[{"tmp":{"legal_code_url":"https://creativecommons.org/licenses/by/4.0/legalcode","short":"CC BY (4.0)","image":"/images/cc_by.png","name":"Creative Commons Attribution 4.0 International Public License (CC-BY 4.0)"},"OA_type":"gold","file":[{"relation":"main_file","date_updated":"2025-12-16T12:45:41Z","file_size":756213,"date_created":"2025-12-16T12:45:41Z","access_level":"open_access","content_type":"application/pdf","file_id":"20830","success":1,"file_name":"2025_ICML_Nguyen.pdf","checksum":"a7edf0e4304171a3e035842b3aab1704","creator":"dernst"}],"license":"https://creativecommons.org/licenses/by/4.0/","abstract":[{"lang":"eng","text":"Modern deep neural networks exhibit heterogeneity across numerous layers of various types such as residuals, multi-head attention, etc., due to varying structures (dimensions, activation functions, etc.), distinct representation characteristics, which impact predictions. We develop a general layer-wise quantization framework with tight variance and code-length bounds, adapting to the heterogeneities over the course of training. We then apply a new layer-wise quantization technique within distributed variational inequalities (VIs), proposing a novel Quantized Optimistic Dual Averaging (QODA) algorithm with adaptive learning rates, which achieves competitive convergence rates for monotone VIs. We empirically show that QODA achieves up to a 150% speedup over the baselines in end-to-end training time for training Wasserstein GAN on 12+GPUs."}],"publication_identifier":{"eissn":["2640-3498"]},"alternative_title":["PMLR"],"language":[{"iso":"eng"}],"title":"Layer-wise quantization for quantized optimistic dual averaging","day":"01","scopus_import":"1","year":"2025","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","date_published":"2025-05-01T00:00:00Z","month":"05","ddc":["000"],"page":"46026-46072","date_created":"2025-12-14T23:02:06Z","date_updated":"2025-12-16T12:46:54Z","publication":"42nd International Conference on Machine Learning","citation":{"chicago":"Nguyen, Anh Duc, Ilia Markov, Frank Zhengqing Wu, Ali Ramezani-Kebrya, Kimon Antonakopoulos, Dan-Adrian Alistarh, and Volkan Cevher. “Layer-Wise Quantization for Quantized Optimistic Dual Averaging.” In <i>42nd International Conference on Machine Learning</i>, 267:46026–72. ML Research Press, 2025.","ama":"Nguyen AD, Markov I, Wu FZ, et al. Layer-wise quantization for quantized optimistic dual averaging. In: <i>42nd International Conference on Machine Learning</i>. Vol 267. ML Research Press; 2025:46026-46072.","short":"A.D. Nguyen, I. Markov, F.Z. Wu, A. Ramezani-Kebrya, K. Antonakopoulos, D.-A. Alistarh, V. Cevher, in:, 42nd International Conference on Machine Learning, ML Research Press, 2025, pp. 46026–46072.","apa":"Nguyen, A. D., Markov, I., Wu, F. Z., Ramezani-Kebrya, A., Antonakopoulos, K., Alistarh, D.-A., &#38; Cevher, V. (2025). Layer-wise quantization for quantized optimistic dual averaging. In <i>42nd International Conference on Machine Learning</i> (Vol. 267, pp. 46026–46072). Vancouver, Canada: ML Research Press.","ista":"Nguyen AD, Markov I, Wu FZ, Ramezani-Kebrya A, Antonakopoulos K, Alistarh D-A, Cevher V. 2025. Layer-wise quantization for quantized optimistic dual averaging. 42nd International Conference on Machine Learning. ICML: International Conference on Machine Learning, PMLR, vol. 267, 46026–46072.","mla":"Nguyen, Anh Duc, et al. “Layer-Wise Quantization for Quantized Optimistic Dual Averaging.” <i>42nd International Conference on Machine Learning</i>, vol. 267, ML Research Press, 2025, pp. 46026–72.","ieee":"A. D. Nguyen <i>et al.