Goto

Collaborating Authors

The Potential of Decentralized Artificial Intelligence in the Future

#artificialintelligence

When a decentralized computing model, like blockchain, is combined with artificial intelligence, the best of both worlds can be leveraged for a scale of resources. Decentralized Artificial intelligence is a model that allows for the isolation of processing without the downside of aggregate knowledge sharing. By virtue, it enables the user to process information independently, among varying computing apparatuses or devices. In doing so, one can achieve different results and then analyze the knowledge, creating new solutions to a problem which a centralized AI system would not be able to. Decentralized AI has incredible potential across businesses, science, and collective people.


An Accelerated Decentralized Stochastic Proximal Algorithm for Finite Sums

Neural Information Processing Systems

Modern large-scale finite-sum optimization relies on two key aspects: distribution and stochastic updates. For smooth and strongly convex problems, existing decentralized algorithms are slower than modern accelerated variance-reduced stochastic algorithms when run on a single machine, and are therefore not efficient. Centralized algorithms are fast, but their scaling is limited by global aggregation steps that result in communication bottlenecks. In this work, we propose an efficient \textbf{A}ccelerated \textbf{D}ecentralized stochastic algorithm for \textbf{F}inite \textbf{S}ums named ADFS, which uses local stochastic proximal updates and randomized pairwise communications between nodes. On $n$ machines, ADFS learns from $nm$ samples in the same time it takes optimal algorithms to learn from $m$ samples on one machine.


Communication Compression for Decentralized Training

Neural Information Processing Systems

Optimizing distributed learning systems is an art of balancing between computation and communication. There have been two lines of research that try to deal with slower networks: {\em communication compression} for low bandwidth networks, and {\em decentralization} for high latency networks. In this paper, We explore a natural question: {\em can the combination of both techniques lead to a system that is robust to both bandwidth and latency?} Although the system implication of such combination is trivial, the underlying theoretical principle and algorithm design is challenging: unlike centralized algorithms, simply compressing {\rc exchanged information, even in an unbiased stochastic way, within the decentralized network would accumulate the error and cause divergence.} In this paper, we develop a framework of quantized, decentralized training and propose two different strategies, which we call {\em extrapolation compression} and {\em difference compression}.


Decentralized Network for Artificial Intelligence - Effect.ai

#artificialintelligence

Our project introduces an open, decentralized network that provides services in the Artificial Intelligence market. This project is called The Effect Network. The 3 phases of The Effect Network require no fees, have a low barrier of entry and provide fast growth to its users. It runs seamlessly on the NEO blockchain and is fueled by a network NEP-5 token. The effect of this network will define the future relationship between humanity and AI.


Inter-Agent Variation Improves Dynamic Decentralized Task Allocation

AAAI Conferences

We examine the effects of inter-agent variation on the ability of a decentralized multi-agent system (MAS) to self-organize in response to dynamically changing task demands. In decentralized biological systems, inter-agent variation as minor as noise has been observed to improve a system's ability to redistribute agent resources in response to external stimuli. We compare the performance of two MAS consisting of agents with and without noisy sensors on a cooperative tracking problem and examine the effects of inter-agent variation on agent behaviors and how those behaviors affect system performance. Results show that small variations in how individual agents respond to stimuli can lead to more accurate and stable allocation of agent resources.