SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2403.06398 · ICML · 2024

On the Diminishing Returns of Width for Continual Learning

Etash Guha, Vihan Lakshman

arXiv · PDF · Open in the Atlas

Code that ran

None of the 3 samples (functions and classes) lifted from this paper's linked repositories has a recorded run on a synthesized input (3 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/2403.06398.json · badge: /api/ran/2403.06398.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
vihan-lakshman/diminishing-returns-wide-continual-learning canonical (classifier label)
classifier basis: census
0 ran · 3 no recorded run
FunctionStatusWhere it lives
get_rotated_gtsrb Not yet run
unverified (harvested, no recorded run)
vihan-lakshman/diminishing-returns-wide-continual-learning/data_utils.py
code served (permissive licence) · get_code("efdce8167e519f21")
How it ran

no invocation recorded.

get_rotated_mnist Not yet run
unverified (harvested, no recorded run)
vihan-lakshman/diminishing-returns-wide-continual-learning/data_utils.py
code served (permissive licence) · get_code("6226df0913be22a5")
How it ran

no invocation recorded.

get_rotated_svhn Not yet run
unverified (harvested, no recorded run)
vihan-lakshman/diminishing-returns-wide-continual-learning/data_utils.py
code served (permissive licence) · get_code("e0d56369bb1e68c8")
How it ran

no invocation recorded.

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 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 3 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

While deep neural networks have demonstrated groundbreaking performance in various settings, these models often suffer from catastrophic forgetting when trained on new tasks in sequence. Several works have empirically demonstrated that increasing the width of a neural network leads to a decrease in catastrophic forgetting but have yet to characterize the exact relationship between width and continual learning. We designed one of the first frameworks to analyze continuous learning theory and prove that width is directly related to forgetting in feed-forward networks (FFN). In particular, we demonstrate that increasing network widths to reduce forgetting yields diminishing returns. We empirically verify our claims at widths hitherto unexplored in prior studies where the diminishing returns are clearly observed as predicted by our theory.

For agents

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

get_harvested_code_for_paper("2403.06398")
get_code_for_paper("2403.06398")
have("2403.06398")

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

curl https://syntology.ai/api/ran/2403.06398.json

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

[![Syntology run record](https://syntology.ai/api/ran/2403.06398.svg)](https://syntology.ai/paper/2403.06398)

Connect an agent — have() is free.