Dan Alistarh
Institute of Science and Technology Austria
H-index: 36
Europe-Austria
Top articles of Dan Alistarh
Title | Journal | Author(s) | Publication Date |
---|---|---|---|
CAP: Correlation-Aware Pruning for Highly-Accurate Sparse Vision Models | Advances in Neural Information Processing Systems | Denis Kuznedelev Eldar Kurtić Elias Frantar Dan Alistarh | 2024/2/13 |
Distributed Computing Column 86 The Environmental Cost of Our Conferences | ACM SIGACT News | Dan Alistarh | 2024/1/3 |
ZipLM: Inference-Aware Structured Pruning of Language Models | Advances in Neural Information Processing Systems | Eldar Kurtić Elias Frantar Dan Alistarh | 2024/2/13 |
Communication-Efficient Federated Learning With Data and Client Heterogeneity | Hossein Zakerinia Shayan Talaei Giorgi Nadiradze Dan Alistarh | 2024/4/18 | |
Knowledge Distillation Performs Partial Variance Reduction | Mher Safaryan Alexandra Peste Dan Alistarh | 2023/5/27 | |
AsGrad: A Sharp Unified Analysis of Asynchronous-SGD Algorithms | Rustem Islamov Mher Safaryan Dan Alistarh | 2023/10/31 | |
Extreme Compression of Large Language Models via Additive Quantization | arXiv preprint arXiv:2401.06118 | Vage Egiazarian Andrei Panferov Denis Kuznedelev Elias Frantar Artem Babenko | 2024/1/11 |
Mitigating the Impact of Outlier Channels for Language Model Quantization with Activation Regularization | arXiv preprint arXiv:2404.03605 | Aniruddha Nrusimha Mayank Mishra Naigang Wang Dan Alistarh Rameswar Panda | 2024/4/4 |
RoSA: Accurate Parameter-Efficient Fine-Tuning via Robust Adaptation | arXiv preprint arXiv:2401.04679 | Mahdi Nikdan Soroush Tabesh Dan Alistarh | 2024/1/9 |
QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs | arXiv preprint arXiv:2404.00456 | Saleh Ashkboos Amirkeivan Mohtashami Maximilian L Croci Bo Li Martin Jaggi | 2024/3/30 |
How to Prune Your Language Model: Recovering Accuracy on the “Sparsity May Cry” Benchmark | Eldar Kurtic Torsten Hoefler Dan Alistarh | 2024/1/8 | |
Fast and scalable channels in kotlin coroutines | Nikita Koval Dan Alistarh Roman Elizarov | 2023/2/25 | |
Systems and methods for neural network pruning with accuracy preservation | 2023/4/25 | ||
Provably-Efficient and Internally-Deterministic Parallel Union-Find | Alexander Fedorov Diba Hashemi Giorgi Nadiradze Dan Alistarh | 2023/6/17 | |
Repeated Game Dynamics in Population Protocols | arXiv preprint arXiv:2307.07297 | Dan Alistarh Krishnendu Chatterjee Mehrdad Karrabi John Lazarsfeld | 2023/7/14 |
Distributed Computing Column 87 Recent Advances in Multi-Pass Graph Streaming Lower Bounds | Dan Alistarh | 2023/9/11 | |
Sparse finetuning for inference acceleration of large language models | arXiv preprint arXiv:2310.06927 | Eldar Kurtic Denis Kuznedelev Elias Frantar Michael Goin Dan Alistarh | 2023/10/10 |
Bias in pruned vision models: In-depth analysis and countermeasures | Eugenia Iofinova Alexandra Peste Dan Alistarh | 2023 | |
Vision Models Can Be Efficiently Specialized via Few-Shot Task-Aware Compression | arXiv preprint arXiv:2303.14409 | Denis Kuznedelev Soroush Tabesh Kimia Noorbakhsh Elias Frantar Sara Beery | 2023/3/25 |
Decentralized Learning Dynamics in the Gossip Model | arXiv preprint arXiv:2306.08670 | John Lazarsfeld Dan Alistarh | 2023/6/14 |