國立虎尾科技大學 |

Probabilistic Inference in the Era of Large Models.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Probabilistic Inference in the Era of Large Models./
作者:	Shih, Andy.
面頁冊數:	1 online resource (138 pages)
附註:	Source: Dissertations Abstracts International, Volume: 85-11, Section: B.
Contained By:	Dissertations Abstracts International85-11B.
標題:	Computer science. -
電子資源:	click for full text (PQDT)
ISBN:	9798382230467

Probabilistic Inference in the Era of Large Models.
Shih, Andy.

Probabilistic Inference in the Era of Large Models. - 1 online resource (138 pages)

Source: Dissertations Abstracts International, Volume: 85-11, Section: B.

Thesis (Ph.D.)--Stanford University, 2024.

Includes bibliographical references

Recent progression in generative artificial intelligence has witnessed a ballooning in model size and data dimensionality. These large models, however, come with increased computational demands which prohibit the use of many traditional probabilistic inference algorithms. There is a pressing need for new inference algorithms that are efficient enough to run on large models and modern architectures, and powerful enough to work with high dimensionalities and large datasets.In this dissertation, we address this challenge by designing algorithms using ingredients that are compatible with model scale, such as parallelization, amortized inference, and neural function approximations. We present a variety of techniques to improve sampling and inference, leading to faster sample speed, better flexibility of sample queries, and more accurate estimation of inference targets. Our methods are applicable to large models across a range of architectures such as diffusion, autoregressive, and masked-autoencoder models. We demonstrate these findings on applications spanning image and text generation, game-playing, and robotics domains. These insights lead to practical improvements and novel perspectives for efficiently deploying large-scale generative models.

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

Mode of access: World Wide Web

ISBN: 9798382230467Subjects--Topical Terms:

573171
Computer science.
Subjects--Index Terms:

Data dimensionalityIndex Terms--Genre/Form:

554714
Electronic books.

Probabilistic Inference in the Era of Large Models.
LDR:02575ntm a22003737 4500 001 1146333
005 20240812064411.5
006 m o d
007 cr bn ---uuuuu
008 250605s2024 xx obm 000 0 eng d
020 $a 9798382230467
035 $a (MiAaPQ)AAI31255810
035 $a (MiAaPQ)nt653cd4468
035 $a AAI31255810
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Shih, Andy. $3 1471707
245 1 0 $a Probabilistic Inference in the Era of Large Models.
264 0 $c 2024
300 $a 1 online resource (138 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: 85-11, Section: B.
500 $a Advisor: Stefano Ermon;Dorsa Sadigh.
502 $a Thesis (Ph.D.)--Stanford University, 2024.
504 $a Includes bibliographical references
520 $a Recent progression in generative artificial intelligence has witnessed a ballooning in model size and data dimensionality. These large models, however, come with increased computational demands which prohibit the use of many traditional probabilistic inference algorithms. There is a pressing need for new inference algorithms that are efficient enough to run on large models and modern architectures, and powerful enough to work with high dimensionalities and large datasets.In this dissertation, we address this challenge by designing algorithms using ingredients that are compatible with model scale, such as parallelization, amortized inference, and neural function approximations. We present a variety of techniques to improve sampling and inference, leading to faster sample speed, better flexibility of sample queries, and more accurate estimation of inference targets. Our methods are applicable to large models across a range of architectures such as diffusion, autoregressive, and masked-autoencoder models. We demonstrate these findings on applications spanning image and text generation, game-playing, and robotics domains. These insights lead to practical improvements and novel perspectives for efficiently deploying large-scale generative models.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2024
538 $a Mode of access: World Wide Web
650 4 $a Computer science. $3 573171
653 $a Data dimensionality
653 $a Modern architectures
653 $a Robotics domains
655 7 $a Electronic books. $2 local $3 554714
690 $a 0984
690 $a 0800
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a Stanford University. $3 1184533
773 0 $t Dissertations Abstracts International $g 85-11B.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31255810 $z click for full text (PQDT)