相关论文: AESOP: Adversarial Execution-path Selection to Ove…

As deep learning models are deployed on resource constrained edge platforms in autonomous driving systems, reli able knowledge of hardware behavior under resource degradation becomes an essential requirement. Therefore, we introduce a…

Building on previous work using reinforcement learning (RL) focused on identification of exfiltration paths, this work expands the methodology to include protocol and payload considerations. The former approach to exfiltration path…

Machine learning and AI have been recently embraced by many companies. Machine Learning Operations, (MLOps), refers to the use of continuous software engineering processes, such as DevOps, in the deployment of machine learning models to…

The majority of online continual learning (CL) advocates single-epoch training and imposes restrictions on the size of replay memory. However, single-epoch training would incur a different amount of computations per CL algorithm, and the…

As inference workloads for large language models (LLMs) scale to meet growing user demand, pipeline parallelism (PP) has become a widely adopted strategy for multi-GPU deployment, particularly in cross-node setups, to improve key-value (KV)…

As the accuracy of machine learning models increases at a fast rate, so does their demand for energy and compute resources. On a low level, the major part of these resources is consumed by data movement between different memory units.…

In the context of an efficient network traffic engineering process where the network continuously measures a new traffic matrix and updates the set of paths in the network, an automated process is required to quickly and efficiently…

Transformer-based language models spread FLOPs uniformly across input sequences. In this work we demonstrate that transformers can instead learn to dynamically allocate FLOPs (or compute) to specific positions in a sequence, optimising the…

The ability of machine learning (ML) classification models to resist small, targeted input perturbations -- known as adversarial attacks -- is a key measure of their safety and reliability. We show that floating-point non-associativity…

The critical path of a group of tasks is an important measure that is commonly used to guide task allocation and scheduling on parallel computers. The critical path is the longest chain of dependencies in an acyclic task dependence graph. A…

Deep Learning Systems (DLSs) are increasingly deployed in real-time applications, including those in resourceconstrained environments such as mobile and IoT devices. To address efficiency challenges, Dynamic Deep Learning Systems (DDLSs)…

Machine learning pipeline potentially consists of several stages of operations like data preprocessing, feature engineering and machine learning model training. Each operation has a set of hyper-parameters, which can become irrelevant for…

Machine Learning operations is unarguably a very important and also one of the hottest topics in Artificial Intelligence lately. Being able to define very clear hypotheses for actual real-life problems that can be addressed by machine…

We optimize pipeline parallelism for deep neural network (DNN) inference by partitioning model graphs into $k$ stages and minimizing the running time of the bottleneck stage, including communication. We give practical and effective…

Serving diverse NLP workloads with large language models is costly: at one enterprise partner, inference costs exceeded $200K/month despite over 70% of queries being routine tasks well within the capability of smaller models. We present…

Conditional decision generation with diffusion models has shown powerful competitiveness in reinforcement learning (RL). Recent studies reveal the relation between energy-function-guidance diffusion models and constrained RL problems. The…

This paper proposes a learning-based approach to accelerate the interior-point method (IPM) for solving optimal power flow (OPF) problems by learning the structure of the IPM central path from its early stable iterations. Unlike traditional…

Extensive studies have demonstrated that deep neural networks (DNNs) are vulnerable to adversarial attacks. Despite the significant progress in the attack success rate that has been made recently, the adversarial noise generated by most of…

Fault-tolerant deep learning accelerator is the basis for highly reliable deep learning processing and critical to deploy deep learning in safety-critical applications such as avionics and robotics. Since deep learning is known to be…

Deploying adversarially robust machine learning systems requires continuous trade-offs between robustness, cost, and latency. We present an autonomic decision-support framework providing a quantitative foundation for adaptive hardware…