SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2602.02877 · ICML · 2026

A Geometry-Aware Efficient Algorithm for Compositional Entropic Risk Minimization

Bokun Wang, Tianbao Yang, Chih-Jen Lin, Xiyuan Wei, Linli Zhou

arXiv · PDF · Open in the Atlas

Code that ran

2 of 2 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 2 have no contract verdict; 0 failures of our instrument; 0 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/2602.02877.json · badge: /api/ran/2602.02877.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
Optimization-AI/SCENT community
Papers with Code archive
2 ran · 0 no recorded run
FunctionStatusWhere it lives
MSELoss Ran
ran on a synthesized input
Optimization-AI/SCENT/dro/mylosses.py
code served (permissive licence) · get_code("a998dc9df38ba955")
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 Tensor, ndim 2, dtype family float, shape (2, 4) 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 torch.nn as nn

class MSELoss(nn.Module):
    """MSE Loss for regression tasks, compatible with DRO methods."""

    def __init__(self, reduction='none'):
        super(MSELoss, self).__init__()
        self.reduction = reduction

    def forward(self, out, target, weight=None):
        out = out.squeeze()
        target = target.squeeze()
        loss = (out - target) ** 2
        if self.reduction == 'mean':
            return loss.mean()
        elif self.reduction == 'sum':
            return loss.sum()
        else:
            return loss


INIT_ARGS = {
    'reduction': 'none'
}

ARGS = {
    'out': torch.randn(2, 4),
    'target': torch.randn(2, 4),
    'weight': None
}

if __name__ == '__main__':
    loss_fn = MSELoss(**INIT_ARGS)
    result = loss_fn(**ARGS)
    print("Output shape:", result.shape)
    print("Output:", result)
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) 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: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
SENT Ran
ran on a synthesized input
Optimization-AI/SCENT/dro/mylosses.py
code served (permissive licence) · get_code("1e8ea8df89540bac")
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 Tensor, ndim 0, 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
import torch.nn as nn

INIT_ARGS = {
    'alpha_t': 2.0
}

# Create small stand-in tensors for the forward pass
batch_size = 2
feature_dim = 4

# Mock output from a model (batch_size, feature_dim)
output = torch.randn(batch_size, feature_dim)

# Mock target values (batch_size, feature_dim)
target = torch.randn(batch_size, feature_dim)

# Mock class weights (batch_size,)
cls_weights = torch.ones(batch_size)

# Mock lambda parameter
myLambda = torch.tensor(0.5)

ARGS = {
    'output': output,
    'target': target,
    'cls_weights': cls_weights,
    'myLambda': myLambda
}
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 0, dtype family float — no output shape is stated: observe_signature.py observed this class with its constructor sizes canonicalised where it could, which the node does not record, so its shape is not stated as this setup block's
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 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 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 2 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

This paper studies optimization for a family of problems termed compositional entropic risk minimization, in which each data's loss is formulated as a Log-Expectation-Exponential (Log-E-Exp) function. The Log-E-Exp formulation serves as an abstraction of the Log-Sum-Exponential (LogSumExp) function when the explicit summation inside the logarithm is taken over a gigantic number of items and is therefore expensive to evaluate. While entropic risk objectives of this form arise in many machine learning problems, existing optimization algorithms suffer from several fundamental limitations including nonconvergence, numerical instability, and slow convergence rates. To address these limitations, we propose a geometry-aware stochastic algorithm, termed SCENT, for the dual formulation of entropic risk minimization cast as a min-min optimization problem. The key to our design is a stochastic proximal mirror descent (SPMD) update for the dual variable, equipped with a Bregman divergence induced by a negative exponential function that faithfully captures the geometry of the objective. Our main contributions are threefold: (i) we establish an O(1/ √ T ) convergence rate of the proposed SCENT algorithm for convex problems; (ii) we theoretically characterize the advantages of SPMD over standard SGD update for optimizing the dual variable; and (iii) we demonstrate the empirical effectiveness of SCENT on extreme classification, partial AUC maximization, contrastive learning and distributionally robust optimization, where it consistently outperforms existing baselines. Code is available at github.com/Optimization-AI/SCENT.

For agents

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

get_harvested_code_for_paper("2602.02877")
get_code_for_paper("2602.02877")
have("2602.02877")

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

curl https://syntology.ai/api/ran/2602.02877.json

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

[![Syntology run record](https://syntology.ai/api/ran/2602.02877.svg)](https://syntology.ai/paper/2602.02877)

Connect an agent — have() is free.