| 2026 | CGO | QIGen: A Kernel Generator for Inference on Nonuniformly Quantized Large Language Models. | Tommaso Pegolotti, Dan Alistarh, Markus Pschel |
| 2026 | EACL | Speculative Decoding Speed-of-Light: Optimal Lower Bounds via Branching Random Walks. | Sergey Pankratov, Dan Alistarh |
| 2025 | AAAI | Hybrid Decentralized Optimization: Leveraging Both First- and Zeroth-Order Optimizers for Faster Convergence. | Shayan Talaei, Matin Ansaripour, Giorgi Nadiradze, Dan Alistarh |
| 2025 | ACL | "Give Me BF16 or Give Me Death"? Accuracy-Performance Trade-Offs in LLM Quantization. | Eldar Kurtic, Alexandre Noll Marques, Shubhra Pandit, Mark Kurtz, Dan Alistarh |
| 2025 | ICLR | LDAdam: Adaptive Optimization from Low-Dimensional Gradient Statistics. | Thomas Robert, Mher Safaryan, Ionut-Vlad Modoranu, Dan Alistarh |
| 2025 | ICLR | Scalable Mechanistic Neural Networks. | Jiale Chen, Dingling Yao, Adeel Pervez, Dan Alistarh, Francesco Locatello |
| 2025 | ICLR | The Journey Matters: Average Parameter Count over Pre-training Unifies Sparse and Dense Scaling Laws. | Tian Jin, Ahmed Imtiaz Humayun, Utku Evci, Suvinay Subramanian, Amir Yazdanbakhsh, Dan Alistarh, Gintare Karolina Dziugaite |
| 2025 | ICLR | Wasserstein Distances, Neuronal Entanglement, and Sparsity. | Shashata Sawmya, Linghao Kong, Ilia Markov, Dan Alistarh, Nir Shavit |
| 2025 | ICML | Layer-wise Quantization for Quantized Optimistic Dual Averaging. | Anh Duc Nguyen, Ilia Markov, Frank Zhengqing Wu, Ali Ramezani-Kebrya, Kimon Antonakopoulos, Dan Alistarh, Volkan Cevher |
| 2025 | ICML | QuEST: Stable Training of LLMs with 1-Bit Weights and Activations. | Andrei Panferov, Jiale Chen, Soroush Tabesh, Mahdi Nikdan, Dan Alistarh |
| 2025 | ICML | Cache Me If You Must: Adaptive Key-Value Quantization for Large Language Models. | Alina Shutova, Vladimir Malinovskii, Vage Egiazarian, Denis Kuznedelev, Denis Mazur, Nikita Surkov, Ivan Ermakov, Dan Alistarh |
| 2025 | ICML | EvoPress: Accurate Dynamic Model Compression via Evolutionary Search. | Oliver Sieberling, Denis Kuznedelev, Eldar Kurtic, Dan Alistarh |
| 2025 | NAACL | HIGGS: Pushing the Limits of Large Language Model Quantization via the Linearity Theorem. | Vladimir Malinovskii, Andrei Panferov, Ivan Ilin, Han Guo, Peter Richtrik, Dan Alistarh |
| 2025 | PPoPP | MARLIN: Mixed-Precision Auto-Regressive Parallel Inference on Large Language Models. | Elias Frantar, Roberto L. Castro, Jiale Chen, Torsten Hoefler, Dan Alistarh |
| 2024 | AISTATS | AsGrad: A Sharp Unified Analysis of Asynchronous-SGD Algorithms. | Rustem Islamov, Mher Safaryan, Dan Alistarh |
| 2024 | AISTATS | Communication-Efficient Federated Learning With Data and Client Heterogeneity. | Hossein Zakerinia, Shayan Talaei, Giorgi Nadiradze, Dan Alistarh |
| 2024 | EMNLP | QUIK: Towards End-to-end 4-Bit Inference on Generative Large Language Models. | Saleh Ashkboos, Ilia Markov, Elias Frantar, Tingxuan Zhong, Xincheng Wang, Jie Ren, Torsten Hoefler, Dan Alistarh |
| 2024 | EMNLP | Mathador-LM: A Dynamic Benchmark for Mathematical Reasoning on Large Language Models. | Eldar Kurtic, Amir Moeini, Dan Alistarh |
| 2024 | ICDCS | Federated SGD with Local Asynchrony. | Bapi Chatterjee, Vyacheslav Kungurtsev, Dan Alistarh |
