{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/129683"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/129683","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"ApproxTuner 2.0: Towards quality-driven approximation tuning","abstract":"Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2027-05-01","abstract_html":"Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2027-05-01","abstract_has_math":false,"creators":["Rambhia, Vidhi"],"institution":"University of Illinois Urbana-Champaign","degree_name":"M.S.","degree_level":"Thesis","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Adve, Vikram"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2025,"date_issued":"2025-04-10","date_published":"2025-04-10","updated_at":"2026-07-22T22:25:05Z","subjects":["Approximate Computing","Approximation Tuning","Edge Computing","Model Optimization","Model Merging"],"languages":["en","eng"],"rights":["Copyright 2025 Vidhi Rambhia"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/2142/129683","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Adve, Vikram"]},{"key":"dc:creator","label":"Author","values":["Rambhia, Vidhi"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2025-04-10","2025-05"]},{"key":"dc:type","label":"Dc Type","values":["text","Thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["M.S."]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Illinois Urbana-Champaign"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Approximate Computing","Approximation Tuning","Edge Computing","Model Optimization","Model Merging"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en","eng"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2025 Vidhi Rambhia"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://hdl.handle.net/2142/129683"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2027-05-01","The student, Vidhi Rambhia, accepted the attached license on 2025-04-09 at 18:40.","The student, Vidhi Rambhia, submitted this Thesis for approval on 2025-04-09 at 19:47.","This Thesis was approved for publication on 2025-04-10 at 10:54.","DSpace SAF Submission Ingestion Package generated from Vireo submission #21734 on 2025-10-19 at 19:52:48","Deploying deep neural networks in real-world applications often requires a balance between model fidelity and resource efficiency. Traditional approximation techniques are usually applied in isolation and evaluated using proxy metrics such as accuracy, which may not reflect actual downstream task performance. This work presents ApproxTuner 2.0 building on top of ApproxTuner [1] and [2], a system for application-aware approximation tuning that puts the downstream task at the center of the optimization process. This system explores a configuration space of approximations using modular, pluggable components—knobs, applications, and QoS evaluators—and scores each configuration using domain-specific metrics that directly reflect utility. We validate our approach across two case studies, monocular depth estimation with DepthAnythingV2 and object tracking with YOLOv8, demonstrating that ApproxTuner can uncover configurations with 4× speedups without compromising application-level quality. Complementing this, we also discuss LEWIS (LayEr-WIse Sparsity) [3], a guided model merging technique that approximates traditional fine-tuning by combining task vectors from pre-trained models. Rather than relying on expensive retraining or naive averaging, LEWIS uses layerwise-activation norm deltas to guide sparsity during model merging. This offers a practical approximation of fine-tuning, especially in resource-constrained scenarios. Our experiments demonstrate that LEWIS significantly improves model merging effectiveness. Together, ApproxTuner and LEWIS represent two complementary axes of approximate computing for real-world AI: one focuses on tuning approximation strategies for a given model and a downstream task, and the other facilitates rapid adaptation across tasks by approximating fine-tuning itself."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["ApproxTuner 2.0: Towards quality-driven approximation tuning"]}]}],"canonical_facts":{"dc:contributor":["Adve, Vikram"],"dc:creator":["Rambhia, Vidhi"],"dc:date":["2025-04-10","2025-05"],"dc:description":["Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2027-05-01","The student, Vidhi Rambhia, accepted the attached license on 2025-04-09 at 18:40.","The student, Vidhi Rambhia, submitted this Thesis for approval on 2025-04-09 at 19:47.","This Thesis was approved for publication on 2025-04-10 at 10:54.","DSpace SAF Submission Ingestion Package generated from Vireo submission #21734 on 2025-10-19 at 19:52:48","Deploying deep neural networks in real-world applications often requires a balance between model fidelity and resource efficiency. Traditional approximation techniques are usually applied in isolation and evaluated using proxy metrics such as accuracy, which may not reflect actual downstream task performance. This work presents ApproxTuner 2.0 building on top of ApproxTuner [1] and [2], a system for application-aware approximation tuning that puts the downstream task at the center of the optimization process. This system explores a configuration space of approximations using modular, pluggable components—knobs, applications, and QoS evaluators—and scores each configuration using domain-specific metrics that directly reflect utility. We validate our approach across two case studies, monocular depth estimation with DepthAnythingV2 and object tracking with YOLOv8, demonstrating that ApproxTuner can uncover configurations with 4× speedups without compromising application-level quality. Complementing this, we also discuss LEWIS (LayEr-WIse Sparsity) [3], a guided model merging technique that approximates traditional fine-tuning by combining task vectors from pre-trained models. Rather than relying on expensive retraining or naive averaging, LEWIS uses layerwise-activation norm deltas to guide sparsity during model merging. This offers a practical approximation of fine-tuning, especially in resource-constrained scenarios. Our experiments demonstrate that LEWIS significantly improves model merging effectiveness. Together, ApproxTuner and LEWIS represent two complementary axes of approximate computing for real-world AI: one focuses on tuning approximation strategies for a given model and a downstream task, and the other facilitates rapid adaptation across tasks by approximating fine-tuning itself."],"dc:format":["application/pdf"],"dc:identifier":["https://hdl.handle.net/2142/129683"],"dc:language":["en","eng"],"dc:rights":["Copyright 2025 Vidhi Rambhia"],"dc:subject":["Approximate Computing","Approximation Tuning","Edge Computing","Model Optimization","Model Merging"],"dc:title":["ApproxTuner 2.0: Towards quality-driven approximation tuning"],"dc:type":["text","Thesis"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["M.S."],"thesis:institution_name":["University of Illinois Urbana-Champaign"]},"updated_at":"2026-07-22T22:25:05Z"}