In this paper, we provide an information-theoretic perspective on Variance-Invariance-
Covariance Regularization (VICReg) for self-supervised learning. To do so, we first …

Abstract Variance-Invariance-Covariance Regularization (VICReg) is a self-supervised
learning (SSL) method that has shown promising results on a variety of tasks. However, the …

The development of machine learning models requires a large amount of training data. Data
marketplace is a critical platform to trade high-quality and private-domain data that is not …

While post-training quantization receives popularity mostly due to its evasion in accessing
the original complete training dataset, its poor performance also stems from scarce images …

The Diffusion Transformers Models (DiTs) have transitioned the network architecture from
traditional UNets to transformers, demonstrating exceptional capabilities in image …

For on-device automatic speech recognition (ASR), quantization aware training (QAT) is
ubiquitous to achieve the trade-off between model predictive performance and efficiency …

Internet of Things (IoT) systems provide large amounts of data on all aspects of human
behavior. Machine learning techniques, especially deep neural networks (DNN), have …

Deep Learning (DL) has shown impressive performance in many mobile applications. Most
existing works have focused on reducing the computational and resource overheads of …

Stochastic computing (SC) has become a promising approximate computing solution by its
negligible resource occupancy and ultralow energy consumption. As a potential …

In this work we show that the size versus accuracy trade-off of neural network quantization
can be significantly improved by increasing the quantization dimensionality. We propose the …