| 2024 | ICLR | SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compression. | Tim Dettmers, Ruslan Svirschevski, Vage Egiazarian, Denis Kuznedelev, Elias Frantar, Saleh Ashkboos, Alexander Borzunov, Torsten Hoefler, Dan Alistarh |
| 2024 | ICLR | Scaling Laws for Sparsely-Connected Foundation Models. | Elias Frantar, Carlos Riquelme Ruiz, Neil Houlsby, Dan Alistarh, Utku Evci |
| 2024 | ICML | Extreme Compression of Large Language Models via Additive Quantization. | Vage Egiazarian, Andrei Panferov, Denis Kuznedelev, Elias Frantar, Artem Babenko, Dan Alistarh |
| 2024 | ICML | SPADE: Sparsity-Guided Debugging for Deep Neural Networks. | Arshia Soltani Moakhar, Eugenia Iofinova, Elias Frantar, Dan Alistarh |
| 2024 | ICML | Error Feedback Can Accurately Compress Preconditioners. | Ionut-Vlad Modoranu, Aleksei Kalinov, Eldar Kurtic, Elias Frantar, Dan Alistarh |
| 2024 | ICML | RoSA: Accurate Parameter-Efficient Fine-Tuning via Robust Adaptation. | Mahdi Nikdan, Soroush Tabesh, Elvir Crncevic, Dan Alistarh |
| 2024 | PODC | Game Dynamics and Equilibrium Computation in the Population Protocol Model. | Dan Alistarh, Krishnendu Chatterjee, Mehrdad Karrabi, John Lazarsfeld |
| 2023 | CAV | Lincheck: A Practical Framework for Testing Concurrent Data Structures on JVM. | Nikita Koval, Alexander Fedorov, Maria Sokolova, Dmitry Tsitelov, Dan Alistarh |
| 2023 | CVPR | Bias in Pruned Vision Models: In-Depth Analysis and Countermeasures. | Eugenia Iofinova, Alexandra Peste, Dan Alistarh |
| 2023 | ICLR | OPTQ: Accurate Quantization for Generative Pre-trained Transformers. | Elias Frantar, Saleh Ashkboos, Torsten Hoefler, Dan Alistarh |
| 2023 | ICLR | CrAM: A Compression-Aware Minimizer. | Alexandra Peste, Adrian Vladu, Eldar Kurtic, Christoph H. Lampert, Dan Alistarh |
| 2023 | ICML | SparseGPT: Massive Language Models Can be Accurately Pruned in One-Shot. | Elias Frantar, Dan Alistarh |
| 2023 | ICML | Quantized Distributed Training of Large Models with Convergence Guarantees. | Ilia Markov, Adrian Vladu, Qi Guo, Dan Alistarh |
| 2023 | ICML | SparseProp: Efficient Sparse Backpropagation for Faster Training of Neural Networks at the Edge. | Mahdi Nikdan, Tommaso Pegolotti, Eugenia Iofinova, Eldar Kurtic, Dan Alistarh |
| 2023 | PPoPP | Fast and Scalable Channels in Kotlin Coroutines. | Nikita Koval, Dan Alistarh, Roman Elizarov |
| 2023 | SPAA | Provably-Efficient and Internally-Deterministic Parallel Union-Find. | Alexander Fedorov, Diba Hashemi, Giorgi Nadiradze, Dan Alistarh |
| 2022 | CVPR | How Well Do Sparse ImageNet Models Transfer? | Eugenia Iofinova, Alexandra Peste, Mark Kurtz, Dan Alistarh |
| 2022 | EMNLP | The Optimal BERT Surgeon: Scalable and Accurate Second-Order Pruning for Large Language Models. | Eldar Kurtic, Daniel Campos, Tuan Nguyen, Elias Frantar, Mark Kurtz, Benjamin Fineran, Michael Goin, Dan Alistarh |
| 2022 | ICML | SPDY: Accurate Pruning with Speedup Guarantees. | Elias Frantar, Dan Alistarh |
| 2022 | Middleware | CGX: adaptive system support for communication-efficient deep learning. | Ilia Markov, Hamidreza Ramezani-Kebrya, Dan Alistarh |
| 2022 | PODC | Near-Optimal Leader Election in Population Protocols on Graphs. | Dan Alistarh, Joel Rybicki, Sasha Voitovych |
