Search Results for author:
Found 10 papers, 3 papers with code
Information Flow Control in Machine Learning through Modular Model Architecture
In today's machine learning (ML) models, any part of the training data can affect its output.
Structured Pruning is All You Need for Pruning CNNs at Initialization
In addition, since PreCropping compresses CNNs at initialization, the computational and memory costs of CNNs are reduced for both training and inference on commodity hardware.
Transformer Quality in Linear Time
We revisit the design choices in Transformers, and propose methods to address their weaknesses in handling long sequences.
Ranked #1 on
Language Modelling
on Wiki-40B
BulletTrain: Accelerating Robust Neural Network Training via Boundary Example Mining
Neural network robustness has become a central topic in machine learning in recent years.
Sinan: Data-Driven, QoS-Aware Cluster Management for Microservices
Cloud applications are increasingly shifting from large monolithic services, to large numbers of loosely-coupled, specialized microservices.
Contrastive Weight Regularization for Large Minibatch SGD
The minibatch stochastic gradient descent method (SGD) is widely applied in deep learning due to its efficiency and scalability that enable training deep networks with a large volume of data.
GuardNN: Secure Accelerator Architecture for Privacy-Preserving Deep Learning
This paper proposes GuardNN, a secure DNN accelerator that provides hardware-based protection for user data and model parameters even in an untrusted environment.
MGX: Near-Zero Overhead Memory Protection for Data-Intensive Accelerators
This paper introduces MGX, a near-zero overhead memory protection scheme for hardware accelerators.
Precision Gating: Improving Neural Network Efficiency with Dynamic Dual-Precision Activations
The proposed approach is applicable to a variety of DNN architectures and significantly reduces the computational cost of DNN execution with almost no accuracy loss.
Channel Gating Neural Networks
Combining our method with knowledge distillation reduces the compute cost of ResNet-18 by 2. 6$\times$ without accuracy drop on ImageNet.
