Research

Paper

TESTING February 24, 2026

Defensive Generation

Authors

Gabriele Farina, Juan Carlos Perdomo

Abstract

We study the problem of efficiently producing, in an online fashion, generative models of scalar, multiclass, and vector-valued outcomes that cannot be falsified on the basis of the observed data and a pre-specified collection of computational tests. Our contributions are twofold. First, we expand on connections between online high-dimensional multicalibration with respect to an RKHS and recent advances in expected variational inequality problems, enabling efficient algorithms for the former. We then apply this algorithmic machinery to the problem of outcome indistinguishability. Our procedure, Defensive Generation, is the first to efficiently produce online outcome indistinguishable generative models of non-Bernoulli outcomes that are unfalsifiable with respect to infinite classes of tests, including those that examine higher-order moments of the generated distributions. Furthermore, our method runs in near-linear time in the number of samples and achieves the optimal, vanishing T^{-1/2} rate for generation error.

Metadata

arXiv ID: 2602.21390
Provider: ARXIV
Primary Category: cs.LG
Published: 2026-02-24
Fetched: 2026-02-26 05:00

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2602.21390v1</id>\n    <title>Defensive Generation</title>\n    <updated>2026-02-24T21:41:11Z</updated>\n    <link href='https://arxiv.org/abs/2602.21390v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2602.21390v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>We study the problem of efficiently producing, in an online fashion, generative models of scalar, multiclass, and vector-valued outcomes that cannot be falsified on the basis of the observed data and a pre-specified collection of computational tests. Our contributions are twofold. First, we expand on connections between online high-dimensional multicalibration with respect to an RKHS and recent advances in expected variational inequality problems, enabling efficient algorithms for the former. We then apply this algorithmic machinery to the problem of outcome indistinguishability. Our procedure, Defensive Generation, is the first to efficiently produce online outcome indistinguishable generative models of non-Bernoulli outcomes that are unfalsifiable with respect to infinite classes of tests, including those that examine higher-order moments of the generated distributions. Furthermore, our method runs in near-linear time in the number of samples and achieves the optimal, vanishing T^{-1/2} rate for generation error.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.LG'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='stat.ML'/>\n    <published>2026-02-24T21:41:11Z</published>\n    <arxiv:primary_category term='cs.LG'/>\n    <author>\n      <name>Gabriele Farina</name>\n    </author>\n    <author>\n      <name>Juan Carlos Perdomo</name>\n    </author>\n  </entry>"
}