{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T07:44:34Z","timestamp":1777016674702,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":73,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,12,17]]},"DOI":"10.1145\/3799830.3799837","type":"proceedings-article","created":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T06:45:08Z","timestamp":1777013108000},"page":"62-70","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Hierarchical Sparse Plus Low Rank Compression of LLM"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5632-6964","authenticated-orcid":false,"given":"pawan","family":"kumar","sequence":"first","affiliation":[{"name":"International Institute of Information Technology, Hyderabad, Hyderabad, India"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-3725-9482","authenticated-orcid":false,"given":"Aditi","family":"Gupta","sequence":"additional","affiliation":[{"name":"International Institute of Information Technology, Hyderabad, Hyderabad, India"}]}],"member":"320","published-online":{"date-parts":[[2026,4,23]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"publisher","unstructured":"Patrick\u00a0R. Amestoy Timothy\u00a0A. Davis and Iain\u00a0S. Duff. 2004. Algorithm 837: AMD an approximate minimum degree ordering algorithm. ACM Trans. Math. Softw. 30 3 (Sept. 2004) 381\u2013388. 10.1145\/1024074.1024081","DOI":"10.1145\/1024074.1024081"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"crossref","unstructured":"Roman Andreev and Christine Tobler. 2015. Multilevel preconditioning and low\u2010rank tensor iteration for space\u2013time simultaneous discretizations of parabolic PDEs. Numerical Linear Algebra with Applications 22 (2015) 317 \u2013 337. https:\/\/api.semanticscholar.org\/CorpusID:17872441","DOI":"10.1002\/nla.1951"},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"crossref","unstructured":"Owe Axelsson. 1985. A survey of preconditioned iterative methods for linear systems of algebraic equations. BIT Numerical Mathematics 25 (1985) 165\u2013187. https:\/\/api.semanticscholar.org\/CorpusID:121072077","DOI":"10.1007\/BF01934996"},{"key":"e_1_3_3_1_5_2","unstructured":"Seyedarmin Azizi Mahdi Nazemi and Massoud Pedram. 2024. Memory-Efficient Vision Transformers: An Activation-Aware Mixed-Rank Compression Strategy. arXiv:https:\/\/arXiv.org\/abs\/2402.06004\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2402.06004"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"crossref","unstructured":"Zhong\u2010Zhi Bai. 2005. Structured preconditioners for nonsingular matrices of block two-by-two structures. Math. Comput. 75 (2005) 791\u2013815. https:\/\/api.semanticscholar.org\/CorpusID:14744070","DOI":"10.1090\/S0025-5718-05-01801-6"},{"key":"e_1_3_3_1_7_2","unstructured":"Dimitris Bertsimas Ryan Cory-Wright and Nicholas A.\u00a0G. Johnson. 2023. Sparse Plus Low Rank Matrix Decomposition: A Discrete Optimization Approach. arXiv:https:\/\/arXiv.org\/abs\/2109.12701\u00a0[stat.ML] https:\/\/arxiv.org\/abs\/2109.12701"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"publisher","unstructured":"Boris Bonev and Jan\u00a0S. Hesthaven. 2022. A Hierarchical Preconditioner for Wave Problems in Quasilinear Complexity. SIAM Journal on Scientific Computing 44 1 (Jan. 2022) A198\u2013A229. 10.1137\/20m1365958","DOI":"10.1137\/20m1365958"},{"key":"e_1_3_3_1_9_2","unstructured":"Tom\u00a0B. Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell Sandhini Agarwal Ariel Herbert-Voss Gretchen Krueger Tom Henighan Rewon Child Aditya Ramesh Daniel\u00a0M. Ziegler Jeffrey Wu Clemens Winter Christopher Hesse Mark Chen Eric Sigler Mateusz Litwin Scott Gray Benjamin Chess Jack Clark Christopher Berner Sam McCandlish Alec Radford Ilya Sutskever and Dario Amodei. 2020. Language Models are Few-Shot Learners. arXiv:https:\/\/arXiv.org\/abs\/2005.14165\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2005.14165"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"publisher","unstructured":"Venkat Chandrasekaran Sujay Sanghavi Pablo\u00a0A. Parrilo and Alan\u00a0S. Willsky. 2009. Sparse and Low-Rank Matrix Decompositions. IFAC Proceedings Volumes 42 10 (2009) 1493\u20131498. 10.3182\/20090706-3-FR-2004.0024915th IFAC Symposium on System Identification.","DOI":"10.3182\/20090706-3-FR-2004.00249"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-93620-4_16"},{"key":"e_1_3_3_1_12_2","unstructured":"Mark Chen Jerry Tworek Heewoo Jun et\u00a0al. 2021. Evaluating Large Language Models Trained on Code. arXiv:https:\/\/arXiv.org\/abs\/2107.03374\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2107.03374"},{"key":"e_1_3_3_1_13_2","unstructured":"Krzysztof Choromanski Valerii Likhosherstov David Dohan Xingyou Song Andreea Gane Tamas Sarlos Peter Hawkins Jared Davis Afroz Mohiuddin Lukasz Kaiser David Belanger Lucy Colwell and Adrian Weller. 2022. Rethinking Attention with Performers. arXiv:https:\/\/arXiv.org\/abs\/2009.14794\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2009.14794"},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"publisher","unstructured":"Tianshu Chu Kun Fang Jie Yang and Xiaolin Huang. 2023. Improving the adversarial robustness of quantized neural networks via exploiting the feature diversity. Pattern Recogn. Lett. 176 C (Dec. 2023) 117\u2013122. 10.1016\/j.patrec.2023.10.024","DOI":"10.1016\/j.patrec.2023.10.024"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1189"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00182"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"publisher","unstructured":"Timothy\u00a0A. Davis John\u00a0R. Gilbert Stefan\u00a0I. Larimore and Esmond\u00a0G. Ng. 2004. Algorithm 836: COLAMD a column approximate minimum degree ordering algorithm. ACM Trans. Math. Softw. 30 3 (Sept. 2004) 377\u2013380. 10.1145\/1024074.1024080","DOI":"10.1145\/1024074.1024080"},{"key":"e_1_3_3_1_18_2","unstructured":"Tim Dettmers Artidoro Pagnoni Ari Holtzman and Luke Zettlemoyer. 2023. QLoRA: Efficient Finetuning of Quantized LLMs. arXiv:https:\/\/arXiv.org\/abs\/2305.14314\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2305.14314"},{"key":"e_1_3_3_1_19_2","unstructured":"Jacob Devlin Ming-Wei Chang Kenton Lee and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. arXiv:https:\/\/arXiv.org\/abs\/1810.04805\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/1810.04805"},{"key":"e_1_3_3_1_20_2","unstructured":"Elias Frantar and Dan Alistarh. 2023. SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot. arXiv:https:\/\/arXiv.org\/abs\/2301.00774\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2301.00774"},{"key":"e_1_3_3_1_21_2","unstructured":"Elias Frantar Saleh Ashkboos Torsten Hoefler and Dan Alistarh. 