A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
HMQ improves quantization for edge devices with mixed precision.
Efficient Bitwidth Search optimizes neural network quantization for better performance.
We consider the post-training quantization problem, which discretizes the weights of pre-trained deep neural networks without re-training the model. We propose multipoint quantization, a quantization method that approximates a full-precision weight vector using a linear combination of multiple vectors of low-bit number…
Mixed-precision CA-SGD for generalized linear models on GPUs
Efficient deep neural network (DNN) inference on mobile or embedded devices typically involves quantization of the network parameters and activations. In particular, mixed precision networks achieve better performance than networks with homogeneous bitwidth for the same size constraint. Since choosing the optimal bitwi…
The study analyzes numerical stability in large language models using mixed-precision arithmetic.
Bayesian Bits unifies quantization and pruning through gradient optimization.
Improved deep learning model deployment on tiny MCUs with mixed-precision quantization.
A new quantization strategy reduces Transformer model size and inference time.
Mixed precision training (MPT) is becoming a practical technique to improve the speed and energy efficiency of training deep neural networks by leveraging the fast hardware support for IEEE half-precision floating point that is available in existing GPUs. MPT is typically used in combination with a technique called los…
A critical part of multi-person multi-camera tracking is person re-identification (re-ID) algorithm, which recognizes and retains identities of all detected unknown people throughout the video stream. Many re-ID algorithms today exemplify state of the art results, but not much work has been done to explore the deployme…
For a data holder, such as a hospital or a government entity, who has a privately held collection of personal data, in which the revealing and/or processing of the personal identifiable data is restricted and prohibited by law. Then, "how can we ensure the data holder does conceal the identity of each individual in the…
CogDL simplifies graph deep learning experiments and benchmarks.
CoDeQ simplifies joint model compression by integrating pruning and quantization.
A new method quantifies feature-map discriminativeness for efficient pruning of deep neural networks.
Synchronized stochastic gradient descent (SGD) optimizers with data parallelism are widely used in training large-scale deep neural networks. Although using larger mini-batch sizes can improve the system scalability by reducing the communication-to-computation ratio, it may hurt the generalization ability of the models…
Improves matrix multiplication throughput for asymmetric bit-width operands.
SINGD improves KFAC for memory-efficiency and stability in low-precision training.
Efficient deep learning computing requires algorithm and hardware co-design to enable specialization: we usually need to change the algorithm to reduce memory footprint and improve energy efficiency. However, the extra degree of freedom from the algorithm makes the design space much larger: it's not only about designin…
Low-precision DNNs have been extensively explored in order to reduce the size of DNN models for edge devices. Recently, the posit numerical format has shown promise for DNN data representation and compute with ultra-low precision in [5..8]-bits. However, previous studies were limited to studying posit for DNN inference…
Deep learning has led to tremendous advancements in the field of Artificial Intelligence. One caveat however is the substantial amount of compute needed to train these deep learning models. Training a benchmark dataset like ImageNet on a single machine with a modern GPU can take upto a week, distributing training on mu…
MLPerf, an emerging machine learning benchmark suite strives to cover a broad range of applications of machine learning. We present a study on its characteristics and how the MLPerf benchmarks differ from some of the previous deep learning benchmarks like DAWNBench and DeepBench. We find that application benchmarks suc…
New framework reduces cost of financial option pricing simulations on FPGAs.
Monte Carlo methods are critical to many routines in quantitative finance such as derivatives pricing, hedging and risk metrics. Unfortunately, Monte Carlo methods are very computationally expensive when it comes to running simulations in high-dimensional state spaces where they are still a method of choice in the fina…
This paper presents the first comprehensive empirical study demonstrating the efficacy of the Brain Floating Point (BFLOAT16) half-precision format for Deep Learning training across image classification, speech recognition, language modeling, generative networks and industrial recommendation systems. BFLOAT16 is attrac…
Popular deep neural networks (DNNs) spend the majority of their execution time computing convolutions. The Winograd family of algorithms can greatly reduce the number of arithmetic operations required and is present in many DNN software frameworks. However, the performance gain is at the expense of a reduction in float…
ActNN reduces neural network training memory by 2-bit quantization.
Deep neural networks have enabled progress in a wide variety of applications. Growing the size of the neural network typically results in improved accuracy. As model sizes grow, the memory and compute requirements for training these models also increases. We introduce a technique to train deep neural networks using hal…
Reduced precision computation for deep neural networks is one of the key areas addressing the widening compute gap driven by an exponential growth in model size. In recent years, deep learning training has largely migrated to 16-bit precision, with significant gains in performance and energy efficiency. However, attemp…
Paper introduces a new adaptive gradient method with gradient compression for distributed training.
This paper presents a novel end-to-end methodology for enabling the deployment of low-error deep networks on microcontrollers. To fit the memory and computational limitations of resource-constrained edge-devices, we exploit mixed low-bitwidth compression, featuring 8, 4 or 2-bit uniform quantization, and we model the i…
Post-training quantization saves resources for neural networks.
This work optimizes neural network bit-width and layer-width for efficiency.
Recent work has shown how to train Convolutional Neural Networks (CNNs) rapidly on large image datasets, then transfer the knowledge gained from these models to a variety of tasks. Following [Radford 2017], in this work, we demonstrate similar scalability and transfer for Recurrent Neural Networks (RNNs) for Natural La…
EMPIR combines low and full precision DNNs to enhance robustness against adversarial attacks.
Widely popular transformer-based NLP models such as BERT and Turing-NLG have enormous capacity trending to billions of parameters. Current execution methods demand brute-force resources such as HBM devices and high speed interconnectivity for data parallelism. In this paper, we introduce a new relay-style execution tec…