Papers › Bilevel Optimization: Convergence Analysis and Enhanced Design

Bilevel Optimization: Convergence Analysis and Enhanced Design

15 Oct 2020arXiv:2010.07962archive 2025-07-28

Kaiyi Ji, Junjie Yang, Yingbin Liang

Bilevel optimization has arisen as a powerful tool for many machine learning problems such as meta-learning, hyperparameter optimization, and reinforcement learning. In this paper, we investigate the nonconvex-strongly-convex bilevel optimization problem. For deterministic bilevel optimization, we provide a comprehensive convergence rate analysis for two popular algorithms respectively based on approximate implicit differentiation (AID) and iterative differentiation (ITD). For the AID-based method, we orderwisely improve the previous convergence rate analysis due to a more practical parameter selection as well as a warm start strategy, and for the ITD-based method we establish the first theoretical convergence rate. Our analysis also provides a quantitative comparison between ITD and AID based approaches. For stochastic bilevel optimization, we propose a novel algorithm named stocBiO, which features a sample-efficient hypergradient estimator using efficient Jacobian- and Hessian-vector product computations. We provide the convergence rate guarantee for stocBiO, and show that stocBiO outperforms the best known computational complexities orderwisely with respect to the condition number κ and the target accuracy ϵ. We further validate our theoretical results and demonstrate the efficiency of bilevel optimization algorithms by the experiments on meta-learning and hyperparameter optimization.

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.

Syntology holds a reference implementation of stocBiO, generated from the paper text (not the authors' code), at level 3 on Syntology's ladder: V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)”; V3 “paper-derived property tests pass on both of those same two generations.” (quoted from Syntology's server card). No rung compares this code against the authors' implementation. For agents: get_reference_implementation(name='stocBiO') (how to connect); the free check have('2010.07962') needs no token.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 18 code samples harvested from 2 repositories linked to this paper: 14 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 0 violated, 5 with no contract checked; 7 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 5 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: 14 samples from 1 repository, 11 ran (7 with no instrument failure; 4 where Syntology's instrument failed); community (archive-listed): 4 samples from 1 repository, 3 ran (0 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. 8 of the 14 samples that ran have no recorded date.

junjieyang97/stocbio_hp officialmentioned in papermentioned on GitHubpytorchMITSyntology: 14 samples, 11 ran (4 instrument-failed) · 3 unverified report
JunjieYang97/stocBiO mentioned on GitHubpytorchSyntology: 4 samples, 3 ran (3 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

18 samples harvested: 14 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 0 violated, 5 with no contract checked; 7 where Syntology's instrument failed) · 4 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 · honoured contract
5ran · our draft was wrong
2ran; the contract check could not run
5ran
4unverified

Licence: 1 of the 18 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, 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.

