Linear Speedup In Saddle-Point Escape For Decentralized Non-Convex Optimization

This video program is a part of the Premium package:

Linear Speedup In Saddle-Point Escape For Decentralized Non-Convex Optimization


  • IEEE MemberUS $11.00
  • Society MemberUS $0.00
  • IEEE Student MemberUS $11.00
  • Non-IEEE MemberUS $15.00
Purchase

Linear Speedup In Saddle-Point Escape For Decentralized Non-Convex Optimization

0 views
  • Share
Under appropriate cooperation protocols and parameter choices, fully decentralized solutions for stochastic optimization have been shown to match the performance of centralized solutions and result in linear speedup (in the number of agents) relative to n
Under appropriate cooperation protocols and parameter choices, fully decentralized solutions for stochastic optimization have been shown to match the performance of centralized solutions and result in linear speedup (in the number of agents) relative to n