**NetAdapt** is a network shrinking algorithm to adapt a pretrained network to a mobile platform given a real resource budget. NetAdapt can incorporate direct metrics, such as latency and energy, into the optimization to maximize the adaptation performance based on the characteristics of the platform. By using empirical measurements, NetAdapt can be applied to any platform as long as we can measure the desired metrics, without any knowledge of the underlying implementation of the platform. 

While many existing algorithms simplify networks based on the number of MACs or weights, optimizing those indirect metrics may not necessarily reduce the direct metrics, such as latency and energy consumption. To solve this problem, NetAdapt incorporates direct metrics into its adaptation algorithm. These direct metrics are evaluated using *empirical measurements*, so that detailed knowledge of the platform and toolchain is not required. NetAdapt automatically and progressively simplifies a pre-trained network until the resource budget is met while maximizing the accuracy.

**Decentralized Distributed Proximal Policy Optimization (DD-PPO)** is a method for distributed reinforcement learning in resource-intensive simulated environments. DD-PPO is distributed (uses multiple machines), decentralized (lacks a centralized server), and synchronous (no computation is ever `stale'), making it conceptually simple and easy to implement. 

Proximal Policy Optimization, or [PPO](https://paperswithcode.com/method/ppo), is a policy gradient method for reinforcement learning. The motivation was to have an algorithm with the data efficiency and reliable performance of [TRPO](https://paperswithcode.com/method/trpo), while using only first-order optimization. 

Let $r\_{t}\left(\theta\right)$ denote the probability ratio $r\_{t}\left(\theta\right) = \frac{\pi\_{\theta}\left(a\_{t}\mid{s\_{t}}\right)}{\pi\_{\theta\_{old}}\left(a\_{t}\mid{s\_{t}}\right)}$, so $r\left(\theta\_{old}\right) = 1$. TRPO maximizes a “surrogate” objective:

$$ L^{v}\left({\theta}\right) = \hat{\mathbb{E}}\_{t}\left[\frac{\pi\_{\theta}\left(a\_{t}\mid{s\_{t}}\right)}{\pi\_{\theta\_{old}}\left(a\_{t}\mid{s\_{t}}\right)})\hat{A}\_{t}\right] = \hat{\mathbb{E}}\_{t}\left[r\_{t}\left(\theta\right)\hat{A}\_{t}\right] $$

As a general abstraction, DD-PPO implements the following:
at step $k$, worker $n$ has a copy of the parameters, $\theta^k_n$, calculates the gradient, $\delta \theta^k_n$, and updates $\theta$ via 

$$ \theta^{k+1}\_n =  \text{ParamUpdate}\Big(\theta^{k}\_n, \text{AllReduce}\big(\delta \theta^k\_1, \ldots, \delta \theta^k\_N\big)\Big) = \text{ParamUpdate}\Big(\theta^{k}\_n, \frac{1}{N}  \sum_{i=1}^{N} { \delta \theta^k_i}   \Big) $$

where $\text{ParamUpdate}$ is any first-order optimization technique (e.g. gradient descent) and $\text{AllReduce}$ performs a reduction (e.g. mean) over all copies of a variable and returns the result to all workers.
Distributed DataParallel scales very well (near-linear scaling up to 32,000 GPUs), and is reasonably simple to implement (all workers synchronously running identical code).

DD-PPO

DD-PPO: Learning Near-Perfect PointGoal Navigators from 2.5 Billion Frames

NetAdapt

NetAdapt: Platform-Aware Neural Network Adaptation for Mobile Applications

An extension of Self-Attention to hypergraph
Skeleton-based action recognition aims to recognize human actions given human joint coordinates with skeletal interconnections. By defining a graph with joints as vertices and their natural connections as edges, previous works successfully adopted Graph Convolutional networks (GCNs) to model joint co-occurrences and achieved superior performance. More recently, a limitation of GCNs is identified, i.e., the topology is fixed after training. To relax such a restriction, Self-Attention (SA) mechanism has been adopted to make the topology of GCNs adaptive to the input, resulting in the state-of-the-art hybrid models. Concurrently, attempts with plain Transformers have also been made, but they still lag behind state-of-the-art GCN-based methods due to the lack of structural prior. Unlike hybrid models, we propose a more elegant solution to incorporate the bone connectivity into Transformer via a graph distance embedding. Our embedding retains the information of skeletal structure during training, whereas GCNs merely use it for initialization. More importantly, we reveal an underlying issue of graph models in general, i.e., pairwise aggregation essentially ignores the high-order kinematic dependencies between body joints. To fill this gap, we propose a new self-attention (SA) mechanism on hypergraph, termed Hypergraph Self-Attention (HyperSA), to incorporate intrinsic higher-order relations into the model. We name the resulting model Hyperformer, and it beats state-of-the-art graph models w.r.t. accuracy and efficiency on NTU RGB+D, NTU RGB+D 120, and Northwestern-UCLA datasets.

Source	NetAdapt: Platform-Aware Neural Network Adaptation for Mobile Applications
Year	2000
Data Source	CC BY-SA - https://paperswithcode.com