We provide the optimal receive combining strategy for federated learning in
multiple-input multiple-output (MIMO) systems. Our proposed algorithm allows
the clients to perform individual gradient sparsification which greatly
improves performance in scenarios with heterogeneous (non i.i.d.) training
data. The proposed method beats the benchmark by a wide margin.

本文提出了一种优化接收组合策略的算法，用于多输入多输出系统中的联邦学习，该算法允许客户端执行个别梯度稀疏化以大大提高在具有异构（非 i.i.d.）训练数据场景下的性能，所提出的方法显著优于基准。

基于梯度稀疏化的盲目联邦边缘学习中的最优 MIMO 组合

Optimal MIMO Combining for Blind Federated Edge Learning with Gradient  Sparsification

Monocular 3D object detection has recently shown promising results, however
there remain challenging problems. One of those is the lack of invariance to
different camera intrinsic parameters, which can be observed across different
3D object datasets. Little effort has been made to exploit the combination of
heterogeneous 3D object datasets. In contrast to general intuition, we show
that more data does not automatically guarantee a better performance, but
rather, methods need to have a degree of 'camera independence' in order to
benefit from large and heterogeneous training data. In this paper we propose a
category-level pose estimation method based on instance segmentation, using
camera independent geometric reasoning to cope with the varying camera
viewpoints and intrinsics of different datasets. Every pixel of an instance
predicts the object dimensions, the 3D object reference points projected in 2D
image space and, optionally, the local viewing angle. Camera intrinsics are
only used outside of the learned network to lift the predicted 2D reference
points to 3D. We surpass camera independent methods on the challenging KITTI3D
benchmark and show the key benefits compared to camera dependent methods.

本文提出了一种基于实例分割的类别级位姿估计方法，利用相机独立几何推理来应对不同数据集的相机视角和内部参数变化，取得了在 KITTI3D 基准测试中超越相机依赖方法的优异表现。

MonoCInIS: 基于实例分割的相机无关单目 3D 目标检测

MonoCInIS: Camera Independent Monocular 3D Object Detection using  Instance Segmentation

We consider the problem of making efficient use of heterogeneous training
data in neural machine translation (NMT). Specifically, given a training
dataset with a sentence-level feature such as noise, we seek an optimal
curriculum, or order for presenting examples to the system during training. Our
curriculum framework allows examples to appear an arbitrary number of times,
and thus generalizes data weighting, filtering, and fine-tuning schemes. Rather
than relying on prior knowledge to design a curriculum, we use reinforcement
learning to learn one automatically, jointly with the NMT system, in the course
of a single training run. We show that this approach can beat uniform and
filtering baselines on Paracrawl and WMT English-to-French datasets by up to
+3.4 BLEU, and match the performance of a hand-designed, state-of-the-art
curriculum.

本研究运用强化学习方法，实现神经机器翻译中异质训练数据的有效生成和利用，提出课程学习框架，相比于传统方法，该方法展现出更好的表现和更强的数据泛化能力。