Papers › Distributionally Robust Post-hoc Classifiers under Prior Shifts

Distributionally Robust Post-hoc Classifiers under Prior Shifts

16 Sep 2023arXiv:2309.08825archive 2025-07-28

Jiaheng Wei, Harikrishna Narasimhan, Ehsan Amid, Wen-Sheng Chu, Yang Liu, Abhishek Kumar

The generalization ability of machine learning models degrades significantly when the test distribution shifts away from the training distribution. We investigate the problem of training models that are robust to shifts caused by changes in the distribution of class-priors or group-priors. The presence of skewed training priors can often lead to the models overfitting to spurious features. Unlike existing methods, which optimize for either the worst or the average performance over classes or groups, our work is motivated by the need for finer control over the robustness properties of the model. We present an extremely lightweight post-hoc approach that performs scaling adjustments to predictions from a pre-trained model, with the goal of minimizing a distributionally robust loss around a chosen target distribution. These adjustments are computed by solving a constrained optimization problem on a validation set and applied to the model during test time. Our constrained optimization objective is inspired by a natural notion of robustness to controlled distribution shifts. Our method comes with provable guarantees and empirically makes a strong case for distributional robust post-hoc classifiers. An empirical implementation is available at https://github.com/weijiaheng/Drops.

PaperPDFCodeCode Syntology ranMethod as code

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 13 code samples harvested from 1 repository linked to this paper: 8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 13 samples from 1 repository, 8 ran (6 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 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 2 of the 8 samples that ran have no recorded date.

weijiaheng/drops officialmentioned in papertfSyntology: 13 samples, 8 ran (2 instrument-failed) · 5 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

13 samples harvested: 8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 5 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.

1ran · violated contract
2ran; the contract check could not run
5ran
5unverified

Licence: 13 of the 13 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 weijiaheng/drops. “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.

weijiaheng/drops official repository 13 samples, 8 ran (2 instrument-failed) · 5 unverified
CBLoss losses_lt.py ran no licence file found · pointer only · 96db750723fc8d0b · report fixture: signature y_true:EagerTensor/1/int, y_pred:EagerTensor/2/float, sample_per_cls:list/1/int, beta:float/0/float · returned EagerTensor · level recorded 2026-09-24
CELoss losses_lt.py ran no licence file found · pointer only · 92265b9bb25c6cfc · report fixture: signature y_true:EagerTensor/1/int, y_pred:EagerTensor/2/float, sample_per_cls:list/1/int, from_logits:bool/0/bool · returned EagerTensor · level recorded 2026-09-24
evaluate in 514 papers utils.py ran no licence file found · pointer only · e19d0c3f75393ec1 · report fixture: signature model:callable/0/?, loader:SimpleLoader/0/?, get_yp_func:callable/0/?, multitask:bool/0/bool, predict_place:bool/0/bool · returned dict · level recorded 2026-09-24
get_cls_idx in 12 papers main_lt.py ran; the contract check could not run (RAISES) · metamorphic tier: well formed no licence file found · pointer only · 99e0fd44f2945184 · report fixture: signature num_per_cls:list/1/int, y_train:list/1/int, is_upsampling:bool/0/bool · returned list · level recorded, date not recorded
get_cls_num main_lt.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 5875084978e41075 · report fixture: signature dataset_name:str/0/str, y_train:ndarray/1/int, imb_factor:float/0/float · returned list · level recorded, date not recorded
get_results in 29 papers utils.py ran no licence file found · pointer only · 58b9298579ed4235 · report fixture: signature acc_groups:dict/0/?, get_yp_func:callable/0/? · returned dict · level recorded 2026-09-24
get_y_p utils.py ran fingerprinted no licence file found · pointer only · d2ae9d5fc68a3253 · report fixture: signature g:int/0/int, n_places:int/0/int · returned tuple · level recorded 2026-09-24
maybe_one_hot drops_test_time.py ran · violated contract no licence file found · pointer only · c76410a2e5a019a8 · report fixture: signature labels:EagerTensor/1/int, depth:int/0/int · returned EagerTensor · level recorded 2026-09-22
MakeLossFunc losses_lt.py unverified no licence file found · pointer only · 7ad316cb77932b5f · report
MakeLossFunc losses_lt_new.py unverified no licence file found · pointer only · 92a081d68735c144 · report
calibrate_shifts drops_test_time.py unverified no licence file found · pointer only · 6ec9e8d6c9981483 · report
calibrate_temp drops_test_time.py unverified no licence file found · pointer only · 0bf7d139457b5de7 · report
ce_loss in 34 papers drops_test_time.py unverified no licence file found · pointer only · a85f3df5207d6bdf · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for Drops (graph method: Drops). 3 bricks; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

  1. calibrate_shifts entry · level 0 · unverified · 6ec9e8d6c9981483
  2. ce_loss helper · level 0 · unverified · a85f3df5207d6bdf
  3. maybe_one_hot helper · level 1 · ran · violated contract · c76410a2e5a019a8

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2309.08825") returns these assemblies with each brick's role and wiring (how to connect).

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