相关论文: Automatic Tuning of Tensorflow's CPU Backend using…

Variational Autoencoder based Bayesian Optimization (VAE-BO) has demonstrated its excellent performance in addressing high-dimensional structured optimization problems. However, current mainstream methods overlook the potential of utilizing…

Convolution is one of the fundamental operations of deep neural networks with demanding matrix computation. In a graphic processing unit (GPU), Tensor Core is a specialized matrix processing hardware equipped with reduced-precision…

We consider the task of generating functionally correct code using large language models (LLMs). The correctness of generated code is influenced by the prompt used to query the given base LLM. We formulate the problem of finding the…

Neural network optimization remains one of the most consequential yet poorly understood challenges in modern AI research, where improvements in training algorithms can lead to enhanced feature learning in foundation models,…

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…

Genetic algorithm (GA) is typically used to solve nonlinear model predictive control's optimization problem. However, the size of the search space in which the GA searches for the optimal control inputs is crucial for its applicability to…

Neural networks have been applied to control problems, typically by combining data, differential equation residuals, and objective costs in the training loss or by incorporating auxiliary architectural components. Instead, we propose a…

The development of large-scale foundation models, particularly Large Language Models (LLMs), is constrained by significant computational and memory bottlenecks. These challenges elevate throughput optimization from a mere engineering task…

The performance of many algorithms in the fields of hard combinatorial problem solving, machine learning or AI in general depends on tuned hyperparameter configurations. Automated methods have been proposed to alleviate users from the…

There is a huge demand for on-device execution of deep learning algorithms on mobile and embedded platforms. These devices present constraints on the application due to limited resources and power. Hence, developing energy-efficient…

In this paper, we present a cross-entropy optimization method for hyperparameter optimization in stochastic gradient-based approaches to train deep neural networks. The value of a hyperparameter of a learning algorithm often has great…

Efficient learning and model compression algorithm for deep neural network (DNN) is a key workhorse behind the rise of deep learning (DL). In this work, we propose a message passing based Bayesian deep learning algorithm called EM-TDAMP to…

Deep Learning (DL) frameworks are now widely used, simplifying the creation of complex models as well as their integration to various applications even to non DL experts. However, like any other programs, they are prone to bugs. This paper…

Many machine learning models require a training procedure based on running stochastic gradient descent. A key element for the efficiency of those algorithms is the choice of the learning rate schedule. While finding good learning rates…

Software packages like TensorFlow and PyTorch are designed to support linear algebra operations, and their speed and usability determine their success. However, by prioritising speed, they often neglect memory requirements. As a…

Optimizing discrete black-box functions is key in several domains, e.g. protein engineering and drug design. Due to the lack of gradient information and the need for sample efficiency, Bayesian optimization is an ideal candidate for these…

The need to collect data via expensive measurements of black-box functions is prevalent across science, engineering and medicine. As an example, hyperparameter tuning of a large AI model is critical to its predictive performance but is…

Parameterizable machine learning (ML) accelerators are the product of recent breakthroughs in ML. To fully enable their design space exploration (DSE), we propose a physical-design-driven, learning-based prediction framework for…

We consider distributed optimization under communication constraints for training deep learning models. We propose a new algorithm, whose parameter updates rely on two forces: a regular gradient step, and a corrective direction dictated by…

Fine-tuning large pre-trained models for downstream tasks has become a fundamental approach in natural language processing. Fully fine-tuning all model parameters is computationally expensive and memory-intensive, especially in…