Low-Rank Gradient Descent for Memory-Efficient Training of Deep In-Memory Arrays.
Siyuan HuangBrian D. HoskinsMatthew W. DanielsMark D. StilesGina C. AdamPublished in: ACM J. Emerg. Technol. Comput. Syst. (2023)
Keyphrases
- memory efficient
- low rank
- external memory
- matrix factorization
- convex optimization
- missing data
- stochastic gradient descent
- linear combination
- low rank matrix
- matrix completion
- rank minimization
- singular value decomposition
- matrix decomposition
- semi supervised
- high order
- trace norm
- singular values
- memory space
- high dimensional data
- supervised learning
- minimization problems
- robust principal component analysis
- kernel matrix
- training samples
- cost function
- data sets
- nonnegative matrix factorization
- main memory
- low rank approximation
- recommender systems
- training set
- pattern recognition
- objective function
- data mining