SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2006.15766 · ICLR · 2021

Heteroskedastic and Imbalanced Deep Learning with Adaptive Regularization

Adrien Gaidon, Tengyu Ma, Junwei Lu, Kaidi Cao, Yining Chen, Nikos Arechiga

arXiv · PDF · Open in the Atlas

Code that ran

None of the 2 samples (functions and classes) lifted from this paper's linked repositories has a recorded run on a synthesized input (2 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/2006.15766.json · badge: /api/ran/2006.15766.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
kaidic/HAR marked official in Papers with Code
Papers with Code archive
0 ran · 2 no recorded run
FunctionStatusWhere it lives
HETEROSKEDASTICCIFAR10 Not yet run
unverified (harvested, no recorded run)
kaidic/HAR/heteroskedastic_cifar.py
code served (permissive licence) · get_code("655fd119be5ca686")
How it ran

no invocation recorded.

multiclass_noisify Not yet run
unverified (harvested, no recorded run)
kaidic/HAR/heteroskedastic_cifar.py
code served (permissive licence) · get_code("c5c3434271117391")
How it ran

no invocation recorded.

Also present in other papers' code

Of 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 2 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.

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

Real-world large-scale datasets are heteroskedastic and imbalanced -labels have varying levels of uncertainty and label distributions are long-tailed. Heteroskedasticity and imbalance challenge deep learning algorithms due to the difficulty of distinguishing among mislabeled, ambiguous, and rare examples. Addressing heteroskedasticity and imbalance simultaneously is under-explored. We propose a data-dependent regularization technique for heteroskedastic datasets that regularizes different regions of the input space differently. Inspired by the theoretical derivation of the optimal regularization strength in a one-dimensional nonparametric classification setting, our approach adaptively regularizes the data points in higher-uncertainty, lower-density regions more heavily. We test our method on several benchmark tasks, including a real-world heteroskedastic and imbalanced dataset, WebVision. Our experiments corroborate our theory and demonstrate a significant improvement over other methods in noise-robust deep learning. 1

For agents

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

get_harvested_code_for_paper("2006.15766")
get_code_for_paper("2006.15766")
have("2006.15766")

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

curl https://syntology.ai/api/ran/2006.15766.json

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

[![Syntology run record](https://syntology.ai/api/ran/2006.15766.svg)](https://syntology.ai/paper/2006.15766)

Connect an agent — have() is free.