Proposes deep-RL with GANs for ultra-reliable low-latency communication.
problem Resource allocation for URLLC with high reliability and low latency.
method Experienced deep-RL framework using GANs to pre-train and optimize resource allocation.
result Deep-RL framework achieves near-optimal reliability and latency under URLLC constraints.
This paper tackles URLLC in 6G networks with deep learning.
problem Stringent requirements on end-to-end delay and reliability for mission-critical applications.
method Develops a multi-level architecture combining theoretical models and real-world data, using deep transfer learning and federated learning.
result Demonstrates improved performance in URLLC for mission-critical applications.
End-to-end Text-to-speech (TTS) system can greatly improve the quality of synthesised speech. But it usually suffers form high time latency due to its auto-regressive structure. And the synthesised speech may also suffer from some error modes, e.g. repeated words, mispronunciations, and skipped words. In this paper, we…
LanguaShrink compresses prompts using psycholinguistic principles to reduce costs.
problem Reducing computational cost and efficiency in large language model inference.
method Leverages psycholinguistic principles and the Ebbinghaus memory curve to compress prompts.
result Achieves up to 26 times compression while maintaining semantic similarity.
DIET-SNN optimizes SNNs for faster, lower-energy image classification.
problem High inference latency and inefficient input encoding in SNNs.
method End-to-end backpropagation to optimize membrane leak and firing threshold.
result Achieves top-1 accuracy of 69% on ImageNet with 5 timesteps and 12x less compute energy.
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…
HOLMES improves real-time model serving for ICU patients, balancing accuracy and speed.
problem Real-time model serving is crucial in ICU due to urgency and cost.
method Online model ensemble serving framework for healthcare applications.
result HOLMES achieves high accuracy and sub-second latency for model ensemble serving.
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…
CAT is a new ASR toolkit using CRF and CTC for state-of-the-art speech recognition.
problem Improving automatic speech recognition systems.
method CRF-based discriminative training with CTC-inspired state topology.
result CAT achieves state-of-the-art results with fewer parameters and is competitive with hybrid models.
Paper proposes an online speech recognition model using Transformer.
problem Challenges in deploying Transformer-based E2E ASR for online speech recognition.
method Chunk self-attention encoder (chunk-SAE) and monotonic truncated attention (MTA) based self-attention decoder (SAD).
result Achieved 23.66% CER with 320 ms latency, significant improvement over offline models.
Automated multi-task learning algorithm that optimizes network topology.
problem Over-sharing in multi-task learning leads to over-generalization and suboptimal performance.
method Tree-structured design space with gumbel-softmax sampling for differentiable network splitting.
result End-to-end trainable algorithm that optimizes network topology for multiple objectives across tasks.
A blockchain-based federated learning system with latency analysis.
problem Latency issues in decentralized federated learning architectures.
method Introduced a consortium blockchain and a latency model to analyze the workflow.
result The latency model accurately quantifies actual delays in the system.
The rising popularity of intelligent mobile devices and the daunting computational cost of deep learning-based models call for efficient and accurate on-device inference schemes. We propose a quantization scheme that allows inference to be carried out using integer-only arithmetic, which can be implemented more efficie…
Efficient neural network for audio source separation.
problem End-to-end general purpose audio source separation.
method SuDoRMRF structure with simple one-dimensional convolutions for feature aggregation.
result SuDoRMRF achieves high quality audio source separation with minimal computational resources.
Optimizes latency and false alarm probability in change detection problems.
problem Balancing latency and false alarms in non-stationary environments.
method Develops order-optimal change detectors under specified latency and false alarm levels.
result Derives a universal lower bound on latency and develops order-optimal detectors.
Study validates low latency's impact on trading profits.
problem Determining the impact of low latency on trading profits.
method Agent-based simulation of trading strategies in a controlled environment.
result Latency inversely affects trading profits; latency rank is key.
