Related papers: Accelerating Deep Learning Classification with Err…
Deep learning (DL) models have become core modules for many applications. However, deploying these models without careful performance benchmarking that considers both hardware and software's impact often leads to poor service and costly…
Diffusion language models offer parallel token generation and inherent bidirectionality, promising more efficient and powerful sequence modeling compared to autoregressive approaches. However, state-of-the-art diffusion models (e.g., Dream…
Deep hashing has been widely used for large-scale approximate nearest neighbor search due to its storage and search efficiency. However, existing deep hashing methods predominantly rely on abundant training data, leaving the more…
The effectiveness of deep neural networks (DNN) in vision, speech, and language processing has prompted a tremendous demand for energy-efficient high-performance DNN inference systems. Due to the increasing memory intensity of most DNN…
Recent approaches for learning policies to improve caching, target just one out of the prefetching, admission and eviction processes. In contrast, we propose an end to end pipeline to learn all three policies using machine learning. We also…
The design of effective online caching policies is an increasingly important problem for content distribution networks, online social networks and edge computing services, among other areas. This paper proposes a new algorithmic toolbox for…
Content-delivery applications can achieve scalability and reduce wide-area network traffic using geographically distributed caches. However, each deployed cache has an associated cost, and under time-varying request rates (e.g., a daily…
Deep active learning (AL) selects batches of instances for annotation to avoid retraining deep neural networks (DNNs) after each new label. Employing a naive top-$b$ selection can result in a batch of redundant (similar) instances. To…
Deep learning (DL) workloads are moving towards accelerators for faster processing and lower cost. Modern DL accelerators are good at handling the large-scale multiply-accumulate operations that dominate DL workloads; however, it is…
We study a classification problem where each feature can be acquired for a cost and the goal is to optimize a trade-off between the expected classification error and the feature cost. We revisit a former approach that has framed the problem…
In this paper, we present a deep learning (DL) algorithm for channel estimation in communication systems. We consider the time-frequency response of a fast fading communication channel as a two-dimensional image. The aim is to find the…
We consider the problem of optimally compressing and caching data across a communication network. Given the data generated at edge nodes and a routing path, our goal is to determine the optimal data compression ratios and caching decisions…
Efficient search operations in databases are paramount for timely retrieval of information various applications. This research introduces a novel approach, combining dynamicalgorithm1 selection and caching2 strategies, to optimize search…
Deep Neural Networks (DNNs) are witnessing increased adoption in multiple domains owing to their high accuracy in solving real-world problems. However, this high accuracy has been achieved by building deeper networks, posing a fundamental…
Videos take a lot of time to transport over the network, hence running analytics on the live video on embedded or mobile devices has become an important system driver. Considering that such devices, e.g., surveillance cameras or AR/VR…
KV caching is a fundamental technique for accelerating Large Language Model (LLM) inference by reusing key-value (KV) pairs from previous queries, but its effectiveness under limited memory is highly sensitive to the eviction policy. The…
Deep Learning is a very powerful machine learning model. Deep Learning trains a large number of parameters for multiple layers and is very slow when data is in large scale and the architecture size is large. Inspired from the shrinking…
We propose a unified methodology to analyse the performance of caches (both isolated and interconnected), by extending and generalizing a decoupling technique originally known as Che's approximation, which provides very accurate results at…
Deep Learning is increasingly being adopted by industry for computer vision applications running on embedded devices. While Convolutional Neural Networks' accuracy has achieved a mature and remarkable state, inference latency and throughput…
The deployment of large-scale models, such as large language models (LLMs), incurs substantial costs due to their computational demands. To mitigate these costs and address challenges related to scalability and data security, there is a…