<?xml version="1.0" encoding="UTF-8"?><?xml-stylesheet type="text/xsl" href="static/style.xsl"?><OAI-PMH xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/ http://www.openarchives.org/OAI/2.0/OAI-PMH.xsd"><responseDate>2026-11-22T20:06:30Z</responseDate><request verb="GetRecord" identifier="oai:digital.lib.washington.edu:1773/53496" metadataPrefix="dim">https://digital.lib.washington.edu/server/oai/request</request><GetRecord><record><header><identifier>oai:digital.lib.washington.edu:1773/53496</identifier><datestamp>2026-02-16T02:09:20Z</datestamp><setSpec>com_1773_4888</setSpec><setSpec>col_1773_4909</setSpec></header><metadata><dim:dim xmlns:dim="http://www.dspace.org/xmlns/dspace/dim" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:doc="http://www.lyncode.com/xoai" xsi:schemaLocation="http://www.dspace.org/xmlns/dspace/dim http://www.dspace.org/schema/dim.xsd">
   <dim:field mdschema="dc" element="contributor" qualifier="advisor">Ceze, Luis</dim:field>
   <dim:field mdschema="dc" element="contributor" qualifier="author">Lin, Chien-Yu</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="accessioned">2025-08-01T22:19:27Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="available">2025-08-01T22:19:27Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="issued">2025-08-01</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="submitted">2025</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="other">Lin_washington_0250E_28591.pdf</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="uri">https://hdl.handle.net/1773/53496</dim:field>
   <dim:field mdschema="dc" element="description">Thesis (Ph.D.)--University of Washington, 2025</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="abstract">The rapid growth of machine learning - in terms of model size, dataset volume, and task complexity - has created significant computational and memory efficiency challenges. This thesis addresses these challenges by developing sampling and compression techniques across a variety of machine learning applications. Specifically, we introduce sampling strategies for efficient graph neural networks (CacheSample), accelerated 3D image rendering (FastSR-NeRF), and optimized retrieval-augmented generation systems (TeleRAG). We further propose novel compression methods targeting convolutional neural networks (SPIN), large language models (Atom), and their key-value caches (Palu). Collectively, these techniques substantially reduce computational and memory requirements while preserving model accuracy, facilitating the scalability and accessibility of machine learning systems. Finally, I present my vision for future efficiency innovations to ensure continued scalability and robustness as machine learning models continue to grow in complexity.</dim:field>
   <dim:field mdschema="dc" element="format" qualifier="mimetype">application/pdf</dim:field>
   <dim:field mdschema="dc" element="language" qualifier="iso">en_US</dim:field>
   <dim:field mdschema="dc" element="rights">none</dim:field>
   <dim:field mdschema="dc" element="subject">efficient machine learning</dim:field>
   <dim:field mdschema="dc" element="subject">machine learning system</dim:field>
   <dim:field mdschema="dc" element="subject">Computer science</dim:field>
   <dim:field mdschema="dc" element="subject" qualifier="other">Computer science and engineering</dim:field>
   <dim:field mdschema="dc" element="title">Toward Efficient Machine Learning Systems with Sampling and Compression.</dim:field>
   <dim:field mdschema="dc" element="type">Thesis</dim:field>
   <dim:field mdschema="dc" element="embargo" qualifier="terms">Open Access</dim:field>
   <dim:field mdschema="others" element="access-status">open.access</dim:field>
</dim:dim>
</metadata></record></GetRecord></OAI-PMH>