國立虎尾科技大學 |

But What Did You Actually Learn? Improving Inference for Non-Identifiable Deep Latent Variable Models.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	But What Did You Actually Learn? Improving Inference for Non-Identifiable Deep Latent Variable Models./
作者:	Yacoby, Yaniv.
面頁冊數:	1 online resource (293 pages)
附註:	Source: Dissertations Abstracts International, Volume: 84-12, Section: B.
Contained By:	Dissertations Abstracts International84-12B.
標題:	Statistics. -
電子資源:	click for full text (PQDT)
ISBN:	9798379604813

But What Did You Actually Learn? Improving Inference for Non-Identifiable Deep Latent Variable Models.
Yacoby, Yaniv.

But What Did You Actually Learn? Improving Inference for Non-Identifiable Deep Latent Variable Models. - 1 online resource (293 pages)

Source: Dissertations Abstracts International, Volume: 84-12, Section: B.

Thesis (Ph.D.)--Harvard University, 2023.

Includes bibliographical references

Deep probabilistic and Bayesian latent variable models allow one to infer variables that have previously not been observed in the data in order to accurately model the data density. They provide an intuitive and flexible modeling paradigm, making them particularly well-suited for safety-critical applications, in which the data is often noisy and complex, requiring expressivity from deep learning, and assumptions need to be well-understood and easily interrogated to ensure safety, requiring an intuitive model specification process. However, this model class comes with several challenges. First, as model complexity grows, so does the possibility for model non-identifiability---the existence of multiple models (or parameterizations of the same models) that explain the observed data equally well. This means that, while the model specification process is intuitive, the results of inference may not be. Second, inference for such models is intractable, requiring approximations. Unfortunately, these approximations require us to make additional assumptions. But unlike the assumptions made in the original model specification, these inference assumptions are highly unintuitive. As such, in safety-critical domains, they present a significant barrier for use. Moreover, these inference assumptions may impact downstream decision-making in unpredictable (and undesirable) ways. This dissertation is focused on (a) understanding how non-identifiability compromises the quality of approximate inference for deep probabilistic and Bayesian latent variable models, and (b) developing novel approximate inference methods that mitigate or accommodate non-identifiability to achieve better performance on downstream tasks.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2024

Mode of access: World Wide Web

ISBN: 9798379604813Subjects--Topical Terms:

556824
Statistics.
Subjects--Index Terms:

Bayesian statisticsIndex Terms--Genre/Form:

554714
Electronic books.

But What Did You Actually Learn? Improving Inference for Non-Identifiable Deep Latent Variable Models.
LDR:03131ntm a22003977 4500 001 1148689
005 20240930100117.5
006 m o d
007 cr bn ---uuuuu
008 250605s2023 xx obm 000 0 eng d
020 $a 9798379604813
035 $a (MiAaPQ)AAI30491461
035 $a AAI30491461
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Yacoby, Yaniv. $3 1474714
245 1 0 $a But What Did You Actually Learn? Improving Inference for Non-Identifiable Deep Latent Variable Models.
264 0 $c 2023
300 $a 1 online resource (293 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertations Abstracts International, Volume: 84-12, Section: B.
500 $a Advisor: Doshi-Velez, F.
502 $a Thesis (Ph.D.)--Harvard University, 2023.
504 $a Includes bibliographical references
520 $a Deep probabilistic and Bayesian latent variable models allow one to infer variables that have previously not been observed in the data in order to accurately model the data density. They provide an intuitive and flexible modeling paradigm, making them particularly well-suited for safety-critical applications, in which the data is often noisy and complex, requiring expressivity from deep learning, and assumptions need to be well-understood and easily interrogated to ensure safety, requiring an intuitive model specification process. However, this model class comes with several challenges. First, as model complexity grows, so does the possibility for model non-identifiability---the existence of multiple models (or parameterizations of the same models) that explain the observed data equally well. This means that, while the model specification process is intuitive, the results of inference may not be. Second, inference for such models is intractable, requiring approximations. Unfortunately, these approximations require us to make additional assumptions. But unlike the assumptions made in the original model specification, these inference assumptions are highly unintuitive. As such, in safety-critical domains, they present a significant barrier for use. Moreover, these inference assumptions may impact downstream decision-making in unpredictable (and undesirable) ways. This dissertation is focused on (a) understanding how non-identifiability compromises the quality of approximate inference for deep probabilistic and Bayesian latent variable models, and (b) developing novel approximate inference methods that mitigate or accommodate non-identifiability to achieve better performance on downstream tasks.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2024
538 $a Mode of access: World Wide Web
650 4 $a Statistics. $3 556824
650 4 $a Computer science. $3 573171
653 $a Bayesian statistics
653 $a Deep learning
653 $a Latent variable models
653 $a Non-identifiability
653 $a Variational inference
655 7 $a Electronic books. $2 local $3 554714
690 $a 0800
690 $a 0463
690 $a 0984
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a Harvard University. $b Engineering and Applied Sciences - Computer Science. $3 1467916
773 0 $t Dissertations Abstracts International $g 84-12B.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30491461 $z click for full text (PQDT)