자료유형  

 학위논문

Control Number  

0016934558

International Standard Book Number  

9798380482653

Dewey Decimal Classification Number  

574

Main Entry-Personal Name  

Kumar, Ananya.

Publication, Distribution, etc. (Imprint  

[S.l.] : Stanford University., 2023

Publication, Distribution, etc. (Imprint  

Ann Arbor : ProQuest Dissertations & Theses, 2023

Physical Description  

1 online resource(244 p.)

General Note  

Source: Dissertations Abstracts International, Volume: 85-04, Section: B.

General Note  

Advisor: Liang, Percy;Tengyu, Tengyu.

Dissertation Note  

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

Restrictions on Access Note  

This item must not be sold to any third party vendors.

Summary, Etc.  

요약Machine learning systems are not robust to distribution shifts-they suffer large drops in accuracy when deployed in different environments from what they were trained on. For example when satellite remote sensing models are deployed in new countries, tumor detection models are deployed in new hospitals, or wildlife conservation models are deployed in new forests, they face large drops in accuracy. In this thesis, we show that the foundation model paradigm is a principled solution that leads to state-of-the-art robustness. The foundation model paradigm consists of three steps: pretraining a model on diverse unlabeled data (e.g., satellite images from around the world) to learn general-purpose representations, adapting these models to downstream tasks that we care about, and then deploying these models in the real world. This thesis will focus on understanding and improving each of these steps for robustness. (1) First, we show that pretraining on unlabeled data learns transferable representations that improves accuracy even on domains where we had no labels. We explain why pretraining can work in a very different way from some classical intuitions of collapsing representations (domain invariance). Our theory predicts phenomena on real datasets, and leads to improved pretraining methods. (2) Next, we will show that the standard approach of adaptation (updating all the model's parameters) can distort pretrained representations and perform poorly out-of-distribution. Our theoretical analysis leads to better methods for adaptation and state-of-the-art accuracies on ImageNet and in applications such as satellite remote sensing, wildlife conservation, and radiology. (3) Finally, when we deploy models in the real world, the data distribution evolves over time which leads to a drop in model performance. We show that self-training on a model's own predictions can improve robustness to distribution shift, and explain when and why self-training works.

Subject Added Entry-Topical Term  

Adaptation.

Subject Added Entry-Topical Term  

Connectivity.

Added Entry-Corporate Name  

Stanford University.

Host Item Entry  

Dissertations Abstracts International. 85-04B.

Host Item Entry  

Dissertation Abstract International

Electronic Location and Access  

로그인을 한후 보실 수 있는 자료입니다.

Control Number  

joongbu:643596