Dan Alistarh

Best Publications

• QSGD: Communication-Efficient SGD via Gradient Quantization and Encoding

  Dan Alistarh;Demjan Grubic;Jerry Z. Li;Ryota Tomioka

  1106
  Citations

• Sparsity in Deep Learning: Pruning and growth for efficient inference and training in neural networks

  Unknown

  343
  Citations

• Model compression via distillation and quantization

  Antonio Polino;Razvan Pascanu;Dan Alistarh

  276
  Citations

• GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers

  Unknown

  271
  Citations

• Byzantine Stochastic Gradient Descent

  Dan Alistarh;Zeyuan Allen-Zhu;Jerry Li

  208
  Citations

• 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

  175
  Citations

• The SprayList: a scalable relaxed priority queue

  Dan Alistarh;Justin Kopinsky;Jerry Li;Nir Shavit

  133
  Citations

• Sparsity in Deep Learning: Pruning and growth for efficient inference and training in neural networks

  Torsten Hoefler;Dan Alistarh;Tal Ben-Nun;Nikoli Dryden

  131
  Citations

• Fast and Exact Majority in Population Protocols

  Dan Alistarh;Rati Gelashvili;Milan Vojnović

  118
  Citations

• SparCML: high-performance sparse communication for machine learning

  Cedric Renggli;Saleh Ashkboos;Mehdi Aghagolzadeh;Dan Alistarh

  112
  Citations

• Polylogarithmic-Time Leader Election in Population Protocols

  Dan Alistarh;Rati Gelashvili

  104
  Citations

• QSGD: Randomized Quantization for Communication-Optimal Stochastic Gradient Descent

  Dan Alistarh;Jerry Li;Ryota Tomioka;Milan Vojnovic

  99
  Citations

• Space-optimal majority in population protocols

  Dan Alistarh;James Aspnes;Rati Gelashvili

  94
  Citations

• FPGA-Accelerated Dense Linear Machine Learning: A Precision-Convergence Trade-Off

  Kaan Kara;Dan Alistarh;Gustavo Alonso;Onur Mutlu

  83
  Citations

• Byzantine Stochastic Gradient Descent

  Dan Alistarh;Zeyuan Allen-Zhu;Jerry Li

  73
  Citations

• SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot

  Unknown

  70
  Citations

• Fast randomized test-and-set and renaming

  Dan Alistarh;Hagit Attiya;Seth Gilbert;Andrei Giurgiu

  70
  Citations

• StackTrack: an automated transactional approach to concurrent memory reclamation

  Dan Alistarh;Patrick Eugster;Maurice Herlihy;Alexander Matveev

  67
  Citations

• SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compression

  Unknown

  59
  Citations

• Recent Algorithmic Advances in Population Protocols

  Dan Alistarh;Rati Gelashvili

  58
  Citations