We introduce a new function-preserving transformation for efficient neural architecture
search. This network transformation allows reusing previously trained networks and existing …

Techniques for automatically designing deep neural network architectures such as reinforcement
learning based approaches have recently shown promising results. However, their …

Efficient on-device learning requires a small memory footprint at training time to fit the tight
memory constraint. Existing work solves this problem by reducing the number of trainable …

We present APQ, a novel design methodology for efficient deep learning deployment. Unlike
previous methods that separately optimize the neural network architecture, pruning policy, …

Neural architecture search (NAS) has a great impact by automatically designing effective
neural network architectures. However, the prohibitive computational demand of conventional …

We address the challenging problem of efficient inference across many devices and resource
constraints, especially on edge devices. Conventional approaches either manually design …

Predicting user responses, such as clicks and conversions, is of great importance and has
found its usage inmany Web applications including recommender systems, websearch and …

Transformers are ubiquitous in Natural Language Processing (NLP) tasks, but they are
difficult to be deployed on hardware due to the intensive computation. To enable low-latency …

Automatically generating coherent and semantically meaningful text has many applications
in machine translation, dialogue systems, image captioning, etc. Recently, by combining with …

Pose estimation plays a critical role in human-centered vision applications. However, it is
difficult to deploy state-of-the-art HRNet-based pose estimation models on resource-…