Papers › Provable Benefits of Complex Parameterizations for Structured State Space Models

Provable Benefits of Complex Parameterizations for Structured State Space Models

17 Oct 2024arXiv:2410.14067archive 2025-07-28

Yuval Ran-Milo, Eden Lumbroso, Edo Cohen-Karlik, Raja Giryes, Amir Globerson, Nadav Cohen

Structured state space models (SSMs), the core engine behind prominent neural networks such as S4 and Mamba, are linear dynamical systems adhering to a specified structure, most notably diagonal. In contrast to typical neural network modules, whose parameterizations are real, SSMs often use complex parameterizations. Theoretically explaining the benefits of complex parameterizations for SSMs is an open problem. The current paper takes a step towards its resolution, by establishing formal gaps between real and complex diagonal SSMs. Firstly, we prove that while a moderate dimension suffices in order for a complex SSM to express all mappings of a real SSM, a much higher dimension is needed for a real SSM to express mappings of a complex SSM. Secondly, we prove that even if the dimension of a real SSM is high enough to express a given mapping, typically, doing so requires the parameters of the real SSM to hold exponentially large values, which cannot be learned in practice. In contrast, a complex SSM can express any given mapping with moderate parameter values. Experiments corroborate our theory, and suggest a potential extension of the theory that accounts for selectivity, a new architectural feature yielding state of the art performance.

PaperPDFCodeCode Syntology ran

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):

Code

Syntology 17 code samples harvested from 2 repositories linked to this paper: 15 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 1 violated, 2 with no contract checked; 10 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 8 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 11 samples from 1 repository, 10 ran (3 with no instrument failure; 7 where Syntology's instrument failed); found in paper text by Syntology: 6 samples from 1 repository, 5 ran (2 with no instrument failure; 3 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.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

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. 1 of the 15 samples that ran has no recorded date.

edenlum/ssmcomplexparambenefits officialmentioned in papermentioned on GitHubpytorchSyntology: 11 samples, 10 ran (7 instrument-failed) · 1 unverified report

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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

17 samples harvested: 15 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 1 violated, 2 with no contract checked; 10 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 last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · honoured contract
1ran · violated contract
8ran · our draft was wrong
2ran; the contract check could not run
2ran
2unverified

Licence: 13 of the 17 samples are pointer only, meaning Syntology does not serve that copy's text. For 2 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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.

edenlum/ssmcomplexparambenefits official repository 11 samples, 10 ran (7 instrument-failed) · 1 unverified
cauchy_naive in 7 papers s4.py ran · our draft was wrong no licence file found · pointer only · 83d17705e31bdff1 · report fixture: signature v:Tensor/2/complex, z:Tensor/2/complex, w:Tensor/2/complex · returned Tensor · level recorded 2026-09-24
complex_log simple_mamba/pscan.py ran · our draft was wrong no licence file found · pointer only · 9828d3d0e675c964 · report fixture: signature input:Tensor/1/float, eps:float/0/float · returned Tensor · level recorded 2026-09-24
convert_type in 5 papers utils.py ran · violated contract no licence file found · pointer only · 24adb09177909a7d · report fixture: signature value:str/0/str · returned bool · level recorded 2026-09-24
delay_l2 datasets.py ran · our draft was wrong no licence file found · pointer only · 9a722661e545209d · report fixture: signature lag:int/0/int · returned function · level recorded 2026-09-24
get_hash in 17 papers utils.py ran · our draft was wrong no licence file found · pointer only · 999d44c96aa5e190 · report fixture: signature config:dict/0/? · returned str · level recorded 2026-09-24
get_logger in 383 papers s4.py ran · our draft was wrong no licence file found · pointer only · 61139ec62260b411 · report fixture: signature name:str/0/str, level:int/0/int · returned Logger · level recorded 2026-09-22
get_target_imp_res theory_ssm/theory_ssm.py ran · honoured contract no licence file found · pointer only · 85c040cde89f147b · report fixture: signature task_name:str/0/str, L:int/0/int · returned Tensor · level recorded 2026-09-24
impulse_response theory_ssm/theory_ssm.py ran no licence file found · pointer only · bbc00961f58e024d · report fixture: signature model:callable/0/?, length:int/0/int · returned Tensor · level recorded 2026-09-24
log_vandermonde_naive in 6 papers s4.py ran · our draft was wrong no licence file found · pointer only · 264ebea7a7690cc2 · report fixture: signature v:Tensor/2/float, x:Tensor/2/float, L:int/0/int, conj:bool/0/bool · returned Tensor · level recorded 2026-09-24
override_config in 9 papers utils.py ran · our draft was wrong no licence file found · pointer only · 23c18f489a46fdc1 · report fixture: signature config:dict/0/?, args:list/1/str · returned dict · level recorded 2026-09-24
logits_to_probability datasets.py unverified no licence file found · pointer only · 0ffc6db74abcbaca · report
alxndrTL/mamba.py found in paper text by Syntology 6 samples, 5 ran (3 instrument-failed) · 1 unverified
repeat_kv in 244 papers
census: 15 implementations from 60 papers, 2 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 4, kind float, dtype float32
mambapy/jamba.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) · 3c76e52815c5401d · report fixture: signature hidden_states:Tensor/4/float, n_rep:int/0/int · returned Tensor · level recorded, date not recorded
load_balancing_loss mambapy/jamba.py ran MIT (permissive) · 0ebccfcf2c0a35d9 · report fixture: signature router_logits:list/1/Tensor, num_experts:int/0/int, num_experts_per_tok:int/0/int · returned Tensor · level recorded 2026-09-24
npo2 in 5 papers mambapy/pscan.py ran · honoured contract fingerprinted MIT (permissive) here; the stored copy is pointer only · d547c23b7746ffe5 · report fixture: signature len:int/0/int · returned int · level recorded 2026-09-25
pad_npo2 in 5 papers mambapy/pscan.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · 8213e85fd713879a · report fixture: signature X:Tensor/4/float · returned Tensor · level recorded 2026-09-25
unsqueeze in 8 papers mlx/misc.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · 152101b1129338c6 · report fixture: signature x:Tensor/3/float, axis:int/0/int · returned Tensor · level recorded 2026-09-24
checkpointed_sequence mambapy/checkpointing.py unverified MIT (permissive) · 6da707934cf98642 · report

Tasks

MambaState Space Models

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Mamba

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