Research examines how strategic latency manipulation impacts Ethereum's network efficiency and decentralization.
problem Impact of artificial latency on Ethereum's network efficiency and decentralization.
method Comprehensive analysis of MEV-Boost auction system and empirical validation with a pilot.
result Increased profitability for node operators and significant systemic challenges like heightened network inefficiencies and centralization risks.
The Tick library simulates and learns Hawkes processes with latency effects.
problem Correctly modeling causality in order book events with latency.
method Exponential kernels shifted by latency, derived log-likelihood expressions.
result Latency determines most decays in real data, showing decay relationships.
Research optimizes C++ patterns for HFT, reducing latency and improving profitability.
problem Optimizing latency-critical code for high-frequency trading systems.
method Creation of a Low-Latency Programming Repository, optimisation of trading strategy, implementation of Disruptor pattern.
result Significant performance improvements in speed and profitability.
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 …
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…
MASnet enhances speech on mobile devices with low latency.
problem Efficiently enhancing speech on mobile devices with low latency.
method MASnet processes linear-scale spectrograms, using ratio masks to enhance noisy frames, and operates in low-latency incremental inference mode.
result MASnet achieves efficient speech enhancement with low latency, reducing FMA/s operations.
CryptoNAS improves PI accuracy by 3.4% with 2.4x less latency.
problem Private inference on machine learning models with limited latency.
method Developed CryptoNAS, a novel NAS method for finding models that maximize accuracy within a ReLU budget.
result Improves accuracy by 3.4% and latency by 2.4x over state-of-the-art methods.
PHAZE framework uses zkML and hashing for fast, verifiable LHC trigger decisions.
problem Inefficient inference on large machine learning models for LHC trigger performance.
method Cryptographic techniques like hashing and zkML for low latency, certifiable inference.
result Achieves nanosecond-order latency for LHC triggers, enabling dynamic low-level triggers.
This paper studies optimal market making for large-tick assets in the presence of latency. We consider a random walk model for the asset price, and formulate the market maker's optimization problem using Markov Decision Processes (MDP). We characterize the value of an order and show that it plays the role of one-period…
BRP-NAS uses GCNs to predict neural network performance for more efficient NAS.
problem Inaccurate performance metrics in NAS lead to suboptimal model designs.
method Proposes BRP-NAS, a hardware-aware NAS using GCNs for accurate performance prediction.
result BRP-NAS outperforms previous methods on NAS-Bench-101 and 201, improving model sample efficiency.
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…
Automated tool reduces FPGA inference latency to 5 μs for deep neural networks.
problem Deploying ultra low-latency, low-power deep neural networks on FPGAs.
method Extending hls4ml library, using model compression techniques like pruning and quantization-aware training.
result Achieved inference latency of 5 μs with 97% resource reduction.
New method reduces model size by 75% on ResNet32 without loss in quality.
problem Large models consume too much memory and energy on low-resource devices.
method Structured multi-hashing combining weight hashing and dimensionality reductions.
result Significant reduction in model size with minimal accuracy loss.
TinyML models detect RF and cyber threats in spacecraft with low latency.
problem Detecting cyber-RF threats in autonomous spacecraft with low latency.
method Analysis of classical models (RF, LR, SVM, MLP) for latency-accuracy trade-offs.
result Logistic Regression achieves microsecond-level inference with minimal accuracy loss.
Speed bumps reduce but do not fully eliminate investment in fast trading technology.
problem Limiting low-latency trading to curb investment in fast trading technology.
method Built an experimental trading platform to test the effects of speed bumps on investment in fast trading technology.
result Asymmetric speed bumps reduce investment in speed by only 20%, and increasing the magnitude further reduces investment by 8.33%. Symmetric speed bumps have no effect on investment levels.
A new algorithm for cryo-EM data collection that balances reward and latency.
problem Optimizing data collection in cryo-EM experiments with action delays.
method Latency-aware contextual bandit framework and COAF algorithm.
result The COAF algorithm efficiently maximizes reward over time in cryo-EM experiments.
