arXiv Machine Learning October 19, 2026 By Xuexing Lu

DisCo Algebra: Why Disintegration and Combination Are Not Inverses

Read the original on arXiv Machine Learning →

arXiv:2610. 15006v2 Announce Type: replace-cross Abstract: We present DisCo algebra---a compositional framework for joint probability built from a symmetric cooperad (disintegration) and a non-unital partial symmetric operad (combination restricted to the image of disintegration) on the bare family $\mathcal{P}_n=\mathrm{Prob}([0,1]^n)$.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Sep 30

Bias-variance decompositions: the exclusive privilege of Bregman divergences

arXiv:2501.18581v5 Announce Type: replace Abstract: Bias-variance decompositions are widely used to understand the generalization performance of machine learning models. While the squared error loss...

By Tom Heskes

safety

arXiv Machine Learning

Aug 12

A Joint-Distribution Route to Fair Representations with Continuous Sensitive Attributes

arXiv:2608. 10470v1 Announce Type: new Abstract: Fair representation learning with a continuous sensitive attribute $S$ requires a representation $Z$ that is statistically independent of $S$.

By Yijin Ni, Xiaoming Huo

safety

arXiv Statistics ML

Sep 25

Transitional Conditional Independence

arXiv:2104. 11547v5 Announce Type: replace-cross Abstract: Statistical models contain variables that are not random: parameters, treatments, environments, design points.

By Patrick Forr\'e

arXiv Machine Learning

Jun 30

IG-Lens: Exact Additive Probability Attribution Across Transformer Layers via Telescoping Integrated Gradients

arXiv:2606. 29693v1 Announce Type: new Abstract: We ask a simple question about decoder-only transformers: \emph{between which two layers is the probability of a predicted token actually produced?

By Duc Anh Nguyen

llms

arXiv Machine Learning

Aug 27

Drift Variation Autoencoder: Unifying Generation and Representation Learning through Conditional Posterior Flow Matching

arXiv:2608. 25138v1 Announce Type: new Abstract: Stochastic masking, cropping, or modality removal makes deterministic reconstruction an incomplete target: one observation can admit many clean completions.

By Jiarui Cao

diffusion multimodal benchmarks

arXiv Machine Learning

Aug 18

The Distributional View of Knowledge Distillation

arXiv:2608. 15215v1 Announce Type: cross Abstract: Token-level knowledge distillation (KD) matches two conditional distributions per position, yet the standard objectives compare them pointwise: a Kullback-Leibler gradient is blind to which wrong token receives probability mass.

By Gordei Verbii, Juho Lee

rag fine-tuning efficiency

One email a morning, machine-written

Related stories

Bias-variance decompositions: the exclusive privilege of Bregman divergences

A Joint-Distribution Route to Fair Representations with Continuous Sensitive Attributes

Transitional Conditional Independence

IG-Lens: Exact Additive Probability Attribution Across Transformer Layers via Telescoping Integrated Gradients

Drift Variation Autoencoder: Unifying Generation and Representation Learning through Conditional Posterior Flow Matching

The Distributional View of Knowledge Distillation