2023. GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers. arXiv:https:\/\/arXiv.org\/abs\/2210.17323\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2210.17323"},{"key":"e_1_3_3_1_22_2","unstructured":"Jay Gala. 2021. Attention Is All You Need \u2013 PyTorch Implementation. https:\/\/colab.research.google.com\/github\/jaygala24\/pytorch-implementations\/blob\/master\/Attention%20Is%20All%20You%20Need.ipynb"},{"key":"e_1_3_3_1_23_2","volume-title":"Matrix Computations - 4th Edition","author":"Golub Gene\u00a0H.","year":"2013","unstructured":"Gene\u00a0H. Golub and Charles\u00a0F. Van\u00a0Loan. 2013. Matrix Computations - 4th Edition. Johns Hopkins University Press, Philadelphia, PA."},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"crossref","unstructured":"Ruihao Gong Yifu Ding Zining Wang Chengtao Lv Xingyu Zheng Jinyang Du Haotong Qin Jinyang Guo Michele Magno and Xianglong Liu. 2024. A Survey of Low-bit Large Language Models: Basics Systems and Algorithms. arXiv:https:\/\/arXiv.org\/abs\/2409.16694\u00a0[cs.AI] https:\/\/arxiv.org\/abs\/2409.16694","DOI":"10.2139\/ssrn.4996660"},{"key":"e_1_3_3_1_25_2","unstructured":"Mitchell Gorsline Zenas Smith et\u00a0al. 2021. On the Adversarial Robustness of Quantized Neural Networks. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2105.00227 (2021). https:\/\/arxiv.org\/abs\/2105.00227"},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"crossref","unstructured":"Lars Grasedyck Ronald Kriemann and Sabine\u00a0Le Borne. 2009. Domain-decomposition Based H-LU Preconditioners. Numer. Math. 112 (2009) 565\u2013600. https:\/\/api.semanticscholar.org\/CorpusID:10244664","DOI":"10.1007\/s00211-009-0218-6"},{"key":"e_1_3_3_1_27_2","volume-title":"A class of multilevel parallel preconditioning strategies","author":"Grigori Laura","year":"2010","unstructured":"Laura Grigori, Pawan Kumar, Fr\u00e9d\u00e9ric Nataf, and Ke Wang. 2010. A class of multilevel parallel preconditioning strategies. Research Report RR-7410. INRIA. https:\/\/inria.hal.science\/inria-00524110"},{"key":"e_1_3_3_1_28_2","unstructured":"Andi Han Jiaxiang Li Wei Huang Mingyi Hong Akiko Takeda Pratik Jawanpuria and Bamdev Mishra. 2024. SLTrain: a sparse plus low-rank approach for parameter and memory efficient pretraining. arXiv:https:\/\/arXiv.org\/abs\/2406.02214\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2406.02214"},{"key":"e_1_3_3_1_29_2","unstructured":"Song Han Huizi Mao and William\u00a0J. Dally. 2016. Deep Compression: Compressing Deep Neural Networks with Pruning Trained Quantization and Huffman Coding. arXiv:https:\/\/arXiv.org\/abs\/1510.00149\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/1510.00149"},{"key":"e_1_3_3_1_30_2","doi-asserted-by":"publisher","unstructured":"Tucker Hartland Georg Stadler Mauro Perego Kim Liegeois and No\u00e9mi Petra. 2023. Hierarchical off-diagonal low-rank approximation of Hessians in inverse problems with application to ice sheet model initialization. Inverse Problems 39 8 (June 2023) 085006. 10.1088\/1361-6420\/acd719","DOI":"10.1088\/1361-6420\/acd719"},{"key":"e_1_3_3_1_31_2","unstructured":"Jordan Hoffmann Sebastian Borgeaud Arthur Mensch Elena Buchatskaya Trevor Cai Eliza Rutherford Diego de Las\u00a0Casas Lisa\u00a0Anne Hendricks Johannes Welbl Aidan Clark Tom Hennigan Eric Noland Katie Millican George van\u00a0den Driessche Bogdan Damoc Aurelia Guy Simon Osindero Karen Simonyan Erich Elsen Jack\u00a0W. Rae Oriol Vinyals and Laurent Sifre. 2022. Training Compute-Optimal Large Language Models. arXiv:https:\/\/arXiv.org\/abs\/2203.15556\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2203.15556"},{"key":"e_1_3_3_1_32_2","unstructured":"Coleman Hooper Sehoon Kim Hiva Mohammadzadeh Michael\u00a0W. Mahoney Yakun\u00a0Sophia Shao Kurt Keutzer and Amir Gholami. 