Neural Rate Control for Video Encoding using Imitation Learning

no code implementations • 9 Dec 2020 • Hongzi Mao, Chenjie Gu, Miaosen Wang, Angie Chen, Nevena Lazic, Nir Levine, Derek Pang, Rene Claus, Marisabel Hechtman, Ching-Han Chiang, Cheng Chen, Jingning Han

In modern video encoders, rate control is a critical component and has been heavily engineered.

Data Augmentation Imitation Learning

High-Dimensional Contextual Policy Search with Unknown Context Rewards using Bayesian Optimization

1 code implementation • NeurIPS 2020 • Qing Feng , Ben Letham, Hongzi Mao, Eytan Bakshy

Contextual policies are used in many settings to customize system parameters and actions to the specifics of a particular setting.

Bayesian Optimization

Real-world Video Adaptation with Reinforcement Learning

no code implementations • 28 Aug 2020 • Hongzi Mao, Shannon Chen, Drew Dimmery, Shaun Singh, Drew Blaisdell, Yuandong Tian, Mohammad Alizadeh, Eytan Bakshy

Client-side video players employ adaptive bitrate (ABR) algorithms to optimize user quality of experience (QoE).

Bayesian Optimization reinforcement-learning +1

Learning Generalizable Device Placement Algorithms for Distributed Machine Learning

1 code implementation • NeurIPS 2019 • Ravichandra Addanki, Shaileshh Bojja Venkatakrishnan, Shreyan Gupta, Hongzi Mao, Mohammad Alizadeh

We present Placeto, a reinforcement learning (RL) approach to efficiently find device placements for distributed neural network training.

BIG-bench Machine Learning Reinforcement Learning (RL)

Park: An Open Platform for Learning-Augmented Computer Systems

1 code implementation • NeurIPS 2019 • Hongzi Mao, Parimarjan Negi, Akshay Narayan, Hanrui Wang, Jiacheng Yang, Haonan Wang, Ryan Marcus, Ravichandra Addanki, Mehrdad Khani Shirkoohi, Songtao He, Vikram Nathan, Frank Cangialosi, Shaileshh Venkatakrishnan, Wei-Hung Weng, Song Han, Tim Kraska, Dr.Mohammad Alizadeh

We present Park, a platform for researchers to experiment with Reinforcement Learning (RL) for computer systems.

reinforcement-learning Reinforcement Learning (RL)

Interpreting Deep Learning-Based Networking Systems

2 code implementations • 9 Oct 2019 • Zili Meng, Minhu Wang, Jiasong Bai, Mingwei Xu, Hongzi Mao, Hongxin Hu

While many deep learning (DL)-based networking systems have demonstrated superior performance, the underlying Deep Neural Networks (DNNs) remain blackboxes and stay uninterpretable for network operators.

Placeto: Learning Generalizable Device Placement Algorithms for Distributed Machine Learning

3 code implementations • 20 Jun 2019 • Ravichandra Addanki, Shaileshh Bojja Venkatakrishnan, Shreyan Gupta, Hongzi Mao, Mohammad Alizadeh

Unlike prior approaches that only find a device placement for a specific computation graph, Placeto can learn generalizable device placement policies that can be applied to any graph.

BIG-bench Machine Learning Reinforcement Learning (RL)

Learning Scheduling Algorithms for Data Processing Clusters

2 code implementations • 3 Oct 2018 • Hongzi Mao, Malte Schwarzkopf, Shaileshh Bojja Venkatakrishnan, Zili Meng, Mohammad Alizadeh

Efficiently scheduling data processing jobs on distributed compute clusters requires complex algorithms.

Reinforcement Learning (RL) Scheduling

Variance Reduction for Reinforcement Learning in Input-Driven Environments

no code implementations • ICLR 2019 • Hongzi Mao, Shaileshh Bojja Venkatakrishnan, Malte Schwarzkopf, Mohammad Alizadeh

We consider reinforcement learning in input-driven environments, where an exogenous, stochastic input process affects the dynamics of the system.

Meta-Learning Object Tracking +3