no code implementations • 10 Jul 2023 • Arti Vedula, Abhishek Gupta, Shaileshh Bojja Venkatakrishnan
To maximize rewards a miner must choose its network connections carefully, ensuring existence of paths to other miners that are on average of a lower latency compared to paths between other miners.
no code implementations • 25 Jun 2023 • Saket Gurukar, Shaileshh Bojja Venkatakrishnan, Balaraman Ravindran, Srinivasan Parthasarathy
Specifically, the subgraph-based sampling approaches such as ClusterGCN and GraphSAINT have achieved state-of-the-art performance on the node classification tasks.
1 code implementation • 23 Oct 2022 • Yunqi Zhang, Shaileshh Bojja Venkatakrishnan
A fundamental operation of applications in a decentralized Internet is data storage and retrieval.
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.
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.
no code implementations • ICLR 2019 • Ravichandra Addanki, Mohammad Alizadeh, Shaileshh Bojja Venkatakrishnan, Devavrat Shah, Qiaomin Xie, Zhi Xu
AlphaGo Zero (AGZ) introduced a new {\em tabula rasa} reinforcement learning algorithm that has achieved superhuman performance in the games of Go, Chess, and Shogi with no prior knowledge other than the rules of the game.
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.
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.
no code implementations • ICLR 2018 • Shaileshh Bojja Venkatakrishnan, Mohammad Alizadeh, Pramod Viswanath
By not limiting the representation to a fixed dimension, Graph2Seq scales naturally to graphs of arbitrary sizes and shapes.
2 code implementations • 16 Jan 2017 • Shaileshh Bojja Venkatakrishnan, Giulia Fanti, Pramod Viswanath
We propose a simple networking policy called Dandelion, which achieves nearly-optimal anonymity guarantees at minimal cost to the network's utility.
Cryptography and Security Information Theory Information Theory