@inproceedings{20821,
  abstract     = {Modern deep neural networks exhibit heterogeneity across numerous layers of various types such as residuals, multi-head attention, etc., due to varying structures (dimensions, activation functions, etc.), distinct representation characteristics, which impact predictions. We develop a general layer-wise quantization framework with tight variance and code-length bounds, adapting to the heterogeneities over the course of training. We then apply a new layer-wise quantization technique within distributed variational inequalities (VIs), proposing a novel Quantized Optimistic Dual Averaging (QODA) algorithm with adaptive learning rates, which achieves competitive convergence rates for monotone VIs. We empirically show that QODA achieves up to a 150% speedup over the baselines in end-to-end training time for training Wasserstein GAN on 12+GPUs.},
  author       = {Nguyen, Anh Duc and Markov, Ilia and Wu, Frank Zhengqing and Ramezani-Kebrya, Ali and Antonakopoulos, Kimon and Alistarh, Dan-Adrian and Cevher, Volkan},
  booktitle    = {42nd International Conference on Machine Learning},
  issn         = {2640-3498},
  location     = {Vancouver, Canada},
  pages        = {46026--46072},
  publisher    = {ML Research Press},
  title        = {{Layer-wise quantization for quantized optimistic dual averaging}},
  volume       = {267},
  year         = {2025},
}

@unpublished{21858,
  abstract     = {The recent surge in high-quality open-source Generative AI text models (colloquially: LLMs), as well as efficient finetuning techniques, have opened the possibility of creating high-quality personalized models that generate text attuned to a specific individual’s needs and are capable of credibly imitating their writing style by refining an open-source model with that person’s own data. The technology to create such models is accessible to private individuals, and training and running such models can be done cheaply on consumer-grade hardware. While these advancements are a huge gain for usability and privacy, this position paper argues that the practical feasibility of impersonating specific individuals also introduces novel safety risks. For instance, this technology enables the creation of phishing emails
or fraudulent social media accounts, based on small amounts of publicly available text, or by the individuals themselves to escape AI text detection. We further argue that these risks are complementary to—and distinct from—the much-discussed risks of other impersonation attacks such as image, voice, or video deepfakes, and are not adequately addressed by the larger research community, or the current generation of open- and closed-source models.},
  author       = {Iofinova, Eugenia B and Jovanovic, Andrej and Alistarh, Dan-Adrian},
  booktitle    = {arXiv},
  title        = {{Position: It's time to act on the risk of efficient personalized text generation}},
  doi          = {10.48550/arXiv.2502.06560},
  year         = {2025},
}