7 citations · 12 across the 6 of their papers we have counts for
7 papers
MCNC: Manifold-Constrained Reparameterization for Neural Compression
Chayne Thrash, Ali Abbasi, Reed Andreas +4
The outstanding performance of large foundational models across diverse tasks, from computer vision to speech and natural language processing, has significantly increased their dem…
BrainWash: A Poisoning Attack to Forget in Continual Learning
Ali Abbasi, Parsa Nooralinejad, Hamed Pirsiavash +1
Continual learning has gained substantial attention within the deep learning community, offering promising solutions to the challenging problem of sequential learning. Yet, a large…
NOLA: Compressing LoRA using Linear Combination of Random Basis
Soroush Abbasi Koohpayegani, KL Navaneet, Parsa Nooralinejad +2
Fine-tuning Large Language Models (LLMs) and storing them for each downstream task or domain is impractical because of the massive model size (e.g., 350GB in GPT-3). Current litera…
PRANC: Pseudo RAndom Networks for Compacting deep models
Parsa Nooralinejad, Ali Abbasi, Soroush Abbasi Koohpayegani +4
We demonstrate that a deep model can be reparametrized as a linear combination of several randomly initialized and frozen deep models in the weight space. During training, we seek…
Sparsity and Heterogeneous Dropout for Continual Learning in the Null Space of Neural Activations
Ali Abbasi, Parsa Nooralinejad, Vladimir Braverman +2
Continual/lifelong learning from a non-stationary input data stream is a cornerstone of intelligence. Despite their phenomenal performance in a wide variety of applications, deep n…
A Simple Baseline for Low-Budget Active Learning
Kossar Pourahmadi, Parsa Nooralinejad, Hamed Pirsiavash
Active learning focuses on choosing a subset of unlabeled data to be labeled. However, most such methods assume that a large subset of the data can be annotated. We are interested…
TaxoNN: A Light-Weight Accelerator for Deep Neural Network Training
Reza Hojabr, Kamyar Givaki, Kossar Pourahmadi +4
Emerging intelligent embedded devices rely on Deep Neural Networks (DNNs) to be able to interact with the real-world environment. This interaction comes with the ability to retrain…