2025. KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization. arXiv:https:\/\/arXiv.org\/abs\/2401.18079\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2401.18079"},{"key":"e_1_3_3_1_33_2","unstructured":"Edward\u00a0J. Hu Yelong Shen Phillip Wallis Zeyuan Allen-Zhu Yuanzhi Li Shean Wang Lu Wang and Weizhu Chen. 2021. LoRA: Low-Rank Adaptation of Large Language Models. arXiv:https:\/\/arXiv.org\/abs\/2106.09685\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2106.09685"},{"key":"e_1_3_3_1_34_2","unstructured":"Yixin Ji Yang Xiang Juntao Li Qingrong Xia Zi Ye Xinyu Duan Zhefeng Wang Kehai Chen and Min Zhang. 2025. Adaptive Feature-based Low-Rank Compression of Large Language Models via Bayesian Optimization. arXiv:https:\/\/arXiv.org\/abs\/2405.10616\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2405.10616"},{"key":"e_1_3_3_1_35_2","unstructured":"Tong Jian Zifeng Wang Yanzhi Wang Jennifer Dy and Stratis Ioannidis. 2022. Pruning Adversarially Robust Neural Networks without Adversarial Examples. arXiv:https:\/\/arXiv.org\/abs\/2210.04311\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2210.04311"},{"key":"e_1_3_3_1_36_2","unstructured":"Jared Kaplan Sam McCandlish Tom Henighan Tom\u00a0B. Brown Benjamin Chess Rewon Child Scott Gray Alec Radford Jeffrey Wu and Dario Amodei. 2020. Scaling Laws for Neural Language Models. arXiv:https:\/\/arXiv.org\/abs\/2001.08361\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2001.08361"},{"key":"e_1_3_3_1_37_2","doi-asserted-by":"publisher","unstructured":"Ritesh Khan V.A. Kandappan and Sivaram Ambikasaran. 2024. HODLRdD: A new black-box fast algorithm for N-body problems in d-dimensions with guaranteed error bounds: Applications to integral equations and support vector machines. J. Comput. Phys. 501 (March 2024) 112786. 10.1016\/j.jcp.2024.112786","DOI":"10.1016\/j.jcp.2024.112786"},{"key":"e_1_3_3_1_38_2","doi-asserted-by":"crossref","unstructured":"Andrew\u00a0V. Knyazev Merico\u00a0E. Argentati Ilya Lashuk and Evgueni\u00a0E. Ovtchinnikov. 2007. Block Locally Optimal Preconditioned Eigenvalue Xolvers (BLOPEX) in hypre and PETSc. SIAM J. Sci. Comput. 29 (2007) 2224\u20132239. https:\/\/api.semanticscholar.org\/CorpusID:266","DOI":"10.1137\/060661624"},{"key":"e_1_3_3_1_39_2","doi-asserted-by":"crossref","unstructured":"Daniel Kressner Michael Steinlechner and Bart Vandereycken. 2016. Preconditioned Low-rank Riemannian Optimization for Linear Systems with Tensor Product Structure. SIAM J. Sci. Comput. 38 (2016). https:\/\/api.semanticscholar.org\/CorpusID:2708932","DOI":"10.1137\/15M1032909"},{"key":"e_1_3_3_1_40_2","doi-asserted-by":"publisher","unstructured":"Pawan Kumar. 2014. Aggregation based on graph matching and inexact coarse grid solve for algebraic two grid. International Journal of Computer Mathematics 91 5 (2014) 1061\u20131081. 10.1080\/00207160.2013.821115","DOI":"10.1080\/00207160.2013.821115"},{"key":"e_1_3_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCC.2014.55"},{"key":"e_1_3_3_1_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISPDC.2014.23"},{"key":"e_1_3_3_1_43_2","doi-asserted-by":"publisher","unstructured":"Pawan Kumar. 2015. Multilevel Communication Optimal Least Squares. Procedia Computer Science 51 (2015) 1838\u20131847. 10.1016\/j.procs.2015.05.410International Conference On Computational Science ICCS 2015.","DOI":"10.1016\/j.procs.2015.05.410"},{"key":"e_1_3_3_1_44_2","doi-asserted-by":"publisher","unstructured":"Pawan Kumar Stefano Markidis Giovanni Lapenta Karl Meerbergen and Dirk Roose. 