Papers › Learning sparse features can lead to overfitting in neural networks
Learning sparse features can lead to overfitting in neural networks
Leonardo Petrini, Francesco Cagnetta, Eric Vanden-Eijnden, Matthieu Wyart
It is widely believed that the success of deep networks lies in their ability to learn a meaningful representation of the features of the data. Yet, understanding when and how this feature learning improves performance remains a challenge: for example, it is beneficial for modern architectures trained to classify images, whereas it is detrimental for fully-connected networks trained for the same task on the same data. Here we propose an explanation for this puzzle, by showing that feature learning can perform worse than lazy training (via random feature kernel or the NTK) as the former can lead to a sparser neural representation. Although sparsity is known to be essential for learning anisotropic data, it is detrimental when the target function is constant or smooth along certain directions of input space. We illustrate this phenomenon in two settings: (i) regression of Gaussian random functions on the d-dimensional unit sphere and (ii) classification of benchmark datasets of images. For (i), we compute the scaling of the generalization error with number of training points, and show that methods that do not learn features generalize better, even when the dimension of the input space is large. For (ii), we show empirically that learning features can indeed lead to sparse and thereby less smooth representations of the image predictors. This fact is plausibly responsible for deteriorating the performance, which is known to be correlated with smoothness along diffeomorphisms.
In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.
Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
For agents, on Syntology's MCP service (how to connect):
get_harvested_code_for_paper(arxiv_id="2206.12314")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="2206.12314", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="2206.12314")
Code
Syntology 18 code samples harvested from 1 repository linked to this paper: 16 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 1 honoured, 0 violated, 15 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.
By repository: official repository: 18 samples from 1 repository, 16 ran (16 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.
Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
18 samples harvested: 16 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 1 honoured, 0 violated, 15 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.
Licence: 0 of the 18 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.
Harvested from pcsl-epfl/regressionsphere. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.
Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.
Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.
A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.
71b4b044f07081ec · report
fixture: signature hashed_activations:list/1/str · returned dict · level recorded 2026-09-25 a3cbe2ad9c5c502c · report
fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-25 cb2578da62e48947 · report
fixture: signature args:Args/0/?, init_loss:float/0/float · returned tuple · level recorded 2026-09-25 f72f872d399d4f2a · report
fixture: signature xtr:Tensor/2/float, w1:Tensor/2/float, w2:Tensor/2/float · returned Tensor · level recorded 2026-09-25 76f93f9f3b586130 · report
fixture: returned tuple · level recorded 2026-09-25 fe93f8b312493d15 · report
fixture: signature d:int/0/int, n:int/0/int · returned Tensor · level recorded 2026-09-25 a7dc348e1fc8ec14 · report
fixture: signature samples:int/0/int · returned Tensor · level recorded 2026-09-25 ea165c25ef2a0e6e · report
fixture: signature elapsed_time:float/0/float · returned str · level recorded 2026-09-25 0c55dfd2474acb2e · report
fixture: signature x:float/0/float, m:int/0/int · returned float · level recorded 2026-09-22 a880819237db04b3 · report
fixture: signature func:callable/0/?, target:float/0/float, lower:float/0/float, upper:float/0/float, atol:float/0/float · returned float · level recorded 2026-09-25 2b8873eb94ee34ab · report
fixture: signature phi:float/0/float · returned float · level recorded 2026-09-25 47c678f57539f602 · report
fixture: signature phi:Tensor/1/float · returned Tensor · level recorded 2026-09-25 87c75ddd40e70ca5 · report
fixture: signature phi:Tensor/2/float · returned Tensor · level recorded 2026-09-25 adc267f0c196b663 · report
fixture: signature args:Args/0/?, epoch:int/0/int · returned float · level recorded 2026-09-25 b580ad0adf4a4d17 · report
fixture: signature x:Tensor/3/float, d:int/0/int, whitening:bool/0/bool · returned Tensor · level recorded 2026-09-25 census: 4 implementations from 5 papers, 4 distinct outputs across 2 buckets, one shared input per bucket stability.py ran fingerprinted MIT (permissive) ·
d9794cc8e3c1bcb9 · report
fixture: signature imgs:Tensor/4/float, timgs:Tensor/4/float · returned Tensor · level recorded 2026-09-25 Results from the paper archive 2025-07-28
No leaderboard rows for this paper in the archive.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections