Federated Optimization with Doubly Regularized Drift Correction

no code implementations • 12 Apr 2024 • Xiaowen Jiang, Anton Rodomanov, Sebastian U. Stich

Federated learning is a distributed optimization paradigm that allows training machine learning models across decentralized devices while keeping the data localized.

Distributed Optimization Federated Learning

Efficient Halftoning via Deep Reinforcement Learning

no code implementations • 24 Apr 2023 • Haitian Jiang, Dongliang Xiong, Xiaowen Jiang, Li Ding, Liang Chen, Kai Huang

In this paper, we propose a fast and structure-aware halftoning method via a data-driven approach.

reinforcement-learning SSIM

Halftoning with Multi-Agent Deep Reinforcement Learning

no code implementations • 23 Jul 2022 • Haitian Jiang, Dongliang Xiong, Xiaowen Jiang, Aiguo Yin, Li Ding, Kai Huang

Deep neural networks have recently succeeded in digital halftoning using vanilla convolutional layers with high parallelism.

reinforcement-learning Reinforcement Learning (RL)

A Low Memory Footprint Quantized Neural Network for Depth Completion of Very Sparse Time-of-Flight Depth Maps

no code implementations • 25 May 2022 • Xiaowen Jiang, Valerio Cambareri, Gianluca Agresti, Cynthia Ifeyinwa Ugwu, Adriano Simonetto, Fabien Cardinaux, Pietro Zanuttigh

We also achieve low memory footprint for weights and activations by means of mixed precision quantization-at-training techniques.

Depth Completion Quantization