Papers › Koopman Kernel Regression

Koopman Kernel Regression

25 May 2023NeurIPS 2023 11arXiv:2305.16215archive 2025-07-28

Petar Bevanda, Max Beier, Armin Lederer, Stefan Sosnowski, Eyke Hüllermeier, Sandra Hirche

Many machine learning approaches for decision making, such as reinforcement learning, rely on simulators or predictive models to forecast the time-evolution of quantities of interest, e.g., the state of an agent or the reward of a policy. Forecasts of such complex phenomena are commonly described by highly nonlinear dynamical systems, making their use in optimization-based decision-making challenging. Koopman operator theory offers a beneficial paradigm for addressing this problem by characterizing forecasts via linear time-invariant (LTI) ODEs, turning multi-step forecasts into sparse matrix multiplication. Though there exists a variety of learning approaches, they usually lack crucial learning-theoretic guarantees, making the behavior of the obtained models with increasing data and dimensionality unclear. We address the aforementioned by deriving a universal Koopman-invariant reproducing kernel Hilbert space (RKHS) that solely spans transformations into LTI dynamical systems. The resulting Koopman Kernel Regression (KKR) framework enables the use of statistical learning tools from function approximation for novel convergence results and generalization error bounds under weaker assumptions than existing work. Our experiments demonstrate superior forecasting performance compared to Koopman operator and sequential data predictors in RKHS.

PaperPDFConference PDFCodeCode 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 39 code samples harvested from 2 repositories linked to this paper: 30 ran (of which 0 constructed an object rather than computing a result; 30 with no instrument failure: 0 honoured, 0 violated, 30 with no contract checked; 0 where Syntology's instrument failed) · 9 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 27 samples from 1 repository, 23 ran (23 with no instrument failure; 0 where Syntology's instrument failed); found in paper text by Syntology: 12 samples from 1 repository, 7 ran (7 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.

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

Levels written on 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

TUM-ITR/koopcore officialmentioned in paperjaxMITSyntology: 27 samples, 23 ran (0 instrument-failed) · 4 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

39 samples harvested: 30 ran (of which 0 constructed an object rather than computing a result; 30 with no instrument failure: 0 honoured, 0 violated, 30 with no contract checked; 0 where Syntology's instrument failed) · 9 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.

30ran
9unverified

Licence: 0 of the 39 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 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.