2013. High Performance Solvers for Implicit Particle in Cell Simulation. Procedia Computer Science 18 (2013) 2251\u20132258. 10.1016\/j.procs.2013.05.3962013 International Conference on Computational Science.","DOI":"10.1016\/j.procs.2013.05.396"},{"key":"e_1_3_3_1_45_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-36803-5_16"},{"key":"e_1_3_3_1_46_2","doi-asserted-by":"crossref","unstructured":"Maxim Larin and Arnold Reusken. 2008. A comparative study of efficient iterative solvers for generalized Stokes equations. Numerical Linear Algebra with Applications 15 (2008). https:\/\/api.semanticscholar.org\/CorpusID:8588124","DOI":"10.1002\/nla.561"},{"key":"e_1_3_3_1_47_2","unstructured":"Aitor Lewkowycz Anders Andreassen David Dohan Ethan Dyer Henryk Michalewski Vinay Ramasesh Ambrose Slone Cem Anil Imanol Schlag Theo Gutman-Solo Yuhuai Wu Behnam Neyshabur Guy Gur-Ari and Vedant Misra. 2022. Solving Quantitative Reasoning Problems with Language Models. arXiv:https:\/\/arXiv.org\/abs\/2206.14858\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2206.14858"},{"key":"e_1_3_3_1_48_2","unstructured":"Hao Li Asim Kadav Igor Durdanovic Hanan Samet and Hans\u00a0Peter Graf. 2017. Pruning Filters for Efficient ConvNets. arXiv:https:\/\/arXiv.org\/abs\/1608.08710\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/1608.08710"},{"key":"e_1_3_3_1_49_2","doi-asserted-by":"crossref","unstructured":"Ruipeng Li and Yousef Saad. 2013. Divide and Conquer Low-Rank Preconditioners for Symmetric Matrices. SIAM J. Sci. Comput. 35 (2013). https:\/\/api.semanticscholar.org\/CorpusID:5753835","DOI":"10.1137\/120872735"},{"key":"e_1_3_3_1_50_2","unstructured":"Zhen Li Yupeng Su Runming Yang Congkai Xie Zheng Wang Zhongwei Xie Ngai Wong and Hongxia Yang. 2025. Quantization Meets Reasoning: Exploring LLM Low-Bit Quantization Degradation for Mathematical Reasoning. arXiv:https:\/\/arXiv.org\/abs\/2501.03035\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2501.03035"},{"key":"e_1_3_3_1_51_2","unstructured":"Ji Lin Jiaming Tang Haotian Tang Shang Yang Wei-Ming Chen Wei-Chen Wang Guangxuan Xiao Xingyu Dang Chuang Gan and Song Han. 2024. AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration. arXiv:https:\/\/arXiv.org\/abs\/2306.00978\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2306.00978"},{"key":"e_1_3_3_1_52_2","unstructured":"Hao Liu and Pieter Abbeel. 2023. Blockwise Parallel Transformer for Large Context Models. arXiv:https:\/\/arXiv.org\/abs\/2305.19370\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2305.19370"},{"key":"e_1_3_3_1_53_2","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611977172.33"},{"key":"e_1_3_3_1_54_2","unstructured":"Stephen Merity Caiming Xiong James Bradbury and Richard Socher. 2016. Pointer Sentinel Mixture Models. arXiv:https:\/\/arXiv.org\/abs\/1609.07843\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/1609.07843"},{"key":"e_1_3_3_1_55_2","first-page":"4646","volume-title":"Proceedings of the 36th International Conference on Machine Learning (ICML)","author":"Mostafa Hesham","year":"2019","unstructured":"Hesham Mostafa and Xin Wang. 2019. Parameter-Efficient Training of Deep Convolutional Neural Networks by Dynamic Sparse Reparameterization. In Proceedings of the 36th International Conference on Machine Learning (ICML). 4646\u20134655. https:\/\/arxiv.org\/abs\/1902.05967 arXiv:https:\/\/arXiv.org\/abs\/1902.05967."