</i>, “Layer-wise quantization for quantized optimistic dual averaging,” in <i>42nd International Conference on Machine Learning</i>, Vancouver, Canada, 2025, vol. 267, pp. 46026–46072."},"department":[{"_id":"DaAl"}],"project":[{"_id":"8e35c14b-16d5-11f0-9cad-a3fc35339161","grant_number":"101158077","name":"FastML: Efficient and Cost-Effective Distributed Machine Learning"}],"volume":267,"file_date_updated":"2025-12-16T12:45:41Z","conference":{"location":"Vancouver, Canada","name":"ICML: International Conference on Machine Learning","start_date":"2025-07-13","end_date":"2025-07-19"},"_id":"20821","oa_version":"Published Version","oa":1,"publisher":"ML Research Press","external_id":{"arxiv":["2505.14371"]},"arxiv":1,"acknowledgement":"This work was supported by Hasler Foundation Program: Hasler Responsible AI (project number 21043). The research was also sponsored by the Army Research Office and was accomplished under Grant Number W911NF-24-1-0048. This work was further funded by the Swiss National Science Foundation (SNSF) under grant number 200021_205011. We also acknowledge project A11 of the Swiss National Supercomputing Centre (CSCS) for providing computing resources. Dan Alistarh and Ilia Markov were supported in part through the ERC Proofof-Concept grant FastML (Grant Agreement 101158077). Ali Ramezani-Kebrya was supported by the Research Council of Norway through FRIPRO Grant under project number 356103, its Centres of Excellence scheme, Integreat - Norwegian Centre for knowledge-driven machine learning under\r\nproject number 332645 - and its Centre for Research-based Innovation funding scheme (Visual Intelligence under grant no. 309439).","has_accepted_license":"1","status":"public","intvolume":"       267","author":[{"first_name":"Anh Duc","full_name":"Nguyen, Anh Duc","last_name":"Nguyen"},{"last_name":"Markov","first_name":"Ilia","id":"D0CF4148-C985-11E9-8066-0BDEE5697425","full_name":"Markov, Ilia"},{"last_name":"Wu","full_name":"Wu, Frank Zhengqing","first_name":"Frank Zhengqing"},{"last_name":"Ramezani-Kebrya","first_name":"Ali","full_name":"Ramezani-Kebrya, Ali"},{"first_name":"Kimon","full_name":"Antonakopoulos, Kimon","last_name":"Antonakopoulos"},{"last_name":"Alistarh","full_name":"Alistarh, Dan-Adrian","orcid":"0000-0003-3650-940X","first_name":"Dan-Adrian","id":"4A899BFC-F248-11E8-B48F-1D18A9856A87"},{"first_name":"Volkan","full_name":"Cevher, Volkan","last_name":"Cevher"}],"publication_status":"published","type":"conference","OA_place":"publisher","quality_controlled":"1","article_processing_charge":"No"},{"day":"02","title":"Position: It's time to act on the risk of efficient personalized text generation","user_id":"8b945eb4-e2f2-11eb-945a-df72226e66a9","year":"2025","month":"06","date_published":"2025-06-02T00:00:00Z","publication":"arXiv","date_updated":"2026-05-19T11:20:27Z","date_created":"2026-05-11T08:55:23Z","abstract":[{"lang":"eng","text":"The recent surge in high-quality open-source Generative AI text models (colloquially: LLMs), as well as efficient finetuning techniques, have opened the possibility of creating high-quality personalized models that generate text attuned to a specific individual’s needs and are capable of credibly imitating their writing style by refining an open-source model with that person’s own data. The technology to create such models is accessible to private individuals, and training and running such models can be done cheaply on consumer-grade hardware. While these advancements are a huge gain for usability and privacy, this position paper argues that the practical feasibility of impersonating specific individuals