Papers › Semi Bandit Dynamics in Congestion Games: Convergence to Nash Equilibrium and...

Semi Bandit Dynamics in Congestion Games: Convergence to Nash Equilibrium and No-Regret Guarantees

27 Jun 2023arXiv:2306.15543links table onlyarchive 2025-07-28

Ioannis Panageas, Stratis Skoulakis, Luca Viano, Xiao Wang, Volkan Cevher

The archive published only this paper's code-link row. Authors, date and abstract are from arXiv's metadata (CC0), read from the Kaggle arXiv metadata snapshot of 2026-09-12 where its title matched the archive's; the title is the archive's.

In this work, we introduce a new variant of online gradient descent, which provably converges to Nash Equilibria and simultaneously attains sublinear regret for the class of congestion games in the semi-bandit feedback setting. Our proposed method admits convergence rates depending only polynomially on the number of players and the number of facilities, but not on the size of the action set, which can be exponentially large in terms of the number of facilities. Moreover, the running time of our method has polynomial-time dependence on the implicit description of the game. As a result, our work answers an open question from (Du et. al, 2022).

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 online gradient descent variant, generated from the paper text (not the authors' code), at level 2 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)” (quoted from Syntology's server card). No rung compares this code against the authors' implementation. For agents: get_reference_implementation(name='online gradient descent variant') (how to connect); the free check have('2306.15543') needs no token.

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

Code

Syntology 15 code samples harvested from 1 repository linked to this paper: 11 ran (of which 1 constructed an object rather than computing a result; 6 with no instrument failure: 4 honoured, 1 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 3 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: 15 samples from 1 repository, 11 ran (6 with no instrument failure; 5 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 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

lviano/sbgd-ce officialmentioned in paperSyntology: 15 samples, 11 ran (5 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.

Code Syntology ran Syntology

15 samples harvested: 11 ran (of which 1 constructed an object rather than computing a result; 6 with no instrument failure: 4 honoured, 1 violated, 1 with no contract checked; 5 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.

4ran · honoured contract
1ran · violated contract
3ran · our draft was wrong
2ran; the contract check could not run
1ran
4unverified

Licence: 15 of the 15 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 lviano/sbgd-ce. “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.

lviano/sbgd-ce official repository 15 samples, 11 ran (5 instrument-failed) · 4 unverified
Graph in 18 papers graph.py ran no licence file found · pointer only · c17b5aafc29b4b86 · report fixture: returned Graph · level recorded 2026-09-22
_remove_zero_rows graph.py ran · honoured contract fingerprinted no licence file found · pointer only · 6f66b2fb658009f4 · report fixture: signature A:ndarray/2/float · returned ndarray · level recorded 2026-09-22
_row_count graph.py ran · honoured contract fingerprinted no licence file found · pointer only · a53d39433053915b · report fixture: signature A:ndarray/2/float · returned ndarray · level recorded 2026-09-22
bg_update_dense graph.py ran; the contract check could not run (RAISES) no licence file found · pointer only · 55b4c439eab8d3db · report fixture: signature plu:tuple/1/ndarray, perm_r:ndarray/1/int, v:ndarray/1/float, j:int/0/int · returned tuple · level recorded 2026-09-22
compute_edges_load graph.py ran · honoured contract fingerprinted no licence file found · pointer only · f5b2eeffe6118bbf · report fixture: signature paths:list/1/list, nbr_edges:int/0/int · returned ndarray · level recorded 2026-09-22
cost_function graph.py ran · violated contract fingerprinted no licence file found · pointer only · f942d37a9fa0f80d · report fixture: signature load:Tensor/1/float · returned Tensor · level recorded 2026-09-22
estimate_cost graph.py ran; the contract check could not run (RAISES) no licence file found · pointer only · 4df166ea562859b6 · report fixture: signature loads:ndarray/1/float, path:ndarray/1/int, x:ndarray/1/float · returned ndarray · level recorded 2026-09-22
evaluate in 514 papers graph.py ran · honoured contract no licence file found · pointer only · 823490d514362782 · report fixture: signature paths:list/1/str, loads:dict/0/? · returned list · level recorded 2026-09-22
find_path_with_indices graph.py ran · our draft was wrong no licence file found · pointer only · 676746f6d7cb8acb · report fixture: signature g:SimpleGraph/0/?, among:set/0/?, must:tuple/1/str · returned tuple · level recorded 2026-09-22
find_path_with_indices_fast graph.py ran · our draft was wrong no licence file found · pointer only · c421aac711841f9c · report fixture: signature g:MockGraph/0/?, among:list/1/int, must:int/0/int · returned tuple · level recorded 2026-09-22
my_remove_redundancy_pivot_dense graph.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 8ec1c0f0080abe83 · report fixture: signature A:ndarray/2/float, true_rank:NoneType/0/? · returned tuple · level recorded 2026-09-22
carat_sgd_multi_player graph.py unverified no licence file found · pointer only · 941391f261ce1bf6 · report
compute_projection graph.py unverified no licence file found · pointer only · 0fe37043c91c3d44 · report
efficient_decomposition graph.py unverified no licence file found · pointer only · f06f22642f0d18ed · report
sample_path graph.py unverified no licence file found · pointer only · 4bb24471b1fe08d0 · 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 online gradient descent variant (graph method: online gradient descent variant), 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, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. Ran end-to-end against an independent peer (level 2).

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

  1. euclidean_projection_onto_simplex entry · level 2 · ran · 06492cd47dee63d3dccd03590d3e142ddd3e44974a318ecc8d0bf76611ac5adc

harvested Assembly for online gradient descent variant (graph method: online gradient descent variant). 15 bricks; individually on a fixture: 11 ran (of which 1 constructed an object rather than computing a result; 6 with no instrument failure: 4 honoured, 1 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified. The assembly has not been run end-to-end.

  1. carat_sgd_multi_player entry · level 0 · unverified · 941391f261ce1bf6
  2. Graph helper · level 1 · ran · c17b5aafc29b4b86
  3. compute_edges_load helper · level 1 · ran · honoured contract · f5b2eeffe6118bbf
  4. compute_projection update_rule · level 0 · unverified · 0fe37043c91c3d44
  5. estimate_cost helper · level 1 · ran; the contract check could not run (RAISES) · 4df166ea562859b6
  6. evaluate metric · level 1 · ran · honoured contract · 823490d514362782
  7. sample_path sampler · level 0 · unverified · 4bb24471b1fe08d0
  8. my_remove_redundancy_pivot_dense helper · level 1 · ran · our draft was wrong · 8ec1c0f0080abe83
  9. cost_function loss · level 1 · ran · violated contract · f942d37a9fa0f80d
  10. efficient_decomposition helper · level 0 · unverified · f06f22642f0d18ed
  11. _remove_zero_rows helper · level 1 · ran · honoured contract · 6f66b2fb658009f4
  12. bg_update_dense helper · level 1 · ran; the contract check could not run (RAISES) · 55b4c439eab8d3db
  13. find_path_with_indices helper · level 1 · ran · our draft was wrong · 676746f6d7cb8acb
  14. find_path_with_indices_fast helper · level 1 · ran · our draft was wrong · c421aac711841f9c
  15. _row_count helper · level 1 · ran · honoured contract · a53d39433053915b

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="2306.15543") 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