相关论文: PATSMA: Parameter Auto-tuning for Shared Memory Al…

Sharing parameters in multi-agent deep reinforcement learning has played an essential role in allowing algorithms to scale to a large number of agents. Parameter sharing between agents significantly decreases the number of trainable…

Developing parallel algorithms efficiently requires careful management of concurrency across diverse hardware architectures. C++ executors provide a standardized interface that simplifies the development process, allowing developers to…

Efficiency of self-optimizing systems is heavily dependent on their optimization strategies, e.g., choosing exact or approximate solver. A choice of such a strategy, in turn, is influenced by numerous factors, such as re-optimization time,…

We investigate parameter-efficient fine-tuning (PEFT) methods that can provide good accuracy under limited computational and memory budgets in the context of large language models (LLMs). We present a new PEFT method called Robust…

Parametric analysis is a powerful tool for designing modern embedded systems, because it permits to explore the space of design parameters, and to check the robustness of the system with respect to variations of some uncontrollable…

Sparse matrix vector multiplication (SpMV) is an important kernel in scientific and engineering applications. The previous optimizations are sparse matrix format specific and expose the choice of the best format to application programmers.…

Parallel programming remains a daunting challenge, from the struggle to express a parallel algorithm without cluttering the underlying synchronous logic, to describing which devices to employ in a calculation, to correctness. Over the…

The increasing complexity and diversity of hardware accelerators in modern computing systems demand flexible, low-overhead program analysis tools. We present PASTA, a low-overhead and modular Program AnalysiS Tool Framework for…

Parameter management is essential for distributed training of large machine learning (ML) tasks. Some ML tasks are hard to distribute because common approaches to parameter management can be highly inefficient. Advanced parameter management…

With the decline of Moore's law, optimizing program performance has become a major focus of software research. However, high-level optimizations such as API and algorithm changes remain elusive due to the difficulty of understanding the…

This paper proposes a method for calibrating control parameters. Examples of such control parameters are gains of PID controllers, weights of a cost function for optimal control, filter coefficients, the sliding surface of a sliding mode…

Optimizing the performance of computational fluid dynamics (CFD) applications accelerated by graphics processing units (GPUs) is crucial for efficient simulations. In this study, we employed a machine learning-based autotuning technique to…

The research activity outlined in this PhD thesis is devoted to define a general approach, a concrete architecture and a prototype Process Management System (PMS) for the automated adaptation of dynamic processes at run-time, on the basis…

This work introduces ParAMS -- a versatile Python package that aims to make parameterization workflows in computational chemistry and physics more accessible, transparent and reproducible. We demonstrate how ParAMS facilitates the parameter…

In this paper, we propose sparsity-aware data-selective adaptive filtering algorithms with adjustable penalties. Prior work incorporates a penalty function into the cost function used in the optimization that originates the algorithms to…

Continual learning methods based on pre-trained models (PTM) have recently gained attention which adapt to successive downstream tasks without catastrophic forgetting. These methods typically refrain from updating the pre-trained parameters…

Despite its flexibility to learn diverse inductive biases in machine learning programs, meta learning (i.e., learning to learn) has long been recognized to suffer from poor scalability due to its tremendous compute/memory costs, training…

Parameter-efficient fine-tuning methods have emerged as a promising solution for adapting pre-trained models to various downstream tasks. While these methods perform well in single-task learning, extending them to multi-task learning…

A wide range of NLP tasks benefit from the fine-tuning of pretrained language models (PLMs). However, a number of redundant parameters which contribute less to the downstream task are observed in a directly fine-tuned model. We consider the…

We introduce CAPA, a parameter-efficient test-time optimization framework that adapts pre-trained 3D foundation models (FMs) for depth completion, using sparse geometric cues. Unlike prior methods that train task-specific encoders for…