-init/src/util/schedules.py
pointer only (licence: MIT); the stored copy get_code serves, from rrmenon10/Bootstrapped-DQN, is pointer only (licence: MIT) · get_code("5908b0de70ae8316")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, victorcampos7/weightnorm-init, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 1 later) and 9 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
linear_interpolation 4 other papers
2 dated earlier, 2 later
1710.00814 (2017-10)
Detecting Adversarial Attacks on Neural Network Policies with Visual Foresight
1710.11417 (2017-10)
TreeQN and ATreeC: Differentiable Tree-Structured Models for Deep Reinforcement Learning
1909.05398 (2019-09)
Interactive Fiction Games: A Colossal Adventure
and 1 more not named here

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Residual networks (ResNet) and weight normalization play an important role in various deep learning applications. However, parameter initialization strategies have not been studied previously for weight normalized networks and, in practice, initialization methods designed for un-normalized networks are used as a proxy. Similarly, initialization for ResNets have also been studied for un-normalized networks and often under simplified settings ignoring the shortcut connection. To address these issues, we propose a novel parameter initialization strategy that avoids explosion/vanishment of information across layers for weight normalized networks with and without residual connections. The proposed strategy is based on a theoretical analysis using mean field approximation. We run over 2,500 experiments and evaluate our proposal on image datasets showing that the proposed initialization outperforms existing initialization methods in terms of generalization performance, robustness to hyper-parameter values and variance between seeds, especially when networks get deeper in which case existing methods fail to even start training. Finally, we show that using our initialization in conjunction with learning rate warmup is able to reduce the gap between the performance of weight normalized and batch normalized networks.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1906.02341")
get_code_for_paper("1906.02341")
have("1906.02341")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/1906.02341.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/1906.02341.svg)](https://syntology.ai/paper/1906.02341)

Connect an agent — have() is free.