SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2303.03307 · NeurIPS · 2023

Efficient Coding of Natural Images using Maximum Manifold Capacity Representations

Sueyeon Chung, Thomas Yerxa, Yilun Kuang, Eero Simoncelli

arXiv · PDF · Open in the Atlas

Code that ran

1 of 1 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; 0 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/2303.03307.json · badge: /api/ran/2303.03307.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
ThomasYerxa/mmcr marked official in Papers with Code
Papers with Code archive
1 ran · 0 no recorded run
FunctionStatusWhere it lives
MMCR_Loss Ran
ran on a synthesized input
ThomasYerxa/mmcr/mmcr/imagenet/loss_mmcr.py
code served (permissive licence) · get_code("593b1e2a5eb5e336")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) and returned tuple, ndim 1, dtype family float; no output shape is stated. The image it ran in was 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
from torch import nn, Tensor
import torch.nn.functional as F
import einops
from typing import Tuple

class MMCR_Loss(nn.Module):

    def __init__(self, lmbda: float, n_aug: int, distributed: bool=True):
        super(MMCR_Loss, self).__init__()
        self.lmbda = lmbda
        self.n_aug = n_aug
        self.distribured = distributed

    def forward(self, z: Tensor) -> Tuple[Tensor, dict]:
        z = F.normalize(z, dim=-1)
        z_local_ = einops.rearrange(z, '(B N) C -> B C N', N=self.n_aug)
        if self.distribured:
            z_list = [torch.zeros_like(z_local_) for i in range(torch.distributed.get_world_size())]
            torch.distributed.all_gather(z_list, z_local_, async_op=False)
            z_list[torch.distributed.get_rank()] = z_local_
            z_local = torch.cat(z_list)
        else:
            z_local = z_local_
        centroids = torch.mean(z_local, dim=-1)
        if self.lmbda != 0.0:
            local_nuc = torch.linalg.svdvals(z_local).sum()
        else:
            local_nuc = torch.tensor(0.0)
        global_nuc = torch.linalg.svdvals(centroids).sum()
        batch_size = z_local.shape[0]
        loss = self.lmbda * local_nuc / batch_size - global_nuc
        loss_dict = {'loss': loss.item(), 'local_nuc': local_nuc.item(), 'global_nuc': global_nuc.item()}
        return (loss, loss_dict)


INIT_ARGS = {
    'lmbda': 0.5,
    'n_aug': 3,
    'distributed': False,
}

ARGS = {
    'z': torch.randn(6, 4),
}

if __name__ == '__main__':
    model = MMCR_Loss(**INIT_ARGS)
    loss, loss_dict = model(**ARGS)
    print(f"Loss: {loss}")
    print(f"Loss dict: {loss_dict}")
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
Imports
einops, 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: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)

Also present in other papers' code

Of 1 samples lifted from this paper's linked repositories, 1 carry a function identity and 0 do not. Of the 1 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 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.

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 efficient coding hypothesis posits that sensory systems are adapted to the statistics of their inputs, maximizing mutual information between environmental signals and their representations, subject to biological constraints. While elegant, information theoretic quantities are notoriously difficult to measure or optimize, and most research on the hypothesis employs approximations, bounds, or substitutes (e.g., reconstruction error). A recently developed measure of coding efficiency, the "manifold capacity", quantifies the number of object categories that may be represented in a linearly separable fashion, but its calculation relies on a computationally intensive iterative procedure that precludes its use as an objective. Here, we simplify this measure to a form that facilitates direct optimization, use it to learn Maximum Manifold Capacity Representations (MMCRs), and demonstrate that these are competitive with state-of-the-art results on current self-supervised learning (SSL) recognition benchmarks. Empirical analyses reveal important differences between MMCRs and the representations learned by other SSL frameworks, and suggest a mechanism by which manifold compression gives rise to class separability. Finally, we evaluate a set of SSL methods on a suite of neural predictivity benchmarks, and find MMCRs are highly competitive as models of the primate ventral stream.

For agents

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

get_harvested_code_for_paper("2303.03307")
get_code_for_paper("2303.03307")
have("2303.03307")

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

curl https://syntology.ai/api/ran/2303.03307.json

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

[![Syntology run record](https://syntology.ai/api/ran/2303.03307.svg)](https://syntology.ai/paper/2303.03307)

Connect an agent — have() is free.