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

Deploying foundation models is increasingly constrained by memory footprint, latency, and hardware costs. Post-training compression can mitigate these bottlenecks by reducing the precision of model parameters without significantly degrading…

In this paper, we develop an online method that leverages machine learning to obtain feasible solutions to the AC optimal power flow (OPF) problem with negligible optimality gaps on extremely fast timescales (e.g., milliseconds), bypassing…

In our prior work, LayerPipe, we had introduced an approach to accelerate training of convolutional, fully connected, and spiking neural networks by overlapping forward and backward computation. However, despite empirical success, a…

Parallel dataflow systems are a central part of most analytic pipelines for big data. The iterative nature of many analysis and machine learning algorithms, however, is still a challenge for current systems. While certain types of bulk…

Accurate performance prediction is essential for optimizing scientific applications on modern high-performance computing (HPC) architectures. Widely used performance models primarily focus on cache and memory bandwidth, which is suitable…

In this paper we present two versions of a parallel working-set map on p processors that supports searches, insertions and deletions. In both versions, the total work of all operations when the map has size at least p is bounded by the…

Adversarial attacks have the potential to mislead deep neural network classifiers by introducing slight perturbations. Developing algorithms that can mitigate the effects of these attacks is crucial for ensuring the safe use of artificial…

Autonomous driving faces significant challenges in achieving human-like iterative decision-making, which continuously generates, evaluates, and refines trajectory proposals. Current generation-evaluation frameworks isolate trajectory…

Deep neural networks ( DNNs ) are becoming a key enabling technology for many application domains. However, on-device inference on battery-powered, resource-constrained embedding systems is often infeasible due to prohibitively long…

We present the One Pass ImageNet (OPIN) problem, which aims to study the effectiveness of deep learning in a streaming setting. ImageNet is a widely known benchmark dataset that has helped drive and evaluate recent advancements in deep…

We present SEIF, a methodology that combines static analysis with symbolic execution to verify and explicate information flow paths in a hardware design. SEIF begins with a statically built model of the information flow through a design and…

We examine the problem of smoothed online optimization, where a decision maker must sequentially choose points in a normed vector space to minimize the sum of per-round, non-convex hitting costs and the costs of switching decisions between…

The Mixture-of-Experts (MoE) model has emerged as a prominent architecture in the field of Large Language Models (LLMs), providing a better balance between model performance and computational efficiency. However the General Matrix Multiply…

Many real-time applications (e.g., Augmented/Virtual Reality, cognitive assistance) rely on Deep Neural Networks (DNNs) to process inference tasks. Edge computing is considered a key infrastructure to deploy such applications, as moving…

Edge accelerators such as Nvidia Jetsons are becoming an integral part of the computing continuum, and are often used for DNN inferencing and training. Nvidia Jetson edge devices have $2000$+ CUDA cores within a $70$W power envelope and…

In recent years, Large Language Models (LLMs) have exhibited remarkable capabilities, driving advancements in real-world applications. However, training LLMs on increasingly long input sequences imposes significant challenges due to high…

When solving decision and optimisation problems, many competing algorithms (model and solver choices) have complementary strengths. Typically, there is no single algorithm that works well for all instances of a problem. Automated algorithm…

Adversarial training is a computationally expensive task and hence searching for neural network architectures with robustness as the criterion can be challenging. As a step towards practical automation, this work explores the efficacy of a…

Looped transformers apply a shared block multiple times and have emerged as a parameter-efficient route to scaling compute in language models. However, at fixed FLOPs a looped model has strictly less capacity than a baseline transformer. We…

Frontier models increasingly adopt Mixture-of-Experts (MoE) architectures to achieve large-model performance at reduced cost. However, training MoE models on HPC platforms is hindered by large memory footprints, frequent large-scale…