← Search

Aleksandr Mikhalev

2 accepted papers

2024

Quantization of Large Language Models with an Overdetermined Basis

UAI 2024poster

In this paper, we introduce an algorithm for data quantization based on the principles of Kashin representation. This approach hinges on decomposing any given vector, matrix, or tensor into two factors. The first factor maintains a small infinity norm, while the second exhibits a similarly constrain…

Cited by 1SourcePDFScholar
2024

SparseGrad: A Selective Method for Efficient Fine-tuning of MLP Layers

EMNLP 2024main

The performance of Transformer models has been enhanced by increasing the number of parameters and the length of the processed text. Consequently, fine-tuning the entire model becomes a memory-intensive process. High-performance methods for parameter-efficient fine-tuning (PEFT) typically work with…