SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2410.02117 · NeurIPS · 2024

Searching for Efficient Linear Layers over a Continuous Space of Structured Matrices

Micah Goldblum, Marc Finzi, Andrew Wilson, Christopher De Sa, Zixi Chen, Andres Potapczynski, Shikai Qiu, Bayan Bruss, Christopher Ferri

arXiv · PDF · Open in the Atlas

Code that ran

2 of 3 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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 1 failure of our instrument; 1 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; 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/2410.02117.json · badge: /api/ran/2410.02117.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
andpotap/einsum-search canonical (classifier label)
classifier basis: classifier_2025
2 ran · 1 no recorded run
FunctionStatusWhere it lives
construct_configs Ran
ran; our contract draft was wrong, not the code
andpotap/einsum-search/model/gpt_fns.py
code served (permissive licence) · get_code("48af3e47455f7711")
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) and returned tuple, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is not recorded. If your copy returns the same type and ndim 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 torch
import numpy as np

torch.manual_seed(0)

ARGS = {
    'n_layer': 2,
    'base_n_head': 4,
    'base_d_head': 8,
    'base_d_model': 32,
    'base_d_embd': 16,
    'n_head': 4,
    'd_head': 8,
    'd_model': 32,
    'd_embd': 16,
    'block_size': 64,
    'bias': True,
    'vocab_size': 256,
    'dropout': 0.1,
    'do_qk_ln': False,
    'split_qkv': False,
    'base_ffn_expansion': 4,
    'ffn_expansion': 4,
    'num_ffn_experts': 1,
    'num_active_ffn_experts': 1,
    'struct': 'dense',
    'num_experts': 1,
    'num_active_experts': 1,
    'tt_dim': 2,
    'tt_rank': 4,
    'num_blocks': 1,
    'rank_frac': 0.5,
    'expr': 'test_expr',
    'every_n_fwds': 10,
    'opt_name': 'adamw',
    'weight_decay': 0.01,
    'init_lr': 0.001,
    'beta1': 0.9,
    'beta2': 0.999,
    'device': 'cpu',
    'head_btt_case_qkv': None,
    'head_btt_case_proj': None,
    'use_head_btt': False,
    'axial': False,
    'lm_head_struct': None,
    'lm_head_tt_rank': None,
    'lm_head_rank_frac': None,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, dtype family float — a tuple output has no array shape of its own; none is stated
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
get_epoch Ran
ran, honoured the contract we drafted
andpotap/einsum-search/model/gpt_fns.py
code served (permissive licence) · get_code("5a338ab5a2b4dce3")
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) and returned int, ndim 0, dtype family int, 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 torch
import numpy as np

torch.manual_seed(0)

# Analyze the function: get_epoch takes iter_num, dataset_size, block_size, batch_size, num_devices
# and computes: int(iter_num // (dataset_size / (block_size * batch_size * num_devices)))
# All parameters are numeric values used in arithmetic operations

ARGS = {
    "iter_num": 1000,
    "dataset_size": 50000,
    "block_size": 128,
    "batch_size": 32,
    "num_devices": 4,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type int, ndim 0, dtype family int, 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
init_dist_process Not yet run
unverified (harvested, no recorded run)
andpotap/einsum-search/model/gpt_fns.py
code served (permissive licence) · get_code("0790868b68269e62")
How it ran

no invocation recorded.

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 0 later) and 1 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.

FunctionAlso present inEarliest-datedOthers named
get_epoch 1 other paper
1 dated earlier
2406.06248 (2024-06)
Compute Better Spent: Replacing Dense Layers with Structured Matrices
init_dist_process 1 other paper
1 dated earlier
2406.06248 (2024-06)
Compute Better Spent: Replacing Dense Layers with Structured Matrices

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

Dense linear layers are the dominant computational bottleneck in large neural networks, presenting a critical need for more efficient alternatives. Previous efforts focused on a small number of hand-crafted structured matrices and neglected to investigate whether these structures can surpass dense layers in terms of computeoptimal scaling laws when both the model size and training examples are optimally allocated. In this work, we present a unifying framework that enables searching among all linear operators expressible via an Einstein summation. This framework encompasses many previously proposed structures, such as low-rank, Kronecker, Tensor-Train, Block Tensor-Train (BTT), and Monarch, along with many novel structures. To analyze the framework, we develop a taxonomy of all such operators based on their computational and algebraic properties and show that differences in the compute-optimal scaling laws are mostly governed by a small number of variables that we introduce. Namely, a small ω (which measures parameter sharing) and large ψ (which measures the rank) reliably led to better scaling laws. Guided by the insight that full-rank structures that maximize parameters per unit of compute perform the best, we propose BTT-MoE, a novel Mixture-of-Experts (MoE) architecture obtained by sparsifying computation in the BTT structure. In contrast to the standard sparse MoE for each entire feed-forward network, BTT-MoE learns an MoE in every single linear layer of the model, including the projection matrices in the attention blocks. We find BTT-MoE provides a substantial compute-efficiency gain over dense layers and standard MoE.

For agents

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

get_harvested_code_for_paper("2410.02117")
get_code_for_paper("2410.02117")
have("2410.02117")

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

curl https://syntology.ai/api/ran/2410.02117.json

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

[![Syntology run record](https://syntology.ai/api/ran/2410.02117.svg)](https://syntology.ai/paper/2410.02117)

Connect an agent — have() is free.