[{"abstract":[{"lang":"eng","text":"As neural-network-based models grow both in size and popularity, interest has grown in making the models smaller and more efficient to train. To that end, many methods have been proposed to prune models by reducing their number of nonzero parameters. Additionally, parameter-efficient fine-tuning, in which a much smaller number of parameters than the total contained in the model is updated during training, has become very popular, especially in the space of Large Language Models. At the same time, the increasingly routine deployment of machine learning in real-world applications has spurred a drive to make them more trustworthy - in the sense of, among other things, being unbiased, interpretable, and editable. In this thesis, we examine the interplay between efficiency and trustworthiness.\r\n\r\nFirst, we analyze the effects of model pruning on bias in computer vision models, demonstrating that increased sparsity leads to greater bias, largely as a function of increased model uncertainty in marginal cases. Based on this observation, we propose several bias mitigation techniques. Then, we demonstrate that example-specific model pruning can improve model interpretation methods while improving pruning efficiency to make example-specific model pruning feasible in real time. Then, we investigate the effectiveness of parameter-efficient and data-efficient model personalization via fine-tuning, demonstrating that it is highly feasible with very small computational and data resources. Finally, we consider efficiency in editing model knowledge using a custom synthetic data framework, demonstrating that parameter-efficient, low-rank fine-tuning frequently outperforms full-rank fine-tuning, and, additionally, that restricting which model blocks are fine-tuned frequently improves results. Together, the results in this thesis provide new insights and techniques for combining trustworthiness and efficiency during neural network inference and training.\r\n\r\n-----------------“In reference to IEEE copyrighted material which is used with permission in this thesis, the IEEE does not endorse any of [name of university or educational entity]’s products or services. Internal or personal use of this material is permitted. If interested in reprinting/republishing IEEE copyrighted material for advertising or promotional purposes or for creating new collective works for resale or redistribution, please go to http://www.ieee.org/publications_standards/publications/rights/rights_link.html to learn how to obtain a License from RightsLink. If applicable, University Microfilms and/or ProQuest Library, or the Archives of Canada may supply single copies of the dissertation.”"}],"publication_identifier":{"issn":["2663-337X"]},"file":[{"file_id":"21856","content_type":"application/zip","creator":"eiofinov","checksum":"2e148dad920e3f9b7c32796e0ba2e5f7","file_name":"EIofinova_thesis_FinalVersion.zip","access_level":"closed","date_created":"2026-05-11T08:36:01Z","file_size":28479571,"relation":"source_file","date_updated":"2026-05-11T08:36:01Z"},{"file_name":"2026_Iofinova_Eugenia_Thesis.pdf","checksum":"b10c2933f386f532b2dbf28b19c5525c","creator":"eiofinov","content_type":"application/pdf","file_id":"21877","success":1,"relation":"main_file","date_updated":"2026-05-13T13:10:48Z","file_size":18137757,"date_created":"2026-05-13T13:10:48Z","access_level":"open_access"}],"corr_author":"1","language":[{"iso":"eng"}],"alternative_title":["ISTA Thesis"],"degree_awarded":"PhD","month":"05","date_published":"2026-05-11T00:00:00Z","date_updated":"2026-05-19T11:20:28Z","date_created":"2026-05-11T08:43:22Z","page":"237","ddc":["000"],"day":"11","title":"On the utility and effects of efficiency in artificial neural networks","user_id":"8b945eb4-e2f2-11eb-945a-df72226e66a9","year":"2026","acknowledged_ssus":[{"_id":"ScienComp"}],"publisher":"Institute of Science and Technology Austria","project":[{"name":"Vienna Graduate School on Computational Optimization","grant_number":"W1260-N35","_id":"9B9290DE-BA93-11EA-9121-9846C619BF3A"}],"citation":{"ieee":"E. B. Iofinova, “On the utility and effects of efficiency in artificial neural networks,” Institute of Science and Technology Austria, 2026.","mla":"Iofinova, Eugenia B. <i>On the Utility and Effects of Efficiency in Artificial Neural Networks</i>. Institute of Science and Technology Austria, 2026, doi:<a href=\"https://doi.org/10.15479/AT-ISTA-21854\">10.15479/AT-ISTA-21854</a>.","ista":"Iofinova EB. 2026. On the utility and effects of efficiency in artificial neural networks. Institute of Science and Technology Austria.","ama":"Iofinova EB. On the utility and effects of efficiency in artificial neural networks. 2026. doi:<a href=\"https://doi.org/10.15479/AT-ISTA-21854\">10.15479/AT-ISTA-21854</a>","apa":"Iofinova, E. B. (2026). <i>On the utility and effects of efficiency in artificial neural networks</i>. Institute of Science and Technology Austria. <a href=\"https://doi.org/10.15479/AT-ISTA-21854\">https://doi.org/10.15479/AT-ISTA-21854</a>","short":"E.B. Iofinova, On the Utility and Effects of Efficiency in Artificial Neural Networks, Institute of Science and Technology Austria, 2026.","chicago":"Iofinova, Eugenia B. “On the Utility and Effects of Efficiency in Artificial Neural Networks.” Institute of Science and Technology Austria, 2026. <a href=\"https://doi.org/10.15479/AT-ISTA-21854\">https://doi.org/10.15479/AT-ISTA-21854</a>."},"department":[{"_id":"GradSch"},{"_id":"DaAl"}],"_id":"21854","oa_version":"Published Version","oa":1,"file_date_updated":"2026-05-13T13:10:48Z","type":"dissertation","publication_status":"published","author":[{"first_name":"Eugenia B","id":"f9a17499-f6e0-11ea-865d-fdf9a3f77117","orcid":"0000-0002-7778-3221","full_name":"Iofinova, Eugenia B","last_name":"Iofinova"}],"article_processing_charge":"No","OA_place":"publisher","supervisor":[{"id":"4A899BFC-F248-11E8-B48F-1D18A9856A87","first_name":"Dan-Adrian","full_name":"Alistarh, Dan-Adrian","orcid":"0000-0003-3650-940X","last_name":"Alistarh"}],"related_material":{"record":[{"status":"public","id":"14771","relation":"part_of_dissertation"},{"relation":"part_of_dissertation","status":"public","id":"18121"},{"relation":"part_of_dissertation","id":"21858","status":"public"},{"status":"public","id":"21859","relation":"part_of_dissertation"},{"relation":"part_of_dissertation","status":"public","id":"21857"}]},"acknowledgement":"The research in this Ph.D. was funded in whole\r\nor in part by the Austrian Science Fund (FWF) W1260-N35 (Vienna Graduate School for\r\nComputational Optimization). For open access purposes the author has applied a CC BY\r\npublic copyright license to any author accepted manuscript version arising from this submission\r\nwherever possible. Additionally, I am grateful to Alois Schlögl, Waleed Khalid, and the rest of\r\nthe ISTA Scientific Computing team for building and maintaining the infrastructure I used\r\nto run experiments. I’m also deeply grateful to the Alistarh group’s administrative assistant,\r\nChristine Francois, who always deals with our nonsense with common sense and a smile.\r\n","status":"public","has_accepted_license":"1","doi":"10.15479/AT-ISTA-21854"}]