Disentanglement by nonlinear ICA with General Incompressible-flow Networks (GIN)
A central question of representation learning asks under which conditions it is possible to reconstruct the true latent variables of an arbitrarily complex generative process. Recent breakthrough work by Khemakhem et al. (2019) on nonlinear ICA has answered this question for a broad class of conditi...
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Dokumenttyp: | Article (Journal) Kapitel/Artikel |
| Sprache: | Englisch |
| Veröffentlicht: |
14 Jan 2020
|
| In: |
Arxiv
Year: 2020, Pages: 1-23 |
| DOI: | 10.48550/arXiv.2001.04872 |
| Online-Zugang: | Verlag, lizenzpflichtig, Volltext: https://doi.org/10.48550/arXiv.2001.04872 Verlag, lizenzpflichtig, Volltext: http://arxiv.org/abs/2001.04872 |
| Verfasserangaben: | Peter Sorrenson, Carsten Rother, Ullrich Köthe |
MARC
| LEADER | 00000caa a2200000 c 4500 | ||
|---|---|---|---|
| 001 | 1810850444 | ||
| 003 | DE-627 | ||
| 005 | 20220820225255.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 220719s2020 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.48550/arXiv.2001.04872 |2 doi | |
| 035 | |a (DE-627)1810850444 | ||
| 035 | |a (DE-599)KXP1810850444 | ||
| 035 | |a (OCoLC)1341463921 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rda | ||
| 041 | |a eng | ||
| 084 | |a 28 |2 sdnb | ||
| 100 | 1 | |a Sorrenson, Peter |d 1994- |e VerfasserIn |0 (DE-588)1224419480 |0 (DE-627)1743772106 |4 aut | |
| 245 | 1 | 0 | |a Disentanglement by nonlinear ICA with General Incompressible-flow Networks (GIN) |c Peter Sorrenson, Carsten Rother, Ullrich Köthe |
| 264 | 1 | |c 14 Jan 2020 | |
| 300 | |a 23 | ||
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a Computermedien |b c |2 rdamedia | ||
| 338 | |a Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Gesehen am 19.07.2022 | ||
| 520 | |a A central question of representation learning asks under which conditions it is possible to reconstruct the true latent variables of an arbitrarily complex generative process. Recent breakthrough work by Khemakhem et al. (2019) on nonlinear ICA has answered this question for a broad class of conditional generative processes. We extend this important result in a direction relevant for application to real-world data. First, we generalize the theory to the case of unknown intrinsic problem dimension and prove that in some special (but not very restrictive) cases, informative latent variables will be automatically separated from noise by an estimating model. Furthermore, the recovered informative latent variables will be in one-to-one correspondence with the true latent variables of the generating process, up to a trivial component-wise transformation. Second, we introduce a modification of the RealNVP invertible neural network architecture (Dinh et al. (2016)) which is particularly suitable for this type of problem: the General Incompressible-flow Network (GIN). Experiments on artificial data and EMNIST demonstrate that theoretical predictions are indeed verified in practice. In particular, we provide a detailed set of exactly 22 informative latent variables extracted from EMNIST. | ||
| 650 | 4 | |a Computer Science - Machine Learning | |
| 650 | 4 | |a Statistics - Machine Learning | |
| 700 | 1 | |a Rother, Carsten |e VerfasserIn |0 (DE-588)1181464692 |0 (DE-627)1662676883 |4 aut | |
