Deep neural networks are generally designed as a stack of differentiable layers, in which a
prediction is obtained only after running the full stack. Recently, some contributions have …

The advent of the Artificial Intelligent Internet of Things (AIoT) has sparked a revolution in the
deployment of intelligent systems, driving the need for innovative data processing …

This paper identifies a structural property of data distributions that enables deep neural
networks to learn hierarchically. We define the``staircase''property for functions over the …

Due to the need to store the intermediate activations for back-propagation, end-to-end (E2E)
training of deep networks usually suffers from high GPUs memory footprint. This paper aims …

The superior performance of modern deep networks usually comes with a costly training
procedure. This paper presents a new curriculum learning approach for the efficient training …

Federated learning is a powerful distributed learning scheme that allows numerous edge
devices to collaboratively train a model without sharing their data. However, training is …

Federated learning (FL) operates based on model exchanges between the server and the
clients, and suffers from significant communication as well as client-side computation …

Training deep neural networks on large-scale datasets requires significant hardware
resources whose costs (even on cloud platforms) put them out of reach of smaller …

While the backpropagation of error algorithm enables deep neural network training, it
implies (i) bidirectional synaptic weight transport and (ii) update locking until the forward and …

We introduce and study the problem of Online Continual Compression, where one attempts
to simultaneously learn to compress and store a representative dataset from a non iid data …