Papers › Empirical or Invariant Risk Minimization? A Sample Complexity Perspective

Empirical or Invariant Risk Minimization? A Sample Complexity Perspective

30 Oct 2020ICLR 2021 1arXiv:2010.16412archive 2025-07-28

Kartik Ahuja, Jun Wang, Amit Dhurandhar, Karthikeyan Shanmugam, Kush R. Varshney

Recently, invariant risk minimization (IRM) was proposed as a promising solution to address out-of-distribution (OOD) generalization. However, it is unclear when IRM should be preferred over the widely-employed empirical risk minimization (ERM) framework. In this work, we analyze both these frameworks from the perspective of sample complexity, thus taking a firm step towards answering this important question. We find that depending on the type of data generation mechanism, the two approaches might have very different finite sample and asymptotic behavior. For example, in the covariate shift setting we see that the two approaches not only arrive at the same asymptotic solution, but also have similar finite sample behavior with no clear winner. For other distribution shifts such as those involving confounders or anti-causal variables, however, the two approaches arrive at different asymptotic solutions where IRM is guaranteed to be close to the desired OOD solutions in the finite sample regime, while ERM is biased even asymptotically. We further investigate how different factors -- the number of environments, complexity of the model, and IRM penalty weight -- impact the sample complexity of IRM in relation to its distance from the OOD solutions

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 14 code samples harvested from 2 repositories linked to this paper: 12 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 14 samples from 2 repositories, 12 ran (10 with no instrument failure; 2 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.

IBM/IRM-games officialmentioned in papermentioned on GitHubtfApache-2.0Syntology: 6 samples, 5 ran (2 instrument-failed) · 1 unverified report
IBM/OoD officialmentioned in papermentioned on GitHubtfApache-2.0Syntology: 8 samples, 7 ran (0 instrument-failed) · 1 unverified report
IBM/OoD officialtfSyntology: 8 samples, 7 ran (0 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.

Code Syntology ran Syntology

14 samples harvested: 12 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 2 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.

2ran · our draft was wrong
10ran
2unverified

Licence: 2 of the 14 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.

IBM/IRM-games official repository 6 samples, 5 ran (2 instrument-failed) · 1 unverified
ERM_Tblock IRM_ITE/models.py ran Apache-2.0 (permissive) · a7f23fec9f83e15e · report fixture: signature X_train:ndarray/2/float, T_train:ndarray/1/int, X_test:ndarray/2/float, y_train:ndarray/2/float, model_type:str/0/str · returned tuple · level recorded 2026-09-25
convert_regn_np_format LRG_games/irm_games_regression.py ran Apache-2.0 (permissive) · cabc72b51279fac0 · report fixture: signature all_environments:list/1/list · returned list · level recorded 2026-09-25
errors LRG_games/ERM_per_env/IRM_exhaustive_argparse_hper_wo_disc_Sep8.py ran Apache-2.0 (permissive) · b73c6efcdaeee963 · report fixture: signature w:Tensor/2/float, w_hat:Tensor/2/float · returned tuple · level recorded 2026-09-25
pretty in 10 papers ERM-IRM/models_crossval_Sep8.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · db4d05619d1e83d4 · report fixture: signature vector:Tensor/2/float · returned str · level recorded 2026-09-22
pretty in 10 papers LRG_games/ERM_per_env/IRM_exhaustive_argparse_hper_wo_disc_Sep8.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · 1463989a26f3aa4f · report fixture: signature vector:Tensor/2/float · returned str · level recorded 2026-09-22
ERM_Sblock IRM_ITE/models.py unverified Apache-2.0 (permissive) · a2f985068c422b43 · report
IBM/OoD official repository 8 samples, 7 ran (0 instrument-failed) · 1 unverified
IRM_Sblock IRM_ITE/irm_block.py ran Apache-2.0 (permissive) · 4dbfd6b03c7a8067 · report fixture: signature environments:list/1/tuple, featuresTest_control:Tensor/2/float, featuresTest_treatment:Tensor/2/float, args:Args/0/? · returned tuple · level recorded 2026-09-25
PEHE IRM_ITE/metrics.py ran fingerprinted Apache-2.0 (permissive) · 3ef447ce6417f2a3 · report fixture: signature test_potential_outcome:ndarray/2/float, pred_potential_outcome:ndarray/2/float · returned float32 · level recorded 2026-09-25
ate_error IRM_ITE/metrics.py ran Apache-2.0 (permissive) · 91d3cbc506dacd10 · report fixture: signature test_ate:ndarray/0/float, pred_ate:ndarray/0/float · returned float64 · level recorded 2026-09-25
envs_irm_S IRM_ITE/irm_block.py ran Apache-2.0 (permissive) · c84217ccfbad36a6 · report fixture: signature X_train:ndarray/2/float, X_test:ndarray/2/float, T_train:ndarray/2/float, y_train:ndarray/2/float, E:ndarray/1/int, number_environments:int/0/int · returned tuple · level recorded 2026-09-25
envs_irm_T IRM_ITE/irm_block.py ran Apache-2.0 (permissive) · 57e301bf69860e40 · report fixture: signature X_train:ndarray/2/float, y_train:ndarray/2/float, E:ndarray/1/int, number_environments:int/0/int · returned list · level recorded 2026-09-25
generate_T IRM_ITE/generate_synthetic_data.py ran fingerprinted Apache-2.0 (permissive) · b46d230fde0188cd · report fixture: signature number_obeservations:int/0/int · returned ndarray · level recorded 2026-09-25
generate_mixture_indicator IRM_ITE/generate_synthetic_data.py ran fingerprinted Apache-2.0 (permissive) · e39c919dc88468e7 · report fixture: signature number_obeservations:int/0/int · returned ndarray · level recorded 2026-09-25
generate_synthetic_data in 7 papers IRM_ITE/generate_synthetic_data.py unverified Apache-2.0 (permissive) · fc6dfd875f58ef25 · report

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