also introduces novel safety risks. For instance, this technology enables the creation of phishing emails\r\nor fraudulent social media accounts, based on small amounts of publicly available text, or by the individuals themselves to escape AI text detection. We further argue that these risks are complementary to—and distinct from—the much-discussed risks of other impersonation attacks such as image, voice, or video deepfakes, and are not adequately addressed by the larger research community, or the current generation of open- and closed-source models."}],"main_file_link":[{"url":"https://doi.org/10.48550/arXiv.2502.06560","open_access":"1"}],"OA_type":"green","corr_author":"1","language":[{"iso":"eng"}],"status":"public","acknowledgement":"This research was supported by the Scientific Service Units (SSU) of IST Austria through resources\r\nprovided by Scientific Computing (SciComp). EI was supported in part by the FWF DK VGSCO,\r\ngrant agreement number W1260-N35. AJ was supported in part by ERC Proof-of-Concept Grant\r\nFastML, grant agreement 101158077.","doi":"10.48550/arXiv.2502.06560","type":"preprint","author":[{"full_name":"Iofinova, Eugenia B","orcid":"0000-0002-7778-3221","first_name":"Eugenia B","id":"f9a17499-f6e0-11ea-865d-fdf9a3f77117","last_name":"Iofinova"},{"first_name":"Andrej","full_name":"Jovanovic, Andrej","last_name":"Jovanovic"},{"last_name":"Alistarh","orcid":"0000-0003-3650-940X","full_name":"Alistarh, Dan-Adrian","id":"4A899BFC-F248-11E8-B48F-1D18A9856A87","first_name":"Dan-Adrian"}],"publication_status":"draft","article_processing_charge":"No","related_material":{"record":[{"id":"21854","status":"public","relation":"dissertation_contains"}]},"OA_place":"repository","project":[{"_id":"8e35c14b-16d5-11f0-9cad-a3fc35339161","grant_number":"101158077","name":"FastML: Efficient and Cost-Effective Distributed Machine Learning"},{"name":"Vienna Graduate School on Computational Optimization","_id":"9B9290DE-BA93-11EA-9121-9846C619BF3A","grant_number":"W1260-N35"}],"department":[{"_id":"GradSch"},{"_id":"DaAl"}],"citation":{"ieee":"E. B. Iofinova, A. Jovanovic, and D.-A. Alistarh, “Position: It’s time to act on the risk of efficient personalized text generation,” <i>arXiv</i>. .","ista":"Iofinova EB, Jovanovic A, Alistarh D-A. Position: It’s time to act on the risk of efficient personalized text generation. arXiv, <a href=\"https://doi.org/10.48550/arXiv.2502.06560\">10.48550/arXiv.2502.06560</a>.","mla":"Iofinova, Eugenia B., et al. “Position: It’s Time to Act on the Risk of Efficient Personalized Text Generation.” <i>ArXiv</i>, doi:<a href=\"https://doi.org/10.48550/arXiv.2502.06560\">10.48550/arXiv.2502.06560</a>.","short":"E.B. Iofinova, A. Jovanovic, D.-A. Alistarh, ArXiv (n.d.).","apa":"Iofinova, E. B., Jovanovic, A., &#38; Alistarh, D.-A. (n.d.). Position: It’s time to act on the risk of efficient personalized text generation. <i>arXiv</i>. <a href=\"https://doi.org/10.48550/arXiv.2502.06560\">https://doi.org/10.48550/arXiv.2502.06560</a>","ama":"Iofinova EB, Jovanovic A, Alistarh D-A. Position: It’s time to act on the risk of efficient personalized text generation. <i>arXiv</i>. doi:<a href=\"https://doi.org/10.48550/arXiv.2502.06560\">10.48550/arXiv.2502.06560</a>","chicago":"Iofinova, Eugenia B, Andrej Jovanovic, and Dan-Adrian Alistarh. “Position: It’s Time to Act on the Risk of Efficient Personalized Text Generation.” <i>ArXiv</i>, n.d. <a href=\"https://doi.org/10.48550/arXiv.2502.06560\">https://doi.org/10.48550/arXiv.2502.06560</a>."},"_id":"21858","oa_version":"Preprint","oa":1,"external_id":{"arxiv":["2502.06560"]},"arxiv":1}]