@misc{21857,
  abstract     = {The availability of powerful open-source large language models (LLMs) opens exciting use cases, such as using personal data to fine-tune these models to imitate a user’s unique writing style. Two key requirements for this functionality are personalization–in the sense that the output should recognizably reflect the user’s own writing style—and privacy–users may justifiably be wary of uploading extremely personal data, such as their email archive, to a third-party service. In this paper, we demonstrate the feasibility of training and running such an assistant, which we call Panza, on commodity hardware, for the specific use case of email generation. Panza’s personalization features are based on a combination of parameter-efficient fine-tuning using a variant of the Reverse Instructions technique [1] and Retrieval-Augmented Generation (RAG) [2]. We demonstrate that this combination allows us to fine-tune an LLM to reflect a user’s writing style using limited data, while executing on extremely limited resources, e.g. on a free Google Colab instance. Our key methodological contribution is the first detailed study of evaluation metrics for this task, and
of how different choices of system components–the use of RAG and of different fine-tuning approaches–impact the system’s performance. Additionally, we demonstrate that very little data - under 100 email samples - are sufficient to create models that convincingly imitate humans, showcasing a previously unknown attack vector in language models. We are releasing the full Panza code as well as three new email datasets licensed for research use.},
  author       = {Nicolicioiu, Armand and Iofinova, Eugenia B and Jovanovic, Andrej and Kurtic, Eldar and Nikdan, Mahdi and Panferov, Andrei and Markov, Ilia and Shavit, Nir and Alistarh, Dan-Adrian},
  booktitle    = {Third Conference on Parsimony and Learning (Proceedings Track)},
  keywords     = {LLMs, PEFT, LoRA, personalization, efficient ML},
  location     = {Tübíngen, Germany},
  publisher    = {OpenReview},
  title        = {{Panza: Investigating the feasibility of fully-local personalized text generation}},
  year         = {2026},
}

@inproceedings{18117,
  abstract     = {We investigate parameter-efficient fine-tuning (PEFT) methods that can provide good accuracy under limited computational and memory budgets in the context of large language models (LLMs). We present a new PEFT method called Robust Adaptation (RoSA) inspired by robust principal component analysis that jointly trains low-rank
 and highly-sparse components on top of a set of fixed pretrained weights to efficiently approximate the performance of a full-fine-tuning (FFT) solution. Across a series of challenging generative tasks such as grade-school math and SQL query generation, which require fine-tuning for good performance, we show that RoSA outperforms LoRA, pure sparse fine-tuning, and alternative hybrid methods at the same parameter budget, and can even recover the performance of FFT on some tasks. We provide system support for RoSA to complement the training algorithm, specifically in the form of sparse GPU kernels which enable memory- and computationally-efficient training, and show that it is also compatible with low-precision base weights, resulting in the first joint representation combining quantization, low-rank and sparse approximations. Our code is available at https://github.com/IST-DASLab/RoSA.},
  author       = {Nikdan, Mahdi and Tabesh, Soroush and Crncevic, Elvir and Alistarh, Dan-Adrian},
  booktitle    = {Proceedings of the 41st International Conference on Machine Learning},
  issn         = {2640-3498},
  location     = {Vienna, Austria},
  pages        = {38187--38206},
  publisher    = {ML Research Press},
  title        = {{RoSA: Accurate parameter-efficient fine-tuning via robust adaptation}},
  volume       = {235},
  year         = {2024},
}

@inproceedings{14460,
  abstract     = {We provide an efficient implementation of the backpropagation algorithm, specialized to the case where the weights of the neural network being trained are sparse. Our algorithm is general, as it applies to arbitrary (unstructured) sparsity and common layer types (e.g., convolutional or linear). We provide a fast vectorized implementation on commodity CPUs, and show that it can yield speedups in end-to-end runtime experiments, both in transfer learning using already-sparsified networks, and in training sparse networks from scratch. Thus, our results provide the first support for sparse training on commodity hardware.},
  author       = {Nikdan, Mahdi and Pegolotti, Tommaso and Iofinova, Eugenia B and Kurtic, Eldar and Alistarh, Dan-Adrian},
  booktitle    = {Proceedings of the 40th International Conference on Machine Learning},
  issn         = {2640-3498},
  location     = {Honolulu, Hawaii, HI, United States},
  pages        = {26215--26227},
  publisher    = {ML Research Press},
  title        = {{SparseProp: Efficient sparse backpropagation for faster training of neural networks at the edge}},
  volume       = {202},
  year         = {2023},
}