arXiv research

MASnet enhances speech on mobile devices with low latency.

Exchanges implement intentional trade delays to limit the harmful impact of low-latency trading. Do such "speed bumps" curb investment in fast trading technology? Data is scarce since trading technologies are proprietary. We build an experimental trading platform where participants face speed bumps and can invest in fa…

Study validates low latency's impact on trading profits.

CoinTossX is a low-latency, open-source matching engine for financial trading.

Paper presents FPGA implementation for efficient recurrent neural networks.

We develop a supervised machine learning model that detects anomalies in systems in real time. Our model processes unbounded streams of data into time series which then form the basis of a low-latency anomaly detection model. Moreover, we extend our preliminary goal of just anomaly detection to simultaneous anomaly pre…

Select-DC reduces GFLOPS for uncertainty estimation in neural networks.

PHAZE framework uses zkML and hashing for fast, verifiable LHC trigger decisions.

Research optimizes C++ patterns for HFT, reducing latency and improving profitability.

Exchanges acquire excess processing capacity to accommodate trading activity surges associated with zero-sum high-frequency trader (HFT) "duels." The idle capacity's opportunity cost is an externality of low-latency trading. We build a model of decentralized exchanges (DEX) with flexible capacity. On DEX, HFTs acquire …

FlashIV solves Black-Scholes implied volatility efficiently and accurately.

This paper tackles URLLC in 6G networks with deep learning.

In this paper, we study how to solve resource allocation problems in ultra-reliable and low-latency communications by unsupervised deep learning, which often yield functional optimization problems with quality-of-service (QoS) constraints. We take a joint power and bandwidth allocation problem as an example, which mini…

The usability and practicality of any machine learning (ML) applications are largely influenced by two critical but hard-to-attain factors: low latency and low cost. Unfortunately, achieving low latency and low cost is very challenging when ML depends on real-world data that are highly distributed and rapidly growing (…

New video compression method outperforms traditional approaches.

Automated tool reduces FPGA inference latency to 5 μs for deep neural networks.

Paper predicts interference for better LA in URLLC.

Kolmogorov-Arnold Networks enable ultrafast online learning with fixed-point quantization.

PolyLUT uses polynomials to reduce FPGA latency.

This concept paper highlights a recently opened opportunity for large scale analytical algorithms to be trained directly on edge devices. Such approach is a response to the arising need of processing data generated by natural person (a human being), also known as personal data. Spiking Neural networks are the core meth…

We present a new algorithm for video coding, learned end-to-end for the low-latency mode. In this setting, our approach outperforms all existing video codecs across nearly the entire bitrate range. To our knowledge, this is the first ML-based method to do so. We evaluate our approach on standard video compression test …

GOBO compresses 99.9% of BERT model parameters to 3 bits, improving inference efficiency.

Power-SMC reduces inference latency for training-free LLM reasoning.

In this paper, a novel joint transmit power and resource allocation approach for enabling ultra-reliable low-latency communication (URLLC) in vehicular networks is proposed. The objective is to minimize the network-wide power consumption of vehicular users (VUEs) while ensuring high reliability in terms of probabilisti…

In this paper, we present iPrescribe, a scalable low-latency architecture for recommending 'next-best-offers' in an online setting. The paper presents the design of iPrescribe and compares its performance for implementations using different real-time streaming technology stacks. iPrescribe uses an ensemble of deep lear…

GPU-accelerates multiuser detection for 5G URLLC systems.

We propose an efficient distributed online learning protocol for low-latency real-time services. It extends a previously presented protocol to kernelized online learners that represent their models by a support vector expansion. While such learners often achieve higher predictive performance than their linear counterpa…

The possibility of latency arbitrage in financial markets has led to the deployment of high-speed communication links between distant financial centers. These links are noisy and so there is a need for coding. In this paper, we develop a gametheoretic model of trading behavior where two traders compete to capture laten…

DCT-SNN uses DCT to reduce inference latency in SNNs.

In this paper, a novel experienced deep reinforcement learning (deep-RL) framework is proposed to provide model-free resource allocation for ultra reliable low latency communication (URLLC). The proposed, experienced deep-RL framework can guarantee high end-to-end reliability and low end-to-end latency, under explicit …

A new method reduces inference cost for FwFM by allowing it to scale with item fields only.

With the rapid emergence of a spectrum of high-end mobile devices, many applications that required desktop-level computation capability formerly can now run on these devices without any problem. However, without a careful optimization, executing Deep Neural Networks (a key building block of the real-time video stream p…

Coherent Multiplex analyzes real-time wavelet coherence among multiple signals.

Learning the optimized solution as a function of environmental parameters is effective in solving numerical optimization in real time for time-sensitive applications. Existing works of learning to optimize train deep neural networks (DNN) with labels, and the learnt solution are inaccurate, which cannot be employed to …

Machine Learning models are often composed of pipelines of transformations. While this design allows to efficiently execute single model components at training time, prediction serving has different requirements such as low latency, high throughput and graceful performance degradation under heavy load. Current predicti…

Scalable model for slate recommendation learns reward probabilities.

Multilingual end-to-end (E2E) models have shown great promise in expansion of automatic speech recognition (ASR) coverage of the world's languages. They have shown improvement over monolingual systems, and have simplified training and serving by eliminating language-specific acoustic, pronunciation, and language models…

We study the robustness of image classifiers to temporal perturbations derived from videos. As part of this study, we construct two datasets, ImageNet-Vid-Robust and YTBB-Robust , containing a total 57,897 images grouped into 3,139 sets of perceptually similar images. Our datasets were derived from ImageNet-Vid and You…

The problem of identifying voice commands has always been a challenge due to the presence of noise and variability in speed, pitch, etc. We will compare the efficacies of several neural network architectures for the speech recognition problem. In particular, we will build a model to determine whether a one second audio…

In this letter, an age of information (AoI)-aware transmission power and resource block (RB) allocation technique for vehicular communication networks is proposed. Due to the highly dynamic nature of vehicular networks, gaining a prior knowledge about the network dynamics, i.e., wireless channels and interference, in o…

When applying machine learning to sensitive data, one has to find a balance between accuracy, information security, and computational-complexity. Recent studies combined Homomorphic Encryption with neural networks to make inferences while protecting against information leakage. However, these methods are limited by the…

In this work, we train fully convolutional networks to detect anger in speech. Since training these deep architectures requires large amounts of data and the size of emotion datasets is relatively small, we use transfer learning. However, unlike previous approaches that use speech or emotion-based tasks for the source …

We seek to achieve the Holy Grail of Bayesian inference for gravitational-wave astronomy: using deep-learning techniques to instantly produce the posterior $p(θ|D)$ for the source parameters $θ$, given the detector data $D$. To do so, we train a deep neural network to take as input a signal + noise data set (drawn from…

GSANet improves semantic segmentation accuracy with selective and global attention.

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…

Index structures are important for efficient data access, which have been widely used to improve the performance in many in-memory systems. Due to high in-memory overheads, traditional index structures become difficult to process the explosive growth of data, let alone providing low latency and high throughput performa…

Bayesian neural networks (BNN) can estimate the uncertainty in predictions, as opposed to non-Bayesian neural networks (NNs). However, BNNs have been far less widely used than non-Bayesian NNs in practice since they need iterative NN executions to predict a result for one data, and it gives rise to prohibitive computat…

TinyML models detect RF and cyber threats in spacecraft with low latency.