Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2509.23825 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914062008320000 |
|---|---|
| author | Kolesov, Alexander Manukhov, Stepan Palyulin, Vladimir V. Korotin, Alexander |
| author_facet | Kolesov, Alexander Manukhov, Stepan Palyulin, Vladimir V. Korotin, Alexander |
| contents | We propose $\textbf{E}$lectric $\textbf{C}$urrent $\textbf{D}$iscrete $\textbf{D}$ata $\textbf{G}$eneration (ECD$^{2}$G), a pioneering method for data generation in discrete settings that is grounded in electrical engineering theory. Our approach draws an analogy between electric current flow in a circuit and the transfer of probability mass between data distributions. We interpret samples from the source distribution as current input nodes of a circuit and samples from the target distribution as current output nodes. A neural network is then used to learn the electric currents to represent the probability flow in the circuit. To map the source distribution to the target, we sample from the source and transport these samples along the circuit pathways according to the learned currents. This process provably guarantees transfer between data distributions. We present proof-of-concept experiments to illustrate our ECD$^{2}$G method. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_23825 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Electric Currents for Discrete Data Generation Kolesov, Alexander Manukhov, Stepan Palyulin, Vladimir V. Korotin, Alexander Machine Learning We propose $\textbf{E}$lectric $\textbf{C}$urrent $\textbf{D}$iscrete $\textbf{D}$ata $\textbf{G}$eneration (ECD$^{2}$G), a pioneering method for data generation in discrete settings that is grounded in electrical engineering theory. Our approach draws an analogy between electric current flow in a circuit and the transfer of probability mass between data distributions. We interpret samples from the source distribution as current input nodes of a circuit and samples from the target distribution as current output nodes. A neural network is then used to learn the electric currents to represent the probability flow in the circuit. To map the source distribution to the target, we sample from the source and transport these samples along the circuit pathways according to the learned currents. This process provably guarantees transfer between data distributions. We present proof-of-concept experiments to illustrate our ECD$^{2}$G method. |
| title | Electric Currents for Discrete Data Generation |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2509.23825 |