| 2022 | PPoPP | PathCAS: an efficient middle ground for concurrent search data structures. | Trevor Brown, William Sigouin, Dan Alistarh |
| 2022 | PPoPP | Multi-queues can be state-of-the-art priority schedulers. | Anastasiia Postnikova, Nikita Koval, Giorgi Nadiradze, Dan Alistarh |
| 2021 | AAAI | Asynchronous Optimization Methods for Efficient Training of Deep Neural Networks with Guarantees. | Vyacheslav Kungurtsev, Malcolm Egan, Bapi Chatterjee, Dan Alistarh |
| 2021 | AAAI | Elastic Consistency: A Practical Consistency Model for Distributed Stochastic Gradient Descent. | Giorgi Nadiradze, Ilia Markov, Bapi Chatterjee, Vyacheslav Kungurtsev, Dan Alistarh |
| 2021 | ICLR | Byzantine-Resilient Non-Convex Stochastic Gradient Descent. | Zeyuan Allen-Zhu, Faeze Ebrahimianghazani, Jerry Li, Dan Alistarh |
| 2021 | ICLR | New Bounds For Distributed Mean Estimation and Variance Reduction. | Peter Davies, Vijaykrishna Gurunanthan, Niusha Moshrefi, Saleh Ashkboos, Dan Alistarh |
| 2021 | ICML | Communication-Efficient Distributed Optimization with Quantized Preconditioners. | Foivos Alimisis, Peter Davies, Dan Alistarh |
| 2021 | OPODIS | Fast Graphical Population Protocols. | Dan Alistarh, Rati Gelashvili, Joel Rybicki |
| 2021 | PODC | Comparison Dynamics in Population Protocols. | Dan Alistarh, Martin Tpfer, Przemyslaw Uznanski |
| 2021 | SPAA | A Scalable Concurrent Algorithm for Dynamic Connectivity. | Alexander Fedorov, Nikita Koval, Dan Alistarh |
| 2021 | SIROCCO | Collecting Coupons is Faster with Friends. | Dan Alistarh, Peter Davies |
| 2021 | SIROCCO | Wait-Free Approximate Agreement on Graphs. | Dan Alistarh, Faith Ellen, Joel Rybicki |
| 2020 | ICALP | Dynamic Averaging Load Balancing on Cycles. | Dan Alistarh, Giorgi Nadiradze, Amirmojtaba Sabour |
| 2020 | ICML | On the Sample Complexity of Adversarial Multi-Source PAC Learning. | Nikola Konstantinov, Elias Frantar, Dan Alistarh, Christoph Lampert |
| 2020 | ICML | Inducing and Exploiting Activation Sparsity for Fast Inference on Deep Neural Networks. | Mark Kurtz, Justin Kopinsky, Rati Gelashvili, Alexander Matveev, John Carr, Michael Goin, William M. Leiserson, Sage Moore, Nir Shavit, Dan Alistarh |
| 2020 | PODC | Brief Announcement: Why Extension-Based Proofs Fail. | Dan Alistarh, James Aspnes, Faith Ellen, Rati Gelashvili, Leqi Zhu |
| 2020 | PPoPP | Non-blocking interpolation search trees with doubly-logarithmic running time. | Trevor Brown, Aleksandar Prokopec, Dan Alistarh |
| 2020 | PPoPP | Testing concurrency on the JVM with lincheck. | Nikita Koval, Maria Sokolova, Alexander Fedorov, Dan Alistarh, Dmitry Tsitelov |
| 2020 | PPoPP | Taming unbalanced training workloads in deep learning with partial collective operations. | Shigang Li, Tal Ben-Nun, Salvatore Di Girolamo, Dan Alistarh, Torsten Hoefler |
| 2020 | SPAA | Memory Tagging: Minimalist Synchronization for Scalable Concurrent Data Structures. | Dan Alistarh, Trevor Brown, Nandini Singhal |
| 2019 | EuroPar | Scalable FIFO Channels for Programming via Communicating Sequential Processes. | Nikita Koval, Dan Alistarh, Roman Elizarov |
| 2019 | ICML | Distributed Learning over Unreliable Networks. | Chen Yu, Hanlin Tang, Cdric Renggli, Simon Kassing, Ankit Singla, Dan Alistarh, Ce Zhang, Ji Liu |
