Pruning is an effective way to reduce the huge inference cost of Transformer models.
However, prior work on pruning Transformers requires retraining the models. This can add …

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 …

Structural pruning can simplify network architecture and improve inference speed. We
propose Hardware-Aware Latency Pruning (HALP) that formulates structural pruning as a …

We propose a novel knowledge distillation framework for effectively teaching a sensorimotor
student agent to drive from the supervision of a privileged teacher agent. Current distillation …

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 …

Filter pruning is a technique that reduces computational complexity, inference time, and
memory footprint by removing unnecessary filters in convolutional neural networks (CNNs) …

The recent focus on the efficiency of deep neural networks (DNNs) has led to significant
work on model compression approaches, of which weight pruning is one of the most …

Realistic use of neural networks often requires adhering to multiple constraints on latency,
energy and memory among others. A popular approach to find fitting networks is through …

Sparsification-based pruning has been an important category in model compression.
Existing methods commonly set sparsity-inducing penalty terms to suppress the importance …

When deployed for risk-sensitive tasks, deep neural networks must include an uncertainty
estimation mechanism. Here we examine the relationship between deep architectures and …