Related papers: WeightAlign: Normalizing Activations by Weight Ali…

In this short note, we propose a new method for quantizing the weights of a fully trained neural network. A simple deterministic pre-processing step allows us to quantize network layers via memoryless scalar quantization while preserving…

The performance of deep neural networks scales with dataset size and label quality, rendering the efficient mitigation of low-quality data annotations crucial for building robust and cost-effective systems. Existing strategies to address…

Batch Normalization (BN) and its variants have delivered tremendous success in combating the covariate shift induced by the training step of deep learning methods. While these techniques normalize feature distributions by standardizing with…

We propose BinaryRelax, a simple two-phase algorithm, for training deep neural networks with quantized weights. The set constraint that characterizes the quantization of weights is not imposed until the late stage of training, and a…

Batch normalization (BN) is a ubiquitous operation in deep neural networks, primarily used to improve stability and regularization during training. BN centers and scales feature maps using sample means and variances, which are naturally…

Deep neural networks have useful applications in many different tasks, however their performance can be severely affected by changes in the data distribution. For example, in the biomedical field, their performance can be affected by…

The large memory requirements of deep neural networks limit their deployment and adoption on many devices. Model compression methods effectively reduce the memory requirements of these models, usually through applying transformations such…

Recent work has shown that using unlabeled data in semi-supervised learning is not always beneficial and can even hurt generalization, especially when there is a class mismatch between the unlabeled and labeled examples. We investigate this…

Artificial neural network (ANN) is a very useful tool in solving learning problems. Boosting the performances of ANN can be mainly concluded from two aspects: optimizing the architecture of ANN and normalizing the raw data for ANN. In this…

This paper studies the Binary Neural Networks (BNNs) in which weights and activations are both binarized into 1-bit values, thus greatly reducing the memory usage and computational complexity. Since the modern deep neural networks are of…

Compressing and pruning large machine learning models has become a critical step towards their deployment in real-world applications. Standard pruning and compression techniques are typically designed without taking the structure of the…

Lately, post-training quantization methods have gained considerable attention, as they are simple to use, and require only a small unlabeled calibration set. This small dataset cannot be used to fine-tune the model without significant…

Large Language Models (LLMs) excel in NLP, but their demands hinder their widespread deployment. While Quantization-Aware Training (QAT) offers a solution, its extensive training costs make Post-Training Quantization (PTQ) a more practical…

Comparing outcomes across hospitals, often to identify underperforming hospitals, is a critical task in health services research. However, naive comparisons of average outcomes, such as surgery complication rates, can be misleading because…

Recently, the number of parameters in DNNs has explosively increased, as exemplified by LLMs (Large Language Models), making inference on small-scale computers more difficult. Model compression technology is, therefore, essential for…

Stochastic neural net weights are used in a variety of contexts, including regularization, Bayesian neural nets, exploration in reinforcement learning, and evolution strategies. Unfortunately, due to the large number of weights, all the…

Existing continual learning methods use Batch Normalization (BN) to facilitate training and improve generalization across tasks. However, the non-i.i.d and non-stationary nature of continual learning data, especially in the online setting,…

We present Sandwich Batch Normalization (SaBN), a frustratingly easy improvement of Batch Normalization (BN) with only a few lines of code changes. SaBN is motivated by addressing the inherent feature distribution heterogeneity that one can…

This paper proposes Quantizable DNNs, a special type of DNNs that can flexibly quantize its bit-width (denoted as `bit modes' thereafter) during execution without further re-training. To simultaneously optimize for all bit modes, a…

Batch Normalization (BN) is widely used in {centralized} deep learning to improve convergence and generalization. However, in {federated} learning (FL) with decentralized data, prior work has observed that training with BN could hinder…