**Greedy Policy Search** (GPS) is a simple algorithm that learns a policy for test-time data augmentation based on the predictive performance on a validation set. GPS starts with an empty policy and builds it in an iterative fashion. Each step selects a sub-policy that provides the largest improvement in calibrated log-likelihood of ensemble predictions and adds it to the current policy.

**Herring** is a parameter server based distributed training method. It combines AWS's Elastic Fabric [Adapter](https://paperswithcode.com/method/adapter) (EFA) with a novel parameter sharding technique that makes better use of the available network bandwidth.  Herring uses EFA and balanced fusion buffer to optimally use the total bandwidth available across all nodes in the cluster. Herring reduces gradients hierarchically, reducing them inside the node first and then reducing across nodes. This enables more efficient use of PCIe bandwidth in the node and helps keep the gradient averaging related burden on GPU low.

Herring

Greedy Policy Search: A Simple Baseline for Learnable Test-Time Augmentation

**Prediction-aware One-To-One**, or **POTO**, is an assignment rule for object detection which dynamically assigns the foreground samples according to the quality of classification and regression simultaneously.

Source	Greedy Policy Search: A Simple Baseline for Learnable Test-Time Augmentation
Year	2000
Data Source	CC BY-SA - https://paperswithcode.com