RecShard: statistical feature-based memory optimization for industry-scale neural recommendation.
Geet SethiBilge AcunNiket AgarwalChristos KozyrakisCaroline TrippelCarole-Jean WuPublished in: ASPLOS (2022)
Keyphrases
- associative memory
- recommender systems
- optimization algorithm
- neural network
- collaborative filtering
- statistical analysis
- global optimization
- network architecture
- scale space
- data driven
- scale invariant
- optimization problems
- memory size
- gaussian markov random fields
- computing power
- optimization model
- memory requirements
- information theoretic
- optimization process
- constrained optimization
- biologically inspired
- statistical methods
- statistical information
- statistical models
- random access
- neural model
- website
- information systems