Papers › RATT: Leveraging Unlabeled Data to Guarantee Generalization

RATT: Leveraging Unlabeled Data to Guarantee Generalization

1 May 2021arXiv:2105.00303archive 2025-07-28

Saurabh Garg, Sivaraman Balakrishnan, J. Zico Kolter, Zachary C. Lipton

To assess generalization, machine learning scientists typically either (i) bound the generalization gap and then (after training) plug in the empirical risk to obtain a bound on the true risk; or (ii) validate empirically on holdout data. However, (i) typically yields vacuous guarantees for overparameterized models. Furthermore, (ii) shrinks the training set and its guarantee erodes with each re-use of the holdout set. In this paper, we introduce a method that leverages unlabeled data to produce generalization bounds. After augmenting our (labeled) training set with randomly labeled fresh examples, we train in the standard fashion. Whenever classifiers achieve low error on clean data and high error on noisy data, our bound provides a tight upper bound on the true risk. We prove that our bound is valid for 0-1 empirical risk minimization and with linear classifiers trained by gradient descent. Our approach is especially useful in conjunction with deep learning due to the early learning phenomenon whereby networks fit true labels before noisy labels but requires one intuitive assumption. Empirically, on canonical computer vision and NLP tasks, our bound provides non-vacuous generalization guarantees that track actual performance closely. This work provides practitioners with an option for certifying the generalization of deep nets even when unseen labeled data is unavailable and provides theoretical insights into the relationship between random label noise and generalization.

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 16 code samples harvested from 1 repository linked to this paper: 8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 8 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 16 samples from 1 repository, 8 ran (7 with no instrument failure; 1 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 on 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 8 samples that ran has no recorded date.

acmi-lab/ratt_generalization_bound officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 16 samples, 8 ran (1 instrument-failed) · 8 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

16 samples harvested: 8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 8 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 · our draft was wrong
7ran
8unverified

Licence: 2 of the 16 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 acmi-lab/ratt_generalization_bound. “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.

acmi-lab/ratt_generalization_bound official repository 16 samples, 8 ran (1 instrument-failed) · 8 unverified
ResNet18 in 174 papers models/resnet.py ran Apache-2.0 (permissive) · ee3a23d9284921b0 · report fixture: signature num_classes:int/0/int · returned ResNet · level recorded 2026-09-25
custom_dataset data_helper.py ran Apache-2.0 (permissive) · 33c9f87823514bad · report fixture: signature cls:callable/0/? · returned type · level recorded 2026-09-25
format_time in 140 papers utils.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · 8d7ec010c29e813b · report fixture: signature seconds:float/0/float · returned str · level recorded, date not recorded
get_model in 368 papers model_helper.py ran Apache-2.0 (permissive) · 4e4f63cb91e4b0e0 · report fixture: signature model_type:str/0/str, input_dim:int/0/int, num_classes:int/0/int · returned Sequential · level recorded 2026-09-25
initialize_bert_transform datasets/IMDb.py ran Apache-2.0 (permissive) · bb921ba6a0704620 · report fixture: signature net:str/0/str · returned function · level recorded 2026-09-25
random_label_noise data_helper.py ran Apache-2.0 (permissive) · 5de1b3eb7678aa7c · report fixture: signature data:ndarray/2/float, targets:ndarray/1/int, clean_size:int/0/int, noise_size:int/0/int, num_classes:int/0/int · returned tuple · level recorded 2026-09-25
read_file in 112 papers plots_helper/plot_acc.py ran Apache-2.0 (permissive) · eeb3d9b0ff6d3654 · report fixture: signature filename:str/0/str · returned ndarray · level recorded 2026-09-25
read_imdb_split datasets/IMDb.py ran Apache-2.0 (permissive) · e1e8c58b1243b4e0 · report fixture: signature split_dir:str/0/str · returned tuple · level recorded 2026-09-25
download_and_load_datasets train_imdb_elmo.py unverified Apache-2.0 (permissive) · 5bbd31590c16d155 · report
getBertTokenizer datasets/IMDb.py unverified Apache-2.0 (permissive) · 08da3d75f4a68eb5 · report
get_mean_and_std in 55 papers utils.py unverified Apache-2.0 (permissive) · 7bd3a77007a65eec · report
get_train_data in 6 papers data_helper.py unverified Apache-2.0 (permissive) · 18d06a46390badba · report
initialize_bert_based_model models/bert.py unverified Apache-2.0 (permissive) here; the stored copy is pointer only · b24bb0be9085efab · report
load_dataset in 276 papers train_imdb_elmo.py unverified Apache-2.0 (permissive) · c7a16597f295a1ba · report
load_directory_data train_imdb_elmo.py unverified Apache-2.0 (permissive) · 7b0fc787f8d444d1 · report
pred_accuracy model_helper.py unverified Apache-2.0 (permissive) · 7e5acdc16eb78bae · report

Tasks

Generalization BoundsHoldout Set

1 archive task tag without a task page not shown.

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