| 700 | 1 | |a Köthe, Ullrich |e VerfasserIn |0 (DE-588)123963435 |0 (DE-627)594480884 |0 (DE-576)304484520 |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Arxiv |d Ithaca, NY : Cornell University, 1991 |g (2020), Artikel-ID 2001.04872, Seite 1-23 |h Online-Ressource |w (DE-627)509006531 |w (DE-600)2225896-6 |w (DE-576)28130436X |7 nnas |a Disentanglement by nonlinear ICA with General Incompressible-flow Networks (GIN) |
| 773 | 1 | 8 | |g year:2020 |g elocationid:2001.04872 |g pages:1-23 |g extent:23 |a Disentanglement by nonlinear ICA with General Incompressible-flow Networks (GIN) |
| 856 | 4 | 0 | |u https://doi.org/10.48550/arXiv.2001.04872 |x Verlag |x Resolving-System |z lizenzpflichtig |3 Volltext |
| 856 | 4 | 0 | |u http://arxiv.org/abs/2001.04872 |x Verlag |z lizenzpflichtig |3 Volltext |
| 951 | |a AR | ||
| 992 | |a 20220719 | ||
| 993 | |a Article | ||
| 994 | |a 2020 | ||
| 998 | |g 123963435 |a Köthe, Ullrich |m 123963435:Köthe, Ullrich |d 700000 |d 708070 |d 700000 |d 728500 |e 700000PK123963435 |e 708070PK123963435 |e 700000PK123963435 |e 728500PK123963435 |k 0/700000/ |k 1/700000/708070/ |k 0/700000/ |k 1/700000/728500/ |p 3 |y j | ||
| 998 | |g 1181464692 |a Rother, Carsten |m 1181464692:Rother, Carsten |d 700000 |d 708070 |d 700000 |d 728500 |e 700000PR1181464692 |e 708070PR1181464692 |e 700000PR1181464692 |e 728500PR1181464692 |k 0/700000/ |k 1/700000/708070/ |k 0/700000/ |k 1/700000/728500/ |p 2 | ||
| 998 | |g 1224419480 |a Sorrenson, Peter |m 1224419480:Sorrenson, Peter |d 700000 |d 708070 |e 700000PS1224419480 |e 708070PS1224419480 |k 0/700000/ |k 1/700000/708070/ |p 1 |x j | ||
| 999 | |a KXP-PPN1810850444 |e 4170218353 | ||
| BIB | |a Y | ||
| JSO | |a {"title":[{"title":"Disentanglement by nonlinear ICA with General Incompressible-flow Networks (GIN)","title_sort":"Disentanglement by nonlinear ICA with General Incompressible-flow Networks (GIN)"}],"person":[{"display":"Sorrenson, Peter","roleDisplay":"VerfasserIn","role":"aut","family":"Sorrenson","given":"Peter"},{"role":"aut","display":"Rother, Carsten","roleDisplay":"VerfasserIn","given":"Carsten","family":"Rother"},{"roleDisplay":"VerfasserIn","display":"Köthe, Ullrich","role":"aut","family":"Köthe","given":"Ullrich"}],"language":["eng"],"recId":"1810850444","note":["Gesehen am 19.07.2022"],"type":{"media":"Online-Ressource","bibl":"chapter"},"id":{"eki":["1810850444"],"doi":["10.48550/arXiv.2001.04872"]},"origin":[{"dateIssuedKey":"2020","dateIssuedDisp":"14 Jan 2020"}],"name":{"displayForm":["Peter Sorrenson, Carsten Rother, Ullrich Köthe"]},"relHost":[{"title":[{"title":"Arxiv","title_sort":"Arxiv"}],"language":["eng"],"recId":"509006531","disp":"Disentanglement by nonlinear ICA with General Incompressible-flow Networks (GIN)Arxiv","type":{"bibl":"edited-book","media":"Online-Ressource"},"note":["Gesehen am 28.05.2024"],"titleAlt":[{"title":"Arxiv.org"},{"title":"Arxiv.org e-print archive"},{"title":"Arxiv e-print archive"},{"title":"De.arxiv.org"}],"part":{"extent":"23","text":"(2020), Artikel-ID 2001.04872, Seite 1-23","pages":"1-23","year":"2020"},"pubHistory":["1991 -"],"id":{"zdb":["2225896-6"],"eki":["509006531"]},"origin":[{"publisher":"Cornell University ; Arxiv.org","dateIssuedKey":"1991","dateIssuedDisp":"1991-","publisherPlace":"Ithaca, NY ; [Erscheinungsort nicht ermittelbar]"}],"physDesc":[{"extent":"Online-Ressource"}]}],"physDesc":[{"extent":"23 S."}]} | ||
| SRT | |a SORRENSONPDISENTANGL1420 | ||