InTune: Reinforcement Learning-based Data Pipeline Optimization for Deep Recommendation Models.
Kabir NagrechaLingyi LiuPablo DelgadoPrasanna PadmanabhanPublished in: CoRR (2023)
Keyphrases
- data sets
- database
- data analysis
- reinforcement learning
- data sources
- data processing
- statistical methods
- experimental data
- prior knowledge
- accurate models
- spatial data
- genetic algorithm
- image data
- data quality
- previously learned
- data collection
- knowledge discovery
- databases
- dynamic programming
- machine learning
- data structure
- high quality
- training data
- data distribution
- predictive model
- historical data
- learning algorithm
- original data
- network structure
- data points
- association rules
- high dimensional
- input data
- probabilistic model