arXiv research

Presents SPEED, an algorithm for optimal policy evaluation in linear bandits with heteroscedastic noise.

LaRT models LLMs' response accuracy and CoT length to evaluate reasoning ability and speed.

HollowFlow speeds up likelihood evaluation for large-scale models.

A computational theory reduces agent evaluation errors and speeds up processes.

DistillKac generates images quickly using damped wave equations.

DistPre predicts traffic speeds efficiently for large networks.

A scalable portfolio approach speeds up Bayesian optimization for noisy functions.

New method speeds up PGD for CV robustness evaluation.

NoTMF forecasts sparse urban road movement speeds with nonstationary temporal matrix factorization.

The paper proposes a technique to speed up evolutionary algorithms by using lower-cost approximations of the objective function.

Study uses CNNs to upscale wind speed data from 100 km to 3 km, improving subgrid-scale variability.

Recurrent neural networks (RNNs) can model natural language by sequentially 'reading' input tokens and outputting a distributed representation of each token. Due to the sequential nature of RNNs, inference time is linearly dependent on the input length, and all inputs are read regardless of their importance. Efforts to…

Gaussian process regression (GPR) is a non-parametric Bayesian technique for interpolating or fitting data. The main barrier to further uptake of this powerful tool rests in the computational costs associated with the matrices which arise when dealing with large data sets. Here, we derive some simple results which we h…

We propose and evaluate new techniques for compressing and speeding up dense matrix multiplications as found in the fully connected and recurrent layers of neural networks for embedded large vocabulary continuous speech recognition (LVCSR). For compression, we introduce and study a trace norm regularization technique f…

Paper accelerates diffusion models, improving sampling speed.

In this paper, we propose a speed-up approach for subclass discriminant analysis and formulate a novel efficient multi-view solution to it. The speed-up approach is developed based on graph embedding and spectral regression approaches that involve eigendecomposition of the corresponding Laplacian matrix and regression …

Estimates neural architecture performance speedily.

A hybrid ASR system using conformer architecture improves word-error-rate and training speed.

Machine learning improves earnings forecasting accuracy and speed.

New method speeds up diffusion models without requiring complex assumptions.

Sparse perturbations improve convergence in SZO methods for faster training.

Stochastic variance-reduced gradient (SVRG) is an optimization method originally designed for tackling machine learning problems with a finite sum structure. SVRG was later shown to work for policy evaluation, a problem in reinforcement learning in which one aims to estimate the value function of a given policy. SVRG m…

Fastest video anomaly detection via teacher-student distillation.

Many reinforcement learning applications involve the use of data that is sensitive, such as medical records of patients or financial information. However, most current reinforcement learning methods can leak information contained within the (possibly sensitive) data on which they are trained. To address this problem, w…

Stochastic variational inference (SVI) employs stochastic optimization to scale up Bayesian computation to massive data. Since SVI is at its core a stochastic gradient-based algorithm, horizontal parallelism can be harnessed to allow larger scale inference. We propose a lock-free parallel implementation for SVI which a…

This paper proposes a convolutional neural network (CNN)-based method that learns traffic as images and predicts large-scale, network-wide traffic speed with a high accuracy. Spatiotemporal traffic dynamics are converted to images describing the time and space relations of traffic flow via a two-dimensional time-space …

BERTino is a lightweight Italian DistilBERT model for NLP tasks.

Predicting structured outputs can be computationally onerous due to the combinatorially large output spaces. In this paper, we focus on reducing the prediction time of a trained black-box structured classifier without losing accuracy. To do so, we train a speedup classifier that learns to mimic a black-box classifier u…

MTFL improves UA and speeds convergence in personalised DNNs on edge devices.

New simulation approaches to evaluating path-dependent options without matrix inversion issues nor Euler bias are evaluated. They employ three main contributions: Stochastic approximation replaces regression in the LSM algorithm; Explicit weak solutions to stochastic differential equations are developed and applied to …

Data application developers and data scientists spend an inordinate amount of time iterating on machine learning (ML) workflows -- by modifying the data pre-processing, model training, and post-processing steps -- via trial-and-error to achieve the desired model performance. Existing work on accelerating machine learni…

Efficient medoid-based Silhouette method speeds up clustering evaluation.

We propose a fast, model agnostic method for finding interpretable counterfactual explanations of classifier predictions by using class prototypes. We show that class prototypes, obtained using either an encoder or through class specific k-d trees, significantly speed up the the search for counterfactual instances and …

A new Metropolis-Hastings algorithm uses Gaussian Processes to speed up sampling from complex models.

Wind speed prediction improved using a novel deep ensemble learning model inspired by jet aerodynamics.

In the present paper, an aerodynamic investigation of a high-speed train is performed. In the first section of this article, a generic high-speed train against a turbulent flow is simulated, numerically. The Reynolds-Averaged Navier-Stokes (RANS) equations combined with the turbulence model are applied to solve incompr…

We propose a conditional non-autoregressive neural sequence model based on iterative refinement. The proposed model is designed based on the principles of latent variable models and denoising autoencoders, and is generally applicable to any sequence generation task. We extensively evaluate the proposed model on machine…

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…

Gaussian process is a very promising novel technology that has been applied to both the regression problem and the classification problem. While for the regression problem it yields simple exact solutions, this is not the case for the classification problem, because we encounter intractable integrals. In this paper we …

AlgoPerf competition evaluates neural network training speed-ups.

Outlier detection is a crucial part of robust evaluation for crowdsourceable assessment of Quality of Experience (QoE) and has attracted much attention in recent years. In this paper, we propose some simple and fast algorithms for outlier detection and robust QoE evaluation based on the nonconvex optimization principle…

In this paper, we compare the performances of FAISS and FENSHSES on nearest neighbor search in Hamming space--a fundamental task with ubiquitous applications in nowadays eCommerce. Comprehensive evaluations are made in terms of indexing speed, search latency and RAM consumption. This comparison is conducted towards a b…

We developed efficient methods to compute gradients for Neural SDEs, improving training speed and accuracy.

We present an approximation scheme for support vector machine models that use an RBF kernel. A second-order Maclaurin series approximation is used for exponentials of inner products between support vectors and test instances. The approximation is applicable to all kernel methods featuring sums of kernel evaluations and…

Recently, Reinforcement Learning (RL) approaches have demonstrated advanced performance in image captioning by directly optimizing the metric used for testing. However, this shaped reward introduces learning biases, which reduces the readability of generated text. In addition, the large sample space makes training unst…

Noncritical soft-faults and model deviations are a challenge for Fault Detection and Diagnosis (FDD) of resident Autonomous Underwater Vehicles (AUVs). Such systems may have a faster performance degradation due to the permanent exposure to the marine environment, and constant monitoring of component conditions is requi…

LEEP measures transferability of learned representations efficiently.

MSCT predicts post-crash traffic speed using causal inference.