SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2010.05893 · NeurIPS · 2020

Large-Scale Methods for Distributionally Robust Optimization

John Duchi, Yair Carmon, Aaron Sidford, Daniel Levy

arXiv · PDF · Open in the Atlas

Code that ran

3 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; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 3 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/2010.05893.json · badge: /api/ran/2010.05893.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
daniellevy/fast-dro canonical (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
FunctionStatusWhere it lives
chi_square_value Ran
ran; our contract draft was wrong, not the code
daniellevy/fast-dro/robust_losses.py
code served (permissive licence) · get_code("0267157a4a1ac6e6")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned Tensor, 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 torch

torch.manual_seed(0)

# p is a probability distribution (should sum to 1 or close to it)
# m is the size of p, which is p.shape[0]
m = 5
p = torch.softmax(torch.randn(m), dim=0)

# v is a vector of the same size as p
v = torch.randn(m)

# reg is a regularization scalar
reg = 0.1

ARGS = {
    'p': p,
    'v': v,
    'reg': reg
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
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, 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
cvar_value Ran
ran; our contract draft was wrong, not the code
daniellevy/fast-dro/robust_losses.py
code served (permissive licence) · get_code("2b8de0efd0313a25")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned Tensor, 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 torch
import numpy as np

torch.manual_seed(0)

# Create a probability distribution p (must sum to 1 and be non-negative)
m = 5
p = torch.tensor([0.1, 0.2, 0.3, 0.25, 0.15], dtype=torch.float32)

# Create a value vector v (same shape as p)
v = torch.tensor([1.0, 2.0, 3.0, 4.0, 5.0], dtype=torch.float32)

# Regularization parameter
reg = 0.5

ARGS = {
    'p': p,
    'v': v,
    'reg': reg
}
Setup block drafted by
a language model, Claude Sonnet 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 Tensor, 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
fenchel_kl_cvar Ran
ran; our contract draft was wrong, not the code
daniellevy/fast-dro/robust_losses.py
code served (permissive licence) · get_code("ad7dd9787d3e8805")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned Tensor, 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 torch
import numpy as np

torch.manual_seed(0)

# Create a small tensor for v
# The function expects a 1D tensor (or at least indexable by v.shape[0])
v = torch.randn(6)

# alpha is a scalar between 0 and 1 (typical for CVaR)
alpha = 0.3

ARGS = {
    'v': v,
    'alpha': alpha
}
Setup block drafted by
a language model, Claude Sonnet 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 Tensor, 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

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, 3 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 3 later) and 0 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
cvar_value 5 other papers
5 later
2302.02931 (2023-02)
Bitrate-Constrained DRO: Beyond Worst Case Robustness To Unknown Group Shifts
2307.03306 (2023-07)
When Fair Classification Meets Noisy Protected Attributes
2309.06717 (2023-09)
Bias Amplification Enhances Minority Group Performance
and 2 more not named here
fenchel_kl_cvar 2 other papers
2 later
2307.03306 (2023-07)
When Fair Classification Meets Noisy Protected Attributes
2410.07395 (2024-10)
LLM Embeddings Improve Test-time Adaptation to Tabular $Y|X$-Shifts
chi_square_value 1 other paper
1 later
2307.03306 (2023-07)
When Fair Classification Meets Noisy Protected Attributes

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

We propose and analyze algorithms for distributionally robust optimization of convex losses with conditional value at risk (CVaR) and χ 2 divergence uncertainty sets. We prove that our algorithms require a number of gradient evaluations independent of training set size and number of parameters, making them suitable for large-scale applications. For χ 2 uncertainty sets these are the first such guarantees in the literature, and for CVaR our guarantees scale linearly in the uncertainty level rather than quadratically as in previous work. We also provide lower bounds proving the worst-case optimality of our algorithms for CVaR and a penalized version of the χ 2 problem. Our primary technical contributions are novel bounds on the bias of batch robust risk estimation and the variance of a multilevel Monte Carlo gradient estimator due to Blanchet and Glynn [7]. Experiments on MNIST and ImageNet confirm the theoretical scaling of our algorithms, which are 9-36 times more efficient than full-batch methods.

For agents

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

get_harvested_code_for_paper("2010.05893")
get_code_for_paper("2010.05893")
have("2010.05893")

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

curl https://syntology.ai/api/ran/2010.05893.json

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

[![Syntology run record](https://syntology.ai/api/ran/2010.05893.svg)](https://syntology.ai/paper/2010.05893)

Connect an agent — have() is free.