Heavy-tails and randomized restarting beam search in goal-oriented neural sequence decoding

DOI10.1007/978-3-030-78230-6_8OpenAlexW3169683796MaRDI QIDQ2117205FDOQ2117205

Authors: Eldan Cohen, J. Christopher Beck 

Publication date: 21 March 2022

Full work available at URL: https://doi.org/10.1007/978-3-030-78230-6_8

zbMATH Keywords

beam searchneural sequence modelsrandomized restarts

Mathematics Subject Classification ID

Problem solving in the context of artificial intelligence (heuristics, search strategies, etc.) (68T20) Combinatorial optimization (90C27)

Cites Work

• Title not available (Why is that?)
• Deep learning
• Heavy-Tail Phenomena
• Simple statistical gradient-following algorithms for connectionist reinforcement learning
• Heavy-tailed phenomena in satisfiability and constraint satisfaction problems
• Optimal speedup of Las Vegas algorithms
• Statistical regimes across constrainedness regions
• Three-dimensional matching instances are rich in stable matchings

Uses Software

• LKH
• Concorde
• Rdkit
• DeepCoder
• CSGNet

This page was built for publication: Heavy-tails and randomized restarting beam search in goal-oriented neural sequence decoding

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2117205)