},{"key":"e_1_3_3_1_56_2","unstructured":"Long Ouyang Jeff Wu Xu Jiang Diogo Almeida Carroll\u00a0L. Wainwright Pamela Mishkin Chong Zhang Sandhini Agarwal Katarina Slama Alex Ray John Schulman Jacob Hilton Fraser Kelton Luke Miller Maddie Simens Amanda Askell Peter Welinder Paul Christiano Jan Leike and Ryan Lowe. 2022. Training language models to follow instructions with human feedback. arXiv:https:\/\/arXiv.org\/abs\/2203.02155\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2203.02155"},{"key":"e_1_3_3_1_57_2","doi-asserted-by":"publisher","unstructured":"Maryam Parvizi Amirreza Khodadadian Sven Beuchler and Thomas Wick. 2024. Hierarchical LU preconditioning for the time-harmonic Maxwell equations. arXiv:https:\/\/arXiv.org\/abs\/2211.11303\u00a0[math.NA] 10.1007\/978-3-031-50769-4_47","DOI":"10.1007\/978-3-031-50769-4_47"},{"key":"e_1_3_3_1_58_2","doi-asserted-by":"publisher","unstructured":"Giorgio Piras Maura Pintor Ambra Demontis Battista Biggio Giorgio Giacinto and Fabio Roli. 2025. Adversarial pruning: A survey and benchmark of pruning methods for adversarial robustness. Pattern Recognition 168 (Dec. 2025) 111788. 10.1016\/j.patcog.2025.111788","DOI":"10.1016\/j.patcog.2025.111788"},{"key":"e_1_3_3_1_59_2","unstructured":"Hadi Pouransari Pieter Coulier and Eric\u00a0F Darve. 2015. Fast Hierarchical Solvers For Sparse Matrices Using Extended Sparsification and Low-Rank Approximation. ArXiv abs\/1510.07363 (2015). https:\/\/api.semanticscholar.org\/CorpusID:10297422"},{"key":"e_1_3_3_1_60_2","unstructured":"Robin Rombach Andreas Blattmann Dominik Lorenz Patrick Esser and Bj\u00f6rn Ommer. 2022. High-Resolution Image Synthesis with Latent Diffusion Models. arXiv:https:\/\/arXiv.org\/abs\/2112.10752\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2112.10752"},{"key":"e_1_3_3_1_61_2","unstructured":"Chitwan Saharia William Chan Saurabh Saxena Lala Li Jay Whang Emily Denton Seyed Kamyar\u00a0Seyed Ghasemipour Burcu\u00a0Karagol Ayan S.\u00a0Sara Mahdavi Rapha\u00a0Gontijo Lopes Tim Salimans Jonathan Ho David\u00a0J Fleet and Mohammad Norouzi. 2022. Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding. arXiv:https:\/\/arXiv.org\/abs\/2205.11487\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2205.11487"},{"key":"e_1_3_3_1_62_2","unstructured":"Victor Sanh Lysandre Debut Julien Chaumond and Thomas Wolf. 2020. DistilBERT a distilled version of BERT: smaller faster cheaper and lighter. arXiv:https:\/\/arXiv.org\/abs\/1910.01108\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/1910.01108"},{"key":"e_1_3_3_1_63_2","unstructured":"Victor Sanh Thomas Wolf and Alexander\u00a0M. Rush. 2020. Movement Pruning: Adaptive Sparsity by Fine-Tuning. arXiv:https:\/\/arXiv.org\/abs\/2005.07683\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2005.07683"},{"key":"e_1_3_3_1_64_2","unstructured":"Dayana Savostianova Emanuele Zangrando Gianluca Ceruti and Francesco Tudisco. 2023. Robust low-rank training via approximate orthonormal constraints. arXiv:https:\/\/arXiv.org\/abs\/2306.01485\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2306.01485"},{"key":"e_1_3_3_1_65_2","doi-asserted-by":"crossref","unstructured":"M. Stoll and Andrew\u00a0J. Wathen. 2008. Combination Preconditioning and the Bramble-Pasciak+ Preconditioner. SIAM J. Matrix Anal. Appl. 30 (2008) 582\u2013608. https:\/\/api.semanticscholar.org\/CorpusID:39726484","DOI":"10.1137\/070688961"},{"key":"e_1_3_3_1_66_2","doi-asserted-by":"publisher","unstructured":"Richard Szeliski. 2006. Locally adapted hierarchical basis preconditioning. ACM Trans. Graph. 25 3 (July 2006) 1135\u20131143. 