Papers › Tropical Attention: Neural Algorithmic Reasoning for Combinatorial Algorithms

Tropical Attention: Neural Algorithmic Reasoning for Combinatorial Algorithms

22 May 2025arXiv:2505.17190archive 2025-07-28

Baran Hashemi, Kurt Pasque, Chris Teska, Ruriko Yoshida

Dynamic programming (DP) algorithms for combinatorial optimization problems work with taking maximization, minimization, and classical addition in their recursion algorithms. The associated value functions correspond to convex polyhedra in the max plus semiring. Existing Neural Algorithmic Reasoning models, however, rely on softmax-normalized dot-product attention where the smooth exponential weighting blurs these sharp polyhedral structures and collapses when evaluated on out-of-distribution (OOD) settings. We introduce Tropical attention, a novel attention function that operates natively in the max-plus semiring of tropical geometry. We prove that Tropical attention can approximate tropical circuits of DP-type combinatorial algorithms. We then propose that using Tropical transformers enhances empirical OOD performance in both length generalization and value generalization, on algorithmic reasoning tasks, surpassing softmax baselines while remaining stable under adversarial attacks. We also present adversarial-attack generalization as a third axis for Neural Algorithmic Reasoning benchmarking. Our results demonstrate that Tropical attention restores the sharp, scale-invariant reasoning absent from softmax.

PaperPDFCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2505.17190")

Code

Syntology Ran 0 of 9 code samples harvested from 1 repository linked to this paper; 9 have no recorded run.

By repository: found in paper text by Syntology: 9 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Baran-phys/Tropical-Attention found in paper text by SyntologyMIT 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

9 samples harvested; 0 ran; 0 honoured the contract we drafted; 9 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

9unverified

Licence: 0 of the 9 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 Baran-phys/Tropical-Attention. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

adaptive_temperature_softmax Baran-phys/Tropical-Attention/models.py found in paper text by Syntology unverified MIT (permissive) · f443dbe93defa3cf · report
convert_value Baran-phys/Tropical-Attention/experiment.py found in paper text by Syntology unverified MIT (permissive) · 17f649fefaa3c71e · report
max_subset_mask Baran-phys/Tropical-Attention/dataloaders.py found in paper text by Syntology unverified MIT (permissive) · 88d2790b0768be11 · report
maxplus_matmul Baran-phys/Tropical-Attention/tropical_gemm_backend.py found in paper text by Syntology unverified MIT (permissive) · 4849f6753bf0ec67 · report
set_max_subset_sum Baran-phys/Tropical-Attention/dataloaders.py found in paper text by Syntology unverified MIT (permissive) · f01f2aa40c7f61ac · report
set_subset_sum_decision Baran-phys/Tropical-Attention/dataloaders.py found in paper text by Syntology unverified MIT (permissive) · aff0ad1b655e8b76 · report
smooth_max Baran-phys/Tropical-Attention/models.py found in paper text by Syntology unverified MIT (permissive) · d5e0a54421d6976c · report
smooth_min Baran-phys/Tropical-Attention/models.py found in paper text by Syntology unverified MIT (permissive) · 1b2a20f459140576 · report
torch_maxplus_matmul Baran-phys/Tropical-Attention/tropical_gemm_backend.py found in paper text by Syntology unverified MIT (permissive) · adfa93deef389005 · report

Tasks

Adversarial AttackBenchmarkingCombinatorial OptimizationMathematical ReasoningOut-of-Distribution Generalization

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AttentionSoftmax

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