Search Results for author:
Found 8 papers, 2 papers with code
Artemis: HE-Aware Training for Efficient Privacy-Preserving Machine Learning
Privacy-Preserving ML (PPML) based on Homomorphic Encryption (HE) is a promising foundational privacy technology.
Enhancing Cross-Category Learning in Recommendation Systems with Multi-Layer Embedding Training
At constant model quality, MLET allows embedding dimension, and model size, reduction by up to 16x, and 5. 8x on average, across the models.
Training with Multi-Layer Embeddings for Model Reduction
Increasing the dimension of embedding vectors improves model accuracy but comes at a high cost to model size.
FlexSA: Flexible Systolic Array Architecture for Efficient Pruned DNN Model Training
Based on our evaluation, FlexSA with the proposed compilation heuristic improves compute resource utilization of pruning and training modern CNN models by 37% compared to a conventional training accelerator with a large systolic array.
DeLTA: GPU Performance Model for Deep Learning Applications with In-depth Memory System Traffic Analysis
Training convolutional neural networks (CNNs) requires intense compute throughput and high memory bandwidth.
Buddy Compression: Enabling Larger Memory for Deep Learning and HPC Workloads on GPUs
However, GPU device memory tends to be relatively small and the memory capacity can not be increased by the user.
Hardware Architecture
PruneTrain: Fast Neural Network Training by Dynamic Sparse Model Reconfiguration
State-of-the-art convolutional neural networks (CNNs) used in vision applications have large models with numerous weights.
Mini-batch Serialization: CNN Training with Inter-layer Data Reuse
Training convolutional neural networks (CNNs) requires intense computations and high memory bandwidth.
