11 citations · 19 across the 23 of their papers we have counts for
10 papers · 1 filter
Theoretical Guarantees for One-Shot Magnitude Pruning and Compute-Adaptive Early Exit
Erdem Koyuncu
We study compute reduction in neural networks through a unified partial versus full computation view, captured by one-shot magnitude pruning in the static regime and early exit in…
Model-Distributed Inference for Large Language Models at the Edge
Davide Macario, Hulya Seferoglu, Erdem Koyuncu
We introduce Model-Distributed Inference for Large-Language Models (MDI-LLM), a novel framework designed to facilitate the deployment of state-of-the-art large-language models (LLM…
Memorization Capacity of Neural Networks with Conditional Computation
Erdem Koyuncu
Many empirical studies have demonstrated the performance benefits of conditional computation in neural networks, including reduced inference time and power consumption. We study th…
Pruning Early Exit Networks
Alperen Görmez, Erdem Koyuncu
Deep learning models that perform well often have high computational costs. In this paper, we combine two approaches that try to reduce the computational cost while keeping the mod…
Federated Momentum Contrastive Clustering
Runxuan Miao, Erdem Koyuncu
We present federated momentum contrastive clustering (FedMCC), a learning framework that can not only extract discriminative representations over distributed local data but also pe…
Robust Principal Component Analysis Using a Novel Kernel Related with the L1-Norm
Hongyi Pan, Diaa Badawi, Erdem Koyuncu +1
We consider a family of vector dot products that can be implemented using sign changes and addition operations only. The dot products are energy-efficient as they avoid the multipl…
ECM: Early Exit via Class Means for Efficient Supervised and Unsupervised Learning
Alperen Görmez, Venkat R. Dasari, Erdem Koyuncu
State-of-the-art neural networks with early exit mechanisms often need considerable amount of training and fine tuning to achieve good performance with low computational cost. We p…
Quantizing Multiple Sources to a Common Cluster Center: An Asymptotic Analysis
Erdem Koyuncu
We consider quantizing an -dimensional sample, which is obtained by concatenating vectors from datasets of -dimensional vectors, to a -dimensional cluster center. The…
A Generalization of Principal Component Analysis
Samuele Battaglino, Erdem Koyuncu
Conventional principal component analysis (PCA) finds a principal vector that maximizes the sum of second powers of principal components. We consider a generalized PCA that aims at…
Robust and Computationally-Efficient Anomaly Detection using Powers-of-Two Networks
Usama Muneeb, Erdem Koyuncu, Yasaman Keshtkarjahromi +3
Robust and computationally efficient anomaly detection in videos is a problem in video surveillance systems. We propose a technique to increase robustness and reduce computational…