Related papers: Autotuning OpenCL Workgroup Size for Stencil Patte…
In this paper, we move towards combining large parametric models with non-parametric prototypical networks. We propose prototypical fine-tuning, a novel prototypical framework for fine-tuning pretrained language models (LM), which…
Machine learning (ML) involves private data and proprietary model parameters. MPC-based ML allows multiple parties to collaboratively run an ML workload without sharing their private data or model parameters using multi-party computing…
Modern computer systems typically conbine multicore CPUs with accelerators like GPUs for inproved performance and energy efficiency. However, these sys- tems suffer from poor performance portability, code tuned for one device must be…
Many artificial intelligence models process input data of different lengths and resolutions, making the shape of the tensors dynamic. The performance of these models depends on the shape of the tensors, which makes it difficult to optimize…
Models trained on data composed of different groups or domains can suffer from severe performance degradation under distribution shifts. While recent methods have largely focused on optimizing the worst-group objective, this often comes at…
When adapting ICL with or without fine-tuning, we are curious about whether the instruction-tuned language model is able to achieve well-calibrated results without suffering from the problem of overconfidence (i.e., miscalibration)…
Finding optimal hyperparameters for the machine learning algorithm can often significantly improve its performance. But how to choose them in a time-efficient way? In this paper we present the protocol of generating benchmark data…
Configuring a storage system to better serve an application is a challenging task complicated by a multidimensional, discrete configuration space and the high cost of space exploration (e.g., by running the application with different…
In multi-party collaborative learning, the parameter server sends a global model to each data holder for local training and then aggregates committed models globally to achieve privacy protection. However, both the dragger issue of…
Performance is an important non-functional aspect of the software requirement. Modern software systems are highly-configurable and misconfigurations may easily cause performance issues. A software system that suffers performance issues may…
We investigate a number of recently reported exact algorithms for the maximum clique problem (MCQ, MCR, MCS, BBMC). The program code used is presented and critiqued showing how small changes in implementation can have a drastic effect on…
Stencil computation is one of the most used kernels in a wide variety of scientific applications, ranging from large-scale weather prediction to solving partial differential equations. Stencil computations are characterized by three unique…
The extensive use of HPC infrastructures and frameworks for running dataintensive applications has led to a growing interest in data partitioning techniques and strategies. In fact, application performance can be heavily affected by how…
The rapid growth of microcontroller-based IoT devices has opened up numerous applications, from smart manufacturing to personalized healthcare. Despite the widespread adoption of energy-efficient microcontroller units (MCUs) in the Tiny…
Large Language Models (LLMs) have recently emerged as planners for language-instructed agents, generating sequences of actions to accomplish natural language tasks. However, their reliability remains a challenge, especially in long-horizon…
TensorFlow is a popular deep learning framework used by data scientists to solve a wide-range of machine learning and deep learning problems such as image classification and speech recognition. It also operates at a large scale and in…
During the initialization of a supercomputer job, no useful calculations are performed. A high proportion of initialization time results in idle computing resources and less computational efficiency. Certain methods and algorithms combining…
The paper combines research approaches that traditionally have been disjoint: 1) model checking as used in formal verification of programs, and 2) auto-tuning as often used in high-performance computing. Auto-tuning frameworks optimize…
Stochastic network calculus is a tool for computing error bounds on the performance of queueing systems. However, deriving accurate bounds for networks consisting of several queues or subject to non-independent traffic inputs is…
Kernel methods are a popular class of nonlinear predictive models in machine learning. Scalable algorithms for learning kernel models need to be iterative in nature, but convergence can be slow due to poor conditioning. Spectral…