Related papers: Studying the Impact of TensorFlow and PyTorch Bind…
Normalizing flows model probability distributions through an expressive tractable density. They transform a simple base distribution, such as a Gaussian, through a sequence of invertible functions, which are referred to as layers. These…
PyTorch has ascended as a premier machine learning framework, yet it lacks a native and comprehensive library for decision and control tasks suitable for large development teams dealing with complex real-world data and environments. To…
This article describes some common issues encountered in the use of Direct Numerical Simulation (DNS) turbulent flow data for machine learning. We focus on two specific issues; 1) the requirements for a fair validation set, and 2) the…
Progress in AI is hindered by the lack of a programming language with all the requisite features. Libraries like PyTorch and TensorFlow provide automatic differentiation and efficient GPU implementation, but are additions to Python, which…
Finding errors in machine learning applications requires a thorough exploration of their behavior over data. Existing approaches used by practitioners are often ad-hoc and lack the abstractions needed to scale this process. We present…
Low-precision training reduces computational cost and produces efficient models. Recent research in developing new low-precision training algorithms often relies on simulation to empirically evaluate the statistical effects of quantization…
Machine learning education faces a fundamental gap: students learn algorithms without understanding the systems that execute them. They study gradient descent without measuring memory, attention mechanisms without analyzing O(N^2) scaling,…
Word embeddings have become essential components in various information retrieval and natural language processing tasks, such as ranking, document classification, and question answering. However, despite their widespread use, traditional…
We present a framework for specifying, training, evaluating, and deploying machine learning models. Our focus is on simplifying cutting edge machine learning for practitioners in order to bring such technologies into production. Recognizing…
Multi-turn instruction following capability constitutes a core competency of large language models (LLMs) in real-world applications. Existing evaluation benchmarks predominantly focus on fine-grained constraint satisfaction and…
Current benchmarks for evaluating neural code models focus on only a small subset of programming languages, excluding many popular languages such as Go or Rust. To ameliorate this issue, we present the BabelCode framework for…
The performance of Deep-Learning (DL) computing frameworks rely on the performance of data ingestion and checkpointing. In fact, during the training, a considerable high number of relatively small files are first loaded and pre-processed on…
Coupling physics with machine learning models has shown great potential for solving fluid dynamics problems governed by partial differential equations. However, conventional methods, such as physics-informed neural networks, often suffer…
As the number of deep learning frameworks increase and certain ones gain popularity, it spurs the discussion of what methodologies are employed by these frameworks and the reasoning behind them. The goal of this survey is to study how…
Because the choice and tuning of the optimizer affects the speed, and ultimately the performance of deep learning, there is significant past and recent research in this area. Yet, perhaps surprisingly, there is no generally agreed-upon…
Machine learning libraries such as TensorFlow and PyTorch simplify model implementation. However, researchers are still required to perform a non-trivial amount of manual tasks such as GPU allocation, training status tracking, and…
This paper evaluates the use of metamorphic relations to enhance the robustness and real-world performance of machine learning models. We propose a Metamorphic Retraining Framework, which applies metamorphic relations to data and utilizes…
Deep neural networks has become the first choice for researchers working on algorithmic aspects of learning-to-rank. Unfortunately, it is not trivial to find the optimal setting of hyper-parameters that achieves the best ranking…
PyTorch Adapt is a library for domain adaptation, a type of machine learning algorithm that re-purposes existing models to work in new domains. It is a fully-featured toolkit, allowing users to create a complete train/test pipeline in a few…
TF.Learn is a high-level Python module for distributed machine learning inside TensorFlow. It provides an easy-to-use Scikit-learn style interface to simplify the process of creating, configuring, training, evaluating, and experimenting a…