SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2206.04993 · ICLR · 2023

The Symmetric Generalized Eigenvalue Problem as a Nash Equilibrium

Deepmind London, Ian Gemp, Brian Mcwilliams, Charlie Chen

arXiv · PDF · Open in the Atlas

Code that ran

1 of 6 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 0 failures of our instrument; 5 no recorded run), measured 2026-11-22; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2206.04993.json · badge: /api/ran/2206.04993.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
deepmind/eigengame canonical (classifier label)
classifier basis not recorded on the link
1 ran · 5 no recorded run
FunctionStatusWhere it lives
decaying_schedule_with_warmup Ran
ran on a synthesized input
deepmind/eigengame/eigengame/eg_experiment.py
code served (permissive licence) · get_code("13c3b743e22f5450")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ArrayImpl, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import jax.numpy as jnp

ARGS = {
    "step": 500,
    "warm_up_step": 1000,
    "end_step": 10000,
    "base_lr": 0.1,
    "end_lr": 0.01,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
jax — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ArrayImpl, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
create_sharded_identity Not yet run
unverified (harvested, no recorded run)
deepmind/eigengame/eigengame/eg_gradients.py
code served (permissive licence) · get_code("c12c16f5e0f85b9a")
How it ran

no invocation recorded.

create_sharded_mask Not yet run
unverified (harvested, no recorded run)
deepmind/eigengame/eigengame/eg_gradients.py
code served (permissive licence) · get_code("06052f1a34d1ea55")
How it ran

no invocation recorded.

get_spherical_gradients Not yet run
unverified (harvested, no recorded run)
deepmind/eigengame/eigengame/eg_utils.py
code served (permissive licence) · get_code("e3a3b89a6b077d47")
How it ran

no invocation recorded.

init_aux_variables Not yet run
unverified (harvested, no recorded run)
deepmind/eigengame/eigengame/eg_utils.py
code served (permissive licence) · get_code("02b593f810e5090d")
How it ran

no invocation recorded.

normalize_eigenvectors Not yet run
unverified (harvested, no recorded run)
deepmind/eigengame/eigengame/eg_utils.py
code served (permissive licence) · get_code("dd5bb5d7aa8125fb")
How it ran

no invocation recorded.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 6 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

The symmetric generalized eigenvalue problem (SGEP) is a fundamental concept in numerical linear algebra. It captures the solution of many classical machine learning problems such as canonical correlation analysis, independent components analysis, partial least squares, linear discriminant analysis, principal components and others. Despite this, most general solvers are prohibitively expensive when dealing with streaming data sets (i.e., minibatches) and research has instead concentrated on finding efficient solutions to specific problem instances. In this work, we develop a game-theoretic formulation of the top-k SGEP whose Nash equilibrium is the set of generalized eigenvectors. We also present a parallelizable algorithm with guaranteed asymptotic convergence to the Nash. Current state-ofthe-art methods require O(d 2 k) runtime complexity per iteration which is prohibitively expensive when the number of dimensions (d) is large. We show how to modify this parallel approach to achieve O(dk) runtime complexity. Empirically we demonstrate that this resulting algorithm is able to solve a variety of SGEP problem instances including a large-scale analysis of neural network activations. * Asterisk denotes equal contribution. † Work done while at DeepMind.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2206.04993")
get_code_for_paper("2206.04993")
have("2206.04993")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2206.04993.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2206.04993.svg)](https://syntology.ai/paper/2206.04993)

Connect an agent — have() is free.