| 2019 | OPODIS | In Search of the Fastest Concurrent Union-Find Algorithm. | Dan Alistarh, Alexander Fedorov, Nikita Koval |
| 2019 | PPoPP | Lock-free channels for programming via communicating sequential processes: poster. | Nikita Koval, Dan Alistarh, Roman Elizarov |
| 2019 | SC | SparCML: high-performance sparse communication for machine learning. | Cdric Renggli, Saleh Ashkboos, Mehdi Aghagolzadeh, Dan Alistarh, Torsten Hoefler |
| 2019 | STOC | Why extension-based proofs fail. | Dan Alistarh, James Aspnes, Faith Ellen, Rati Gelashvili, Leqi Zhu |
| 2019 | SPAA | Efficiency Guarantees for Parallel Incremental Algorithms under Relaxed Schedulers. | Dan Alistarh, Giorgi Nadiradze, Nikita Koval |
| 2018 | EDBT | Synchronous Multi-GPU Training for Deep Learning with Low-Precision Communications: An Empirical Study. | Demjan Grubic, Leo Tam, Dan Alistarh, Ce Zhang |
| 2018 | ICLR | Model compression via distillation and quantization. | Antonio Polino, Razvan Pascanu, Dan Alistarh |
| 2018 | PODC | Brief Announcement: Performance Prediction for Coarse-Grained Locking. | Vitaly Aksenov, Dan Alistarh, Petr Kuznetsov |
| 2018 | PODC | Session details: Session 1B: Shared Memory Theory. | Dan Alistarh |
| 2018 | PODC | A Brief Tutorial on Distributed and Concurrent Machine Learning. | Dan Alistarh |
| 2018 | PODC | Relaxed Schedulers Can Efficiently Parallelize Iterative Algorithms. | Dan Alistarh, Trevor Brown, Justin Kopinsky, Giorgi Nadiradze |
| 2018 | PODC | The Convergence of Stochastic Gradient Descent in Asynchronous Shared Memory. | Dan Alistarh, Christopher De Sa, Nikola Konstantinov |
| 2018 | SODA | Space-Optimal Majority in Population Protocols. | Dan Alistarh, James Aspnes, Rati Gelashvili |
| 2018 | SPAA | Distributionally Linearizable Data Structures. | Dan Alistarh, Trevor Brown, Justin Kopinsky, Jerry Zheng Li, Giorgi Nadiradze |
| 2018 | SPAA | The Transactional Conflict Problem. | Dan Alistarh, Syed Kamran Haider, Raphael Kbler, Giorgi Nadiradze |
| 2017 | CoNEXT | Towards unlicensed cellular networks in TV white spaces. | Ghufran Baig, Dan Alistarh, Thomas Karagiannis, Bozidar Radunovic, Matthew Balkwill, Lili Qiu |
| 2017 | DNA | Robust Detection in Leak-Prone Population Protocols. | Dan Alistarh, Bartlomiej Dudek, Adrian Kosowski, David Soloveichik, Przemyslaw Uznanski |
| 2017 | EuroSys | Forkscan: Conservative Memory Reclamation for Modern Operating Systems. | Dan Alistarh, William M. Leiserson, Alexander Matveev, Nir Shavit |
| 2017 | FCCM | FPGA-Accelerated Dense Linear Machine Learning: A Precision-Convergence Trade-Off. | Kaan Kara, Dan Alistarh, Gustavo Alonso, Onur Mutlu, Ce Zhang |
| 2017 | ICML | ZipML: Training Linear Models with End-to-End Low Precision, and a Little Bit of Deep Learning. | Hantian Zhang, Jerry Li, Kaan Kara, Dan Alistarh, Ji Liu, Ce Zhang |
| 2017 | PODC | The Power of Choice in Priority Scheduling. | Dan Alistarh, Justin Kopinsky, Jerry Li, Giorgi Nadiradze |
| 2017 | SODA | Time-Space Trade-offs in Population Protocols. | Dan Alistarh, James Aspnes, David Eisenstat, Rati Gelashvili, Ronald L. Rivest |
| 2016 | PPoPP | Lease/release: architectural support for scaling contended data structures. | Syed Kamran Haider, William Hasenplaugh, Dan Alistarh |