junjieyang97/stocbio_hp official repository 14 samples, 11 ran (4 instrument-failed) · 3 unverified
accuracy in 872 papers
census: 8 implementations from 7 papers, 7 distinct outputs across 6 buckets, one shared input per bucket
Meta-learning/ANIL/miniimagenet/anil.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) · d41eb4e2f3bebbf1 · report fixture: signature predictions:Tensor/2/float, targets:Tensor/1/int · returned Tensor · level recorded 2026-09-22
cat_list_to_tensor in 7 papers Hyperparameter-optimization/hypergrad/CG_torch.py ran · honoured contract MIT (permissive) · 3ed1406329714c3f · report fixture: signature list_tx:list/1/Tensor · returned Tensor · level recorded, date not recorded
cg in 10 papers Hyperparameter-optimization/hypergrad/CG_torch.py ran · our draft was wrong MIT (permissive) · 31f282d2a7c181bb · report fixture: signature Ax:callable/0/?, b:list/1/Tensor, max_iter:int/0/int, epsilon:float/0/float · returned list · level recorded, date not recorded
fixed_point in 7 papers Hyperparameter-optimization/hypergrad/hypergradients.py ran · our draft was wrong MIT (permissive) · 11d924c279d6166a · report fixture: signature params:list/1/Tensor, hparams:list/1/Tensor, K:int/0/int, fp_map:callable/0/?, outer_loss:callable/0/?, tol:float/0/float, set_grad:bool/0/bool, stochastic:bool/0/bool · returned list · level recorded, date not recorded
from_sparse Hyperparameter-optimization/experimental/l2reg_on_twentynews.py ran MIT (permissive) · e73c33a4af5fe161 · report fixture: signature x:coo_matrix/2/float · returned Tensor · level recorded 2026-09-25
gd_step Hyperparameter-optimization/hypergrad/diff_optimizers.py ran MIT (permissive) here; the stored copy is pointer only · 3ffa7e0c883965f8 · report fixture: signature params:list/1/Tensor, loss:Tensor/0/float, step_size:float/0/float, create_graph:bool/0/bool · returned list · level recorded 2026-09-25
heavy_ball_step Hyperparameter-optimization/hypergrad/diff_optimizers.py ran MIT (permissive) · d533144f406f4f80 · report fixture: signature params:list/1/Tensor, aux_params:list/1/Tensor, loss:Tensor/0/float, step_size:float/0/float, momentum:float/0/float, create_graph:bool/0/bool · returned tuple · level recorded 2026-09-25
reverse in 15 papers Hyperparameter-optimization/hypergrad/hypergradients.py ran · honoured contract MIT (permissive) · 52b6f88728db5c40 · report fixture: signature params_history:list/1/list, hparams:list/1/Tensor, update_map_history:list/1/callable, outer_loss:callable/0/?, set_grad:bool/0/bool · returned list · level recorded, date not recorded
reverse_unroll in 5 papers Hyperparameter-optimization/hypergrad/hypergradients.py ran · our draft was wrong MIT (permissive) · 677c8518ad1a22c9 · report fixture: signature params:list/1/Tensor, hparams:list/1/Tensor, outer_loss:callable/0/?, set_grad:bool/0/bool · returned tuple · level recorded, date not recorded
torch_momentum_step Hyperparameter-optimization/hypergrad/diff_optimizers.py ran MIT (permissive) · 6cdf7a8f1301bf5c · report fixture: signature params:list/1/Tensor, aux_params:list/1/Tensor, loss:Tensor/0/float, step_size:float/0/float, momentum:float/0/float, create_graph:bool/0/bool · returned tuple · level recorded 2026-09-25
train_loss Hyperparameter-optimization/experimental/l2reg_on_twentynews.py ran MIT (permissive) · fae35b77af7219e9 · report fixture: signature params:list/1/Tensor, hparams:tuple/1/Tensor, data:tuple/1/Tensor · returned Tensor · level recorded 2026-09-25
fast_adapt Meta-learning/ANIL/miniimagenet/anil.py unverified MIT (permissive) · 186dcd090e91bb0e · report
fast_adapt Meta-learning/FO-ITD-BiO/miniimagenet/ITD-BiO.py unverified MIT (permissive) · e77a457bca6c4a2d · report
get_data_loaders in 22 papers Hyperparameter-optimization/experimental/mnist_exp.py unverified MIT (permissive) · 3851e32f29e94b92 · report
JunjieYang97/stocBiO community (archive-listed) 4 samples, 3 ran (3 instrument-failed) · 1 unverified
gradient_fy Hyperparameter-optimization/experimental/stocBiO.py ran · our draft was wrong MIT (permissive) · b233bbdedd873c21 · report fixture: signature args:Tensor/2/float, labels:Tensor/1/int, params:Tensor/2/float, data:NoneType/0/?, output:Tensor/2/float · returned Tensor · level recorded, date not recorded
gradient_gy Hyperparameter-optimization/experimental/stocBiO.py ran · our draft was wrong MIT (permissive) · cda14929afcae4b3 · report fixture: signature args:NoneType/0/?, labels_cp:Tensor/1/int, params:Tensor/2/float, data:NoneType/0/?, hparams:dict/0/?, output:Tensor/2/float, reg_f:callable/0/? · returned Tensor · level recorded, date not recorded
loss_train_avg Hyperparameter-optimization/experimental/mnist_exp.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant MIT (permissive) · d46ee4443d27d233 · report fixture: signature data_loader:list/1/tuple, parameters:Tensor/2/float, device:device/0/?, batch_num:int/0/int · returned Tensor · level recorded, date not recorded
stocbio Hyperparameter-optimization/experimental/stocBiO.py unverified MIT (permissive) · e519fae7e667e28f · 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. For a generated assembly, an independent peer is a second implementation generated separately from the same paper text; neither implementation read the authors' code. At level 2 the two agreed numerically on the fixture's inputs; level 3 is recorded when property tests derived from the paper also passed on both, and each level 3 card prints how many its report lists. 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. A generated assembly's label was set when its code was generated for the method, and no model judged it; its card prints it as "by construction" or "not judged by a model". Where an assembly's phrase has no constructed figure, a brick that ran is not among the harvested samples this build reads, and whether a brick's run only constructed an object is read from that brick's harvested sample, so the figure was not counted; it does not say there were none.

2 assemblies on this paper: 1 harvested, 1 generated.

generated Assembly for stocBiO (graph method: stocBiO), generated from the paper text, not the repository's code. 1 brick; individually on a fixture: 1 ran (1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. Ran end-to-end against an independent peer (level 3; 4 property tests passed on both).

label matches by construction: the code was generated for this method (not judged by a model)

  1. stocbio_hypergradient_estimate entry · level 3 · ran · violated contract · fdaa947b47d407ea2b4297b550e2dacfa1d685c44f547fe2d82139fd958a093f

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

  1. stocbio entry · level 0 · unverified · e519fae7e667e28f
  2. gradient_fy helper · level 1 · ran · our draft was wrong · b233bbdedd873c21
  3. gradient_gy loss · level 1 · ran · our draft was wrong · cda14929afcae4b3

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="2010.07962") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Bilevel OptimizationHyperparameter OptimizationMeta-Learning

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