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.
A hybrid ASR system using conformer architecture improves word-error-rate and training speed.
Expert augmentation improves hybrid model generalization.
Hybrid models forecast EPEC energy spot prices.
Hybrid model improves weather forecasting accuracy.
We introduce a new framework for training deep generative models for high-dimensional conditional density estimation. The Bottleneck Conditional Density Estimator (BCDE) is a variant of the conditional variational autoencoder (CVAE) that employs layer(s) of stochastic variables as the bottleneck between the input a…
Hybrid models combine interpretable and complex models for better performance and control.
Regularization is an important component of predictive model building. The hybrid bootstrap is a regularization technique that functions similarly to dropout except that features are resampled from other training points rather than replaced with zeros. We show that the hybrid bootstrap offers superior performance to dr…
A hybrid method improves Convolutional Neural Networks training.
New method sparsifies hybrid neural ODEs for better performance and stability.
Hybrid regularization avoids double descent in random feature models.
Meta learning optimizes neural network quantization for efficient inference.
Hybrid LSTM-fully convolutional networks (LSTM-FCN) for time series classification have produced state-of-the-art classification results on univariate time series. We show that replacing the LSTM with a gated recurrent unit (GRU) to create a GRU-fully convolutional network hybrid model (GRU-FCN) can offer even better p…
Synthetic images rendered by graphics engines are a promising source for training deep networks. However, it is challenging to ensure that they can help train a network to perform well on real images, because a graphics-based generation pipeline requires numerous design decisions such as the selection of 3D shapes and …
Hybrid models improve groundwater level prediction and uncertainty analysis.
In this paper we propose a hybrid architecture of actor-critic algorithms for reinforcement learning in parameterized action space, which consists of multiple parallel sub-actor networks to decompose the structured action space into simpler action spaces along with a critic network to guide the training of all sub-acto…
Transformer with self-attention has achieved great success in the area of nature language processing. Recently, there have been a few studies on transformer for end-to-end speech recognition, while its application for hybrid acoustic model is still very limited. In this paper, we revisit the transformer-based hybrid ac…
We introduce a parameter sharing scheme, in which different layers of a convolutional neural network (CNN) are defined by a learned linear combination of parameter tensors from a global bank of templates. Restricting the number of templates yields a flexible hybridization of traditional CNNs and recurrent networks. Com…
Deploying deep learning (DL) models across multiple compute devices to train large and complex models continues to grow in importance because of the demand for faster and more frequent training. Data parallelism (DP) is the most widely used parallelization strategy, but as the number of devices in data parallel trainin…
A hybrid training method reduces SNN training time and complexity.
Novel hybrid modeling combines ML and physics for real-time diagnosis.
A hybrid ML method improves ship response predictions across different sea conditions.
Quantum hybrid vision transformers improve event classification in high energy physics.
A hybrid K-NN and SVM technique improves classification accuracy.
HDP-VFL hybridizes DP for VFL, reducing privacy costs.
Hybrid RL algorithm combines offline and online data for robust and efficient policy learning.
CAT toolkit combines hybrid and E2E approaches for efficient speech recognition.
In this paper, we propose and investigate a variety of distributed deep learning strategies for automatic speech recognition (ASR) and evaluate them with a state-of-the-art Long short-term memory (LSTM) acoustic model on the 2000-hour Switchboard (SWB2000), which is one of the most widely used datasets for ASR performa…
A hybrid machine learning and process-based-modeling (PBM) approach is proposed and evaluated at a handful of AmeriFlux sites to simulate the top-layer soil moisture state. The Hybrid-PBM (HPBM) employed here uses the Noah land-surface model integrated with Gaussian Processes. It is designed to correct the model only i…
Quantum neural tangent kernels help understand variational quantum circuits in machine learning.
Hybrid approach combines user feedback and machine learning for predicting user satisfaction.
Deep Reinforcement Learning (DRL) has been applied to address a variety of cooperative multi-agent problems with either discrete action spaces or continuous action spaces. However, to the best of our knowledge, no previous work has ever succeeded in applying DRL to multi-agent problems with discrete-continuous hybrid (…
Hybrid LSTM-GNN model improves stock price prediction accuracy.
Paper proposes DCT for efficient hybrid parallel training of large recommendation models.
New methods improve integration of external LMs with AED models.
As deep neural networks continue to revolutionize various application domains, there is increasing interest in making these powerful models more understandable and interpretable, and narrowing down the causes of good and bad predictions. We focus on recurrent neural networks (RNNs), state of the art models in speech re…
VQC-MLPNet combines quantum and classical elements for scalable quantum machine learning.
There is an implicit assumption that traditional hybrid approaches for automatic speech recognition (ASR) cannot directly model graphemes and need to rely on phonetic lexicons to get competitive performance, especially on English which has poor grapheme-phoneme correspondence. In this work, we show for the first time t…
Predicting firm's failure is one of the most interesting subjects for investors and decision makers. In this paper, a bankruptcy prediction model is proposed based on Artificial Neural networks (ANN). Taking into consideration that the choice of variables to discriminate between bankrupt and non-bankrupt firms influenc…
Hybrid approach combines Markowitz's theory with reinforcement learning for optimal portfolio management.
This paper proposes a cooperative mechanism for mitigating the performance degradation due to non-independent-and-identically-distributed (non-IID) data in collaborative machine learning (ML), namely federated learning (FL), which trains an ML model using the rich data and computational resources of mobile clients with…
Hybrid model improves sequential data prediction by combining neural and time series models.
This thesis evaluates text-based vs audio-based classification of mental health interviews.
Paper proposes hybrid modeling to improve surrogate accuracy using multiple data sources.
A hybrid Convolutional VAE predicts crypto volatility surfaces, outperforming single-symbol approaches.
Interpretable machine learning has become a strong competitor for traditional black-box models. However, the possible loss of the predictive performance for gaining interpretability is often inevitable, putting practitioners in a dilemma of choosing between high accuracy (black-box models) and interpretability (interpr…
Paper proposes a hybrid loss function for graph self-supervised learning.
Research combines econometric, machine learning, and deep learning models for financial forecasting.
Hybrid model combines SV and LSTM for S&P 500 volatility forecasting.