TUM-ITR/koopcore official repository 27 samples, 23 ran (0 instrument-failed) · 4 unverified
convert_2d_to_complex koopcore/auxilliary/eigenvalues.py ran MIT (permissive) · 6dfc8a2c6e8eeb01 · report fixture: signature data:Tensor/2/float · returned Tensor · level recorded 2026-09-26
convert_ct_to_dt koopcore/auxilliary/eigenvalues.py ran fingerprinted MIT (permissive) · f1ab2fc65d7d9d30 · report fixture: signature e:ndarray/1/float, dt:float/0/float · returned ndarray · level recorded 2026-09-26
convert_dt_to_ct koopcore/auxilliary/eigenvalues.py ran MIT (permissive) · 90213921b6596bd8 · report fixture: returned ndarray · level recorded 2026-09-26
discretize_RK4 koopcore/auxilliary/dynamical_systems.py ran MIT (permissive) · d3bc66e9e4565788 · report fixture: signature f:callable/0/?, dt:float/0/float · returned function · level recorded 2026-09-26
get_all_one_step koopcore/auxilliary/any.py ran MIT (permissive) · ff728c09ecd69eea · report fixture: signature X:ArrayImpl/3/float · returned tuple · level recorded 2026-09-26
get_subplots_fig_ax koopcore/auxilliary/plot.py ran MIT (permissive) · 9a0422aa1a7a1151 · report fixture: signature fig_ax:NoneType/0/? · returned tuple · level recorded 2026-09-26
gramian_tensor_to_lstsq_matrix koopcore/jax/explicit_invariant_kernels.py ran MIT (permissive) · 72e4361ad07b60fd · report fixture: signature koopman_gramian:ArrayImpl/4/float, dtype:callable/0/? · returned ArrayImpl · level recorded 2026-09-26
koopman_kernel koopcore/jax/explicit_invariant_kernels.py ran MIT (permissive) · 599fce4fcfc64447 · report fixture: signature base_kernel:callable/0/?, g_1:ArrayImpl/3/float, g_2:ArrayImpl/3/float, t_vec:ArrayImpl/1/float, l_vec:ArrayImpl/1/float · returned ArrayImpl · level recorded 2026-09-26
load_trajectory_dict koopcore/auxilliary/data_classes.py ran MIT (permissive) · c6688b714f2426b2 · report fixture: signature path:str/0/str · returned dict · level recorded 2026-09-26
make_kernel in 34 papers koopcore/jax/kernels.py ran MIT (permissive) · ea268ac4b3e2bf0c · report fixture: signature kernel_name:str/0/str, p_kernel:dict/0/? · returned function · level recorded 2026-09-26
make_koopman_kernel koopcore/jax/invariant_kernels.py ran MIT (permissive) · 8e4e65cd0a32e769 · report fixture: signature base_kernel:callable/0/?, eigenvalues_dt:ArrayImpl/1/float, H:int/0/int, einsum_kwargs:dict/0/?, normalize:callable/0/? · returned dict · level recorded 2026-09-26
make_vector_valued_kernel koopcore/jax/explicit_invariant_kernels.py ran MIT (permissive) · ffbeaea4a2febd90 · report fixture: signature base_kernel:callable/0/?, D:int/0/int, x_base:ArrayImpl/2/float · returned function · level recorded 2026-09-26
mono_between_enum koopcore/auxilliary/monomials.py ran fingerprinted MIT (permissive) · 760ebc4e73a31fe7 · report fixture: signature m:int/0/int, n1:int/0/int, n2:int/0/int · returned float64 · level recorded 2026-09-26
mono_between_next_grevlex koopcore/auxilliary/monomials.py ran MIT (permissive) · 4422ebf49fc59a7a · report fixture: signature m:int/0/int, n1:int/0/int, n2:int/0/int, x:ndarray/1/int · returned ndarray · level recorded 2026-09-26
mono_between_next_grlex koopcore/auxilliary/monomials.py ran MIT (permissive) · 5b919da0f063d4d2 · report fixture: signature m:int/0/int, n1:int/0/int, n2:int/0/int, x:ndarray/1/int · returned ndarray · level recorded 2026-09-26
normalize_eigenfunctions_by_norm koopcore/jax/koopman_model.py ran fingerprinted MIT (permissive) · cb3d0f920549f7d9 · report fixture: signature L:ArrayImpl/2/float · returned ArrayImpl · level recorded 2026-09-26
normalize_eigenfunctions_by_operator koopcore/jax/koopman_model.py ran MIT (permissive) · 2eefac08464a0d0c · report fixture: signature L:ArrayImpl/2/complex · returned ArrayImpl · level recorded 2026-09-26
normalize_eigenfunctions_by_steps koopcore/jax/koopman_model.py ran fingerprinted MIT (permissive) · 1cfff57a9293a2cf · report fixture: signature L:Tensor/2/float · returned Tensor · level recorded 2026-09-26
p_norm koopcore/auxilliary/any.py ran MIT (permissive) · 7ea1ef685fd613d3 · report fixture: signature e:Tensor/3/float, a:int/0/int, p:float/0/float, mean:bool/0/bool · returned Tensor · level recorded 2026-09-26
