Related papers: Efficient Multitask Learning on Resource-Constrain…
Task-based programming models have risen in popularity as an alternative to traditional fork-join parallelism. They are better suited to write applications with irregular parallelism that can present load imbalance. However, these…
The deployment of inference services at the network edge, called edge inference, offloads computation-intensive inference tasks from mobile devices to edge servers, thereby enhancing the former's capabilities and battery lives. In a…
While previous work on energy-efficient algorithms focused on assumption that tasks can be assigned to any processor, we initially study the problem of task scheduling on restricted parallel processors. The objective is to minimize the…
Deep learning architectures for supervised learning on tabular data range from simple multilayer perceptrons (MLP) to sophisticated Transformers and retrieval-augmented methods. This study highlights a major, yet so far overlooked…
As machine learning inferences increasingly move to edge devices, adapting to diverse computational capabilities, hardware, and memory constraints becomes more critical. Instead of relying on a pre-trained model fixed for all future…
The rise of LLMs has driven demand for private serverless deployments, characterized by moderate-sized models and infrequent requests. While existing serverless solutions follow exclusive GPU allocation, we take a step back to explore…
Multi-task learning (MTL) encapsulates multiple learned tasks in a single model and often lets those tasks learn better jointly. However, when deploying MTL onto those real-world systems that are often resource-constrained or…
Transformer-based models are becoming more and more intelligent and are revolutionizing a wide range of human tasks. To support their deployment, AI labs offer inference services that consume hundreds of GWh of energy annually and charge…
Scheduling flexible sources to promote the integration of renewable generation is one fundamental problem for operating active distribution networks (ADNs). However, existing works are usually based on power flow models, which require…
In a cloud computing job with many parallel tasks, the tasks on the slowest machines (straggling tasks) become the bottleneck in the job completion. Computing frameworks such as MapReduce and Spark tackle this by replicating the straggling…
We propose an approach to Multitask Learning (MTL) to make deep learning models faster and lighter for applications in which multiple tasks need to be solved simultaneously, which is particularly useful in embedded, real-time systems. We…
This paper investigates the use of nonparametric kernel-regression to obtain a tasksimilarity aware meta-learning algorithm. Our hypothesis is that the use of tasksimilarity helps meta-learning when the available tasks are limited and may…
This paper investigates the usage of FPGA devices for energy-efficient exact kNN search in high-dimension latent spaces. This work intercepts a relevant trend that tries to support the increasing popularity of learned representations based…
Transformer-based language models such as BERT provide significant accuracy improvement for a multitude of natural language processing (NLP) tasks. However, their hefty computational and memory demands make them challenging to deploy to…
Recent breakthroughs in Artificial Intelligence have shown that the combination of tree-based planning with deep learning can lead to superior performance. We present Adaptive Entropy Tree Search (ANTS) - a novel algorithm combining…
In this work, we investigate the potential utility of parallelization for meeting real-time constraints and minimizing energy. We consider malleable Gang scheduling of implicit-deadline sporadic tasks upon multiprocessors. We first show the…
The rapid advancement of large language models has unlocked remarkable capabilities across a diverse array of natural language processing tasks. However, the considerable differences among available LLMs-in terms of cost, performance, and…
The Tsetlin Machine (TM) offers high-speed inference on resource-constrained devices such as CPUs. Its logic-driven operations naturally lend themselves to parallel execution on modern CPU architectures. Motivated by this, we propose an…
We present a novel federated multi-task learning method that leverages cross-client similarity to enable personalized learning for each client. To avoid transmitting the entire model to the parameter server, we propose a…
Deep learning models rely on highly optimized tensor libraries for efficient inference on heterogeneous hardware. Current deep compilers typically predetermine layouts of tensors and then optimize loops of operators. However, such…