High frequency trading has led to widespread efforts to reduce information propagation delays between physically distant exchanges. Using relativistically correct millisecond-resolution tick data, we document a 3-millisecond decrease in one-way communication time between the Chicago and New York areas that has occurred…
S3NAS finds high-accuracy CNN architectures for NPUs in 3 hours.
problem Finding optimal CNN architectures for NPUs with high accuracy and low latency.
method Supernet design, Single-Path NAS, scaling, analytical latency estimation.
result 82.72% top-1 accuracy on ImageNet with 11.66 ms latency.
DCT-SNN uses DCT to reduce inference latency in SNNs.
problem High inference latency in SNNs.
method Proposes a time-based encoding scheme using DCT to reduce timesteps.
result Achieves top-1 accuracy comparable to standard deep learning while reducing inference latency.
PolyLUT uses polynomials to reduce FPGA latency.
problem Reducing latency in FPGA-based neural network inference.
method Training neural networks using multivariate polynomials as basic building blocks.
result Achieved significant latency and area improvements.
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…
This study analyzes satellite communication latency using a stochastic geometry model.
problem Latency analysis of LEO satellite relay communication systems.
method Stochastic geometry framework with spherical BPP models, suboptimal satellite relay selection strategy.
result Derives distance distributions and analytical expressions for transmission delays.
Paper analyzes how latency affects optimal order execution in markets.
problem Balancing profit from optimal order execution against execution risk.
method Stochastic optimal control problem with risk-averse trader.
result Closed-form approximations of fill probability, limit price, and latency.
Paper presents FPGA implementation for efficient recurrent neural networks.
problem Implementing recurrent neural networks on FPGAs for low latency.
method Developed hls4ml framework to implement LSTM and GRU layers.
result Demonstrated effective designs for both small and large models.
New attacks exploit neural network energy and latency, increasing costs by 10-200x.
problem Energy and latency vulnerabilities in neural networks.
method Crafted sponge examples to maximize energy and latency.
result Adversaries can increase energy consumption by 10-200x and delay decisions.
This paper proposes an EM approach to reduce inference latency in NAR sequence generation.
problem High inference latency in NAR models due to multi-modality in sequence generation.
method A unified EM framework that jointly optimizes AR and NAR models, with iterative refinement.
result The proposed approach achieves competitive performance with existing NAR models and significantly reduces inference latency.
Improves text-to-speech speed by interleaving character reading and audio synthesis.
problem Latency in text-to-speech models limits their use in time-sensitive tasks.
method Reinforcement learning to train an agent to choose the order of character reading and audio synthesis.
result The proposed method successfully balances latency and audio quality.
A blockchain replaces central counterparties with time-consuming consensus protocols to record the transfer of ownership. This settlement latency slows cross-exchange trading, exposing arbitrageurs to price risk. Off-chain settlement, instead, exposes arbitrageurs to costly default risk. We show with Bitcoin network an…
Freezing intermediate layers reduces DNN inference latency.
problem High latency in deep learning inference due to computationally expensive models.
method Introduce approximate caching at each intermediate layer to avoid running all layers for many inference requests.
result Reduces the number of effective layers by half for 91.58% of CIFAR-10 requests.
Reinforcement learning approaches have long appealed to the data management community due to their ability to learn to control dynamic behavior from raw system performance. Recent successes in combining deep neural networks with reinforcement learning have sparked significant new interest in this domain. However, pract…
NeuraLUT maps neural networks to lookup tables, reducing latency and improving expressivity.
problem Reducing latency in deep neural networks for FPGA accelerators.
method Mapping entire sub-networks to a single lookup table, introducing skip connections.
result Up to 4.3x lower latency for the same accuracy.
We resolve the fundamental problem of online decoding with general nth order ergodic Markov chain models. Specifically, we provide deterministic and randomized algorithms whose performance is close to that of the optimal offline algorithm even when latency is small. Our algorithms admit efficient implementation vi…