arXiv Machine Learning By Mikhail Persiianov, Arip Asadulaev, Nikita Andreev, Nikita Starodubcev, Dmitry Baranchuk, Anastasis Kratsios, Evgeny Burnaev, Alexander Korotin

Inverse Entropic Optimal Transport Solves Semi-supervised Learning via Data Likelihood Maximization

Read the original on arXiv Machine Learning →

arXiv:2410. 02628v5 Announce Type: replace Abstract: Learning conditional distributions $\pi^*(\cdot|x)$ is a central problem in machine learning, which is typically approached via supervised methods with paired data $(x,y) \sim \pi^*$.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv AI
Jul 7

Machine Unlearning via Information Theoretic Regularization

arXiv:2502. 05684v5 Announce Type: replace-cross Abstract: How can we effectively remove or ``unlearn'' undesirable information, such as specific features or the influence of individual data points, from a learning outcome while minimizing utility loss and ensuring rigorous guarantees?

By Shizhou Xu, Thomas Strohmer
arXiv AI
Jun 10

MMD Guidance: Training-Free Distribution Adaptation for Diffusion Models via Maximum Mean Discrepancy Guidance

arXiv:2601. 08379v2 Announce Type: replace-cross Abstract: Pre-trained diffusion models have emerged as powerful generative priors for both unconditional and conditional sample generation, yet their outputs often deviate from the characteristics of user-specific target data.

By Matina Mahdizadeh Sani, Nima Jamali, Mohammad Jalali, Farzan Farnia
arXiv Machine Learning
Jun 26

Learning from a Biased Sample

arXiv:2209. 01754v5 Announce Type: replace-cross Abstract: The empirical risk minimization approach to data-driven decision making requires access to training data drawn under the same conditions as those that will be faced when the decision rule is deployed.

By Roshni Sahoo, Lihua Lei, Stefan Wager
arXiv Machine Learning
Jun 5

Variational Entropic Optimal Transport

arXiv:2602. 02241v2 Announce Type: replace Abstract: Entropic optimal transport (EOT) in continuous spaces with quadratic cost is a classical tool for solving the domain translation problem.

By Roman Dyachenko, Nikita Gushchin, Kirill Sokolov, Petr Mokrov, Evgeny Burnaev, Alexander Korotin