| 2015 | ICALP | Polylogarithmic-Time Leader Election in Population Protocols. | Dan Alistarh, Rati Gelashvili |
| 2015 | PODC | Fast and Exact Majority in Population Protocols. | Dan Alistarh, Rati Gelashvili, Milan Vojnovic |
| 2015 | PODC | How To Elect a Leader Faster than a Tournament. | Dan Alistarh, Rati Gelashvili, Adrian Vladu |
| 2015 | PODC | Lock-Free Algorithms under Stochastic Schedulers. | Dan Alistarh, Thomas Sauerwald, Milan Vojnovic |
| 2015 | PPoPP | The SprayList: a scalable relaxed priority queue. | Dan Alistarh, Justin Kopinsky, Jerry Li, Nir Shavit |
| 2015 | SIGCOMM | A High-Radix, Low-Latency Optical Switch for Data Centers. | Dan Alistarh, Hitesh Ballani, Paolo Costa, Adam C. Funnell, Joshua Benjamin, Philip M. Watts, Benn Thomsen |
| 2015 | SPAA | ThreadScan: Automatic and Scalable Memory Reclamation. | Dan Alistarh, William M. Leiserson, Alexander Matveev, Nir Shavit |
| 2014 | EuroSys | StackTrack: an automated transactional approach to concurrent memory reclamation. | Dan Alistarh, Patrick Eugster, Maurice Herlihy, Alexander Matveev, Nir Shavit |
| 2014 | ICDCS | The LevelArray: A Fast, Practical Long-Lived Renaming Algorithm. | Dan Alistarh, Justin Kopinsky, Alexander Matveev, Nir Shavit |
| 2014 | PODC | Brief announcement: are lock-free concurrent algorithms practically wait-free? | Dan Alistarh, Keren Censor-Hillel, Nir Shavit |
| 2014 | PODC | Balls-into-leaves: sub-logarithmic renaming in synchronous message-passing systems. | Dan Alistarh, Oksana Denysyuk, Lus E. T. Rodrigues, Nir Shavit |
| 2014 | SODA | Dynamic Task Allocation in Asynchronous Shared Memory. | Dan Alistarh, James Aspnes, Michael A. Bender, Rati Gelashvili, Seth Gilbert |
| 2014 | STOC | Are lock-free concurrent algorithms practically wait-free? | Dan Alistarh, Keren Censor-Hillel, Nir Shavit |
| 2013 | PODC | Randomized loose renaming in | Dan Alistarh, James Aspnes, George Giakkoupis, Philipp Woelfel |
| 2012 | FOCS | How to Allocate Tasks Asynchronously. | Dan Alistarh, Michael A. Bender, Seth Gilbert, Rachid Guerraoui |
| 2012 | SPAA | On the cost of composing shared-memory algorithms. | Dan Alistarh, Rachid Guerraoui, Petr Kuznetsov, Giuliano Losa |
| 2012 | SIROCCO | Early Deciding Synchronous Renaming in O( logf ) Rounds or Less. | Dan Alistarh, Hagit Attiya, Rachid Guerraoui, Corentin Travers |
| 2011 | FOCS | The Complexity of Renaming. | Dan Alistarh, James Aspnes, Seth Gilbert, Rachid Guerraoui |
| 2011 | ICDCN | Generating Fast Indulgent Algorithms. | Dan Alistarh, Seth Gilbert, Rachid Guerraoui, Corentin Travers |
| 2011 | PODC | Optimal-time adaptive strong renaming, with applications to counting. | Dan Alistarh, James Aspnes, Keren Censor-Hillel, Seth Gilbert, Morteza Zadimoghaddam |
| 2010 | ICALP | How Efficient Can Gossip Be? (On the Cost of Resilient Information Exchange). | Dan Alistarh, Seth Gilbert, Rachid Guerraoui, Morteza Zadimoghaddam |
| 2010 | SPAA | Securing every bit: authenticated broadcast in radio networks. | Dan Alistarh, Seth Gilbert, Rachid Guerraoui, Zarko Milosevic, Calvin C. Newport |
| 2009 | ISAAC | Of Choices, Failures and Asynchrony: The Many Faces of Set Agreement. | Dan Alistarh, Seth Gilbert, Rachid Guerraoui, Corentin Travers |