rk4 in 7 papers koopcore/auxilliary/dynamical_systems.py ran MIT (permissive) · f6b71302a6d554f3 · report fixture: signature f:callable/0/?, x0:Tensor/2/float, dt:float/0/float · returned Tensor · level recorded 2026-09-26
rmse in 44 papers koopcore/auxilliary/any.py ran MIT (permissive) · f6d85b06a431d110 · report fixture: signature X:ArrayImpl/2/float, Y:ArrayImpl/2/float, mean_axis:list/1/int, sum_axis:NoneType/0/? · returned ArrayImpl · level recorded 2026-09-26
sample_grid koopcore/auxilliary/sample.py ran MIT (permissive) · 0062f2e557c26150 · report fixture: signature N1:int/0/int, d:int/0/int, _range:tuple/1/float, dtype:callable/0/? · returned tuple · level recorded 2026-09-26
tmap koopcore/auxilliary/multithreading.py ran MIT (permissive) · 07e2e4902a0f5796 · report fixture: signature function:callable/0/?, devices:list/1/str, log:callable/0/? · returned function · level recorded 2026-09-26
get_equilibrium_evals koopcore/auxilliary/dynamical_systems.py unverified MIT (permissive) · e76ca414c11ec7ed · report
load_trajectory_data_train_test koopcore/auxilliary/data_classes.py unverified MIT (permissive) · 55fab559ff449555 · report
plot_data koopcore/auxilliary/plot.py unverified MIT (permissive) · 9d2bdad369559772 · report
plot_eigevalues koopcore/auxilliary/plot.py unverified MIT (permissive) · bb5e6fdfb9fa307c · report
Ceyron/machine-learning-and-simulation found in paper text by Syntology 12 samples, 7 ran (0 instrument-failed) · 5 unverified
approximate_kl_divergence english/probabilistic_machine_learning/contrib/vi_elbo_intuition_visual_torch.py ran MIT (permissive) · aa2d12c4c78a3230 · report fixture: signature p:Normal/0/?, q:Normal/0/?, size:int/0/int · returned ndarray · level recorded 2026-09-26
estimate_params english/probabilistic_machine_learning/contrib/em_gmm_multivariate.py ran fingerprinted MIT (permissive) · 31e15bcbe318a96b · report fixture: signature x_sub:ndarray/2/float · returned tuple · level recorded 2026-09-26
mock_data english/probabilistic_machine_learning/contrib/em_gmm_multivariate.py ran MIT (permissive) · ac5e3f90105578c2 · report fixture: signature n_samples:int/0/int, n_classes:int/0/int · returned tuple · level recorded 2026-09-26
surrogate_posterior english/probabilistic_machine_learning/contrib/vi_elbo_intuition_visual_torch.py ran MIT (permissive) · c558f30361054045 · report fixture: signature loc_approx:Tensor/2/float, scale_approx:Tensor/2/float · returned Normal · level recorded 2026-09-26
surrogate_posterior_parameter english/probabilistic_machine_learning/univariate_normal_posterior_vi.py ran MIT (permissive) · cb95017ad0122041 · report fixture: signature dataset:ndarray/1/float, alpha_0:float/0/float, beta_0:float/0/float, mu_0:float/0/float, tau_0:float/0/float, max_iter:int/0/int · returned tuple · level recorded 2026-09-26
true_posterior english/probabilistic_machine_learning/contrib/vi_elbo_intuition_visual_torch.py ran MIT (permissive) · 97e20fc4e726685e · report fixture: signature mixture_probs:Tensor/1/float, mus:Tensor/1/float, sigmas:Tensor/1/float · returned MixtureSameFamily · level recorded 2026-09-26
true_posterior_parameter english/probabilistic_machine_learning/univariate_normal_posterior_vi.py ran MIT (permissive) · 9330ce580a5a376c · report fixture: signature dataset:ndarray/1/float, alpha_0:float/0/float, beta_0:float/0/float, mu_0:float/0/float, tau_0:float/0/float · returned tuple · level recorded 2026-09-26
em in 12 papers english/probabilistic_machine_learning/em_gmm.py unverified MIT (permissive) · 362705c2ca3ed543 · report
em in 12 papers english/probabilistic_machine_learning/em_multivariate_gmm.py unverified MIT (permissive) · ca84bfff521d9b46 · report
em in 12 papers english/probabilistic_machine_learning/contrib/em_gmm_multivariate.py unverified MIT (permissive) · 057f69e5229c5333 · report
em_sieved english/probabilistic_machine_learning/em_gmm_with_sieving.py unverified MIT (permissive) · 0e91c42fab93bb7c · report
em_with_guesses english/probabilistic_machine_learning/em_gmm_with_sieving.py unverified MIT (permissive) · a60c74d010e4b551 · report

Tasks

Decision Makingregression

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