Sustainable ai: Environmental implications, challenges and opportunities
CJ Wu, R Raghavendra, U Gupta… - Proceedings of …, 2022 - proceedings.mlsys.org
This paper explores the environmental impact of the super-linear growth trends for AI from a
holistic perspective, spanning Data, Algorithms, and System Hardware. We characterize the …
holistic perspective, spanning Data, Algorithms, and System Hardware. We characterize the …
An overview of processing-in-memory circuits for artificial intelligence and machine learning
Artificial intelligence (AI) and machine learning (ML) are revolutionizing many fields of study,
such as visual recognition, natural language processing, autonomous vehicles, and …
such as visual recognition, natural language processing, autonomous vehicles, and …
Compute trends across three eras of machine learning
Compute, data, and algorithmic advances are the three fundamental factors that drive
progress in modern Machine Learning (ML). In this paper we study trends in the most readily …
progress in modern Machine Learning (ML). In this paper we study trends in the most readily …
A survey of quantization methods for efficient neural network inference
This chapter provides approaches to the problem of quantizing the numerical values in deep
Neural Network computations, covering the advantages/disadvantages of current methods …
Neural Network computations, covering the advantages/disadvantages of current methods …
Captum: A unified and generic model interpretability library for pytorch
N Kokhlikyan, V Miglani, M Martin, E Wang… - arXiv preprint arXiv …, 2020 - arxiv.org
In this paper we introduce a novel, unified, open-source model interpretability library for
PyTorch [12]. The library contains generic implementations of a number of gradient and …
PyTorch [12]. The library contains generic implementations of a number of gradient and …
Dcn v2: Improved deep & cross network and practical lessons for web-scale learning to rank systems
Learning effective feature crosses is the key behind building recommender systems.
However, the sparse and large feature space requires exhaustive search to identify effective …
However, the sparse and large feature space requires exhaustive search to identify effective …
Direct access,{High-Performance} memory disaggregation with {DirectCXL}
New cache coherent interconnects such as CXL have recently attracted great attention
thanks to their excellent hardware heterogeneity management and resource disaggregation …
thanks to their excellent hardware heterogeneity management and resource disaggregation …
Lamp: When large language models meet personalization
This paper highlights the importance of personalization in large language models and
introduces the LaMP benchmark--a novel benchmark for training and evaluating language …
introduces the LaMP benchmark--a novel benchmark for training and evaluating language …
Learning-rate-free learning by d-adaptation
A Defazio, K Mishchenko - International Conference on …, 2023 - proceedings.mlr.press
The speed of gradient descent for convex Lipschitz functions is highly dependent on the
choice of learning rate. Setting the learning rate to achieve the optimal convergence rate …
choice of learning rate. Setting the learning rate to achieve the optimal convergence rate …
Mlperf inference benchmark
Machine-learning (ML) hardware and software system demand is burgeoning. Driven by ML
applications, the number of different ML inference systems has exploded. Over 100 …
applications, the number of different ML inference systems has exploded. Over 100 …