10.1145\/1141911.1142005","DOI":"10.1145\/1141911.1142005"},{"key":"e_1_3_3_1_67_2","unstructured":"Hugo Touvron Thibaut Lavril Gautier Izacard Xavier Martinet Marie-Anne Lachaux Timoth\u00e9e Lacroix Baptiste Rozi\u00e8re Naman Goyal Eric Hambro Faisal Azhar Aurelien Rodriguez Armand Joulin Edouard Grave and Guillaume Lample. 2023. LLaMA: Open and Efficient Foundation Language Models. arXiv:https:\/\/arXiv.org\/abs\/2302.13971\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2302.13971"},{"key":"e_1_3_3_1_68_2","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)\n                  arXiv:https:\/\/arXiv.org\/abs\/1706.03762","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan\u00a0N. Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention Is All You Need, In Advances in Neural Information Processing Systems (NeurIPS). arXiv:https:\/\/arXiv.org\/abs\/1706.03762. https:\/\/arxiv.org\/abs\/1706.03762"},{"key":"e_1_3_3_1_69_2","unstructured":"Hongyu Wang Shuming Ma Li Dong Shaohan Huang Huaijie Wang Lingxiao Ma Fan Yang Ruiping Wang Yi Wu and Furu Wei. 2023. BitNet: Scaling 1-bit Transformers for Large Language Models. arXiv:https:\/\/arXiv.org\/abs\/2310.11453\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2310.11453"},{"key":"e_1_3_3_1_70_2","volume-title":"ICLR 2018 Workshop","author":"Wang Luyu","year":"2018","unstructured":"Luyu Wang, Gavin\u00a0Weiguang Ding, Ruitong Huang, Yanshuai Cao, and Yik\u00a0Chau Lui. 2018. Adversarial Robustness of Pruned Neural Networks. In ICLR 2018 Workshop. https:\/\/openreview.net\/pdf?id=SJGrAisIz"},{"key":"e_1_3_3_1_71_2","unstructured":"Sinong Wang Belinda\u00a0Z. Li Madian Khabsa Han Fang and Hao Ma. 2020. Linformer: Self-Attention with Linear Complexity. arXiv:https:\/\/arXiv.org\/abs\/2006.04768\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2006.04768"},{"key":"e_1_3_3_1_72_2","unstructured":"Guangxuan Xiao Ji Lin Mickael Seznec Hao Wu Julien Demouth and Song Han. 2024. SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models. arXiv:https:\/\/arXiv.org\/abs\/2211.10438\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2211.10438"},{"key":"e_1_3_3_1_73_2","unstructured":"Shaokai Ye Kaidi Xu Sijia Liu Jan-Henrik Lambrechts Huan Zhang Aojun Zhou Kaisheng Ma Yanzhi Wang and Xue Lin. 2021. Adversarial Robustness vs Model Compression or Both? arXiv:https:\/\/arXiv.org\/abs\/1903.12561\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/1903.12561"},{"key":"e_1_3_3_1_74_2","unstructured":"Xunyu Zhu Jian Li Yong Liu Can Ma and Weiping Wang. 2024. A Survey on Model Compression for Large Language Models. arXiv:https:\/\/arXiv.org\/abs\/2308.07633\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2308.07633"}],"event":{"name":"CODS 2025: 13th ACM IKDD International Conference on Data Science","location":"Pune India","acronym":"CODS 2025"},"container-title":["Proceedings of the 13th ACM IKDD International Conference on Data Science"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3799830.3799837","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T07:12:58Z","timestamp":1777014778000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3799830.3799837"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,17]]},"references-count":73,"alternative-id":["10.1145\/3799830.3799837","10.1145\/3799830"],"URL":"https:\/\/doi.org\/10.1145\/3799830.3799837","relation":{},"subject":[],"published":{"date-parts":[[2025,12,17]]},"assertion":[{"value":"2026-04-23","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}