Eldar Kurtic

Alexandre Noll Marques

Shubhra Pandit

Mark Kurtz

Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2025

2024

Accurate Neural Network Pruning Requires Rethinking Sparse Optimization.

[BibT_eX]

[DOI]

Trans. Mach. Learn. Res., 2024

EvoPress: Towards Optimal Dynamic Model Compression via Evolutionary Search.

[BibT_eX]

[DOI]

CoRR, 2024

Panza: A Personalized Text Writing Assistant via Data Playback and Local Fine-Tuning.

[BibT_eX]

[DOI]

CoRR, 2024

Enabling High-Sparsity Foundational Llama Models with Efficient Pretraining and Deployment.

[BibT_eX]

[DOI]

Abhinav Agarwalla

Abhay Gupta

Alexandre Noll Marques

CoRR, 2024

MicroAdam: Accurate Adaptive Optimization with Low Space Overhead and Provable Convergence.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

Error Feedback Can Accurately Compress Preconditioners.

[BibT_eX]

[DOI]

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Mathador-LM: A Dynamic Benchmark for Mathematical Reasoning on Large Language Models.

[BibT_eX]

[DOI]

Amir Moeini

Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024

How to Prune Your Language Model: Recovering Accuracy on the "Sparsity May Cry" Benchmark.

[BibT_eX]

[DOI]

Torsten Hoefler

Proceedings of the Conference on Parsimony and Learning, 2024

2023

Sparse Fine-tuning for Inference Acceleration of Large Language Models.

[BibT_eX]

[DOI]

CoRR, 2023

Error Feedback Can Accurately Compress Preconditioners.

[BibT_eX]

[DOI]

CoRR, 2023

Vision Models Can Be Efficiently Specialized via Few-Shot Task-Aware Compression.

[BibT_eX]

[DOI]

CoRR, 2023

SparseProp: Efficient Sparse Backpropagation for Faster Training of Neural Networks.

[BibT_eX]

[DOI]

CoRR, 2023

ZipLM: Hardware-Aware Structured Pruning of Language Models.

[BibT_eX]

[DOI]

CoRR, 2023

CAP: Correlation-Aware Pruning for Highly-Accurate Sparse Vision Models.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

ZipLM: Inference-Aware Structured Pruning of Language Models.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

SparseProp: Efficient Sparse Backpropagation for Faster Training of Neural Networks at the Edge.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2023

CrAM: A Compression-Aware Minimizer.

[BibT_eX]

[DOI]

Proceedings of the Eleventh International Conference on Learning Representations, 2023

2022

oViT: An Accurate Second-Order Pruning Framework for Vision Transformers.

[BibT_eX]

[DOI]

CoRR, 2022

GMP*: Well-Tuned Global Magnitude Pruning Can Outperform Most BERT-Pruning Methods.

[BibT_eX]

[DOI]

CoRR, 2022

Vision for Bosnia and Herzegovina in Artificial Intelligence Age: Global Trends, Potential Opportunities, Selected Use-cases and Realistic Goals.

[BibT_eX]

[DOI]

CoRR, 2022

The Optimal BERT Surgeon: Scalable and Accurate Second-Order Pruning for Large Language Models.

[BibT_eX]

[DOI]

Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, 2022

2021

Efficient Matrix-Free Approximations of Second-Order Information, with Applications to Pruning and Optimization.

[BibT_eX]

[DOI]

CoRR, 2021

M-FAC: Efficient Matrix-Free Approximations of Second-Order Information.

[BibT_eX]

[DOI]