New methods improve integration of external LMs with AED models.
problem Improving performance of AED models by integrating external LMs.
method Comparing and proposing novel methods to estimate implicit LM from AED models.
result Proposed methods outperform previous approaches.
Improved neural transducer model outperforms attention model on longer sequences.
problem Improving performance of neural transducer models.
method Comparison of training criteria (marginalization vs. maximum approximation), model generalization, and output label topology.
result Final transducer model outperforms attention model by over 6% relative WER on Switchboard 300h.
Improved speech recognition model with better performance.
problem Speech recognition accuracy on Librispeech.
method Integrates an external language model with an internal LM correction.
result Over 14% relative improvement in performance.
Conditional random fields (CRFs) have been shown to be one of the most successful approaches to sequence labeling. Various linear-chain neural CRFs (NCRFs) are developed to implement the non-linear node potentials in CRFs, but still keeping the linear-chain hidden structure. In this paper, we propose NCRF transducers, …
A new method calculates optimal decisions from classifier outputs, improving predictions in drug discovery.
problem Finding optimal decisions from classifier outputs in fields like medicine.
method Develops a transducer that calculates probabilities from classifier outputs, enabling expected-utility maximization.
result Improves prediction accuracy in drug discovery problems, sometimes close to theoretical maximum.
Study improves electricity price forecasting accuracy using a hybrid model.
problem Accurate short-term electricity price forecasting is challenging due to social and natural factors.
method Hybrid model combining GARMA, G-GARCH, Wavelet, LLWNN, and optimization algorithms.
result The hybrid model outperforms other models in Nord Pool Electricity markets.
The hybrid Monte Carlo (HMC) algorithm is used for Bayesian analysis of the generalized autoregressive conditional heteroscedasticity (GARCH) model. The HMC algorithm is one of Markov chain Monte Carlo (MCMC) algorithms and it updates all parameters at once. We demonstrate that how the HMC reproduces the GARCH paramete…
Framework for differentiating WFSTs for structured loss functions.
problem Training dynamic structured loss functions in neural networks.
method Automatic differentiation with WFSTs, combining pruning and back-off.
result Demonstrated learning over WFST latent phrase decomposition.
This review compares various deep generative models.
problem Training deep neural networks to model data distributions.
method Comprehensive comparison of VAEs, GANs, flows, energy models, and autoregressives.
result Trade-offs and interrelationships among different models.
New method selects recent similar periods for better electricity price forecasting.
problem Improving accuracy in forecasting electricity prices.
method Change-point detection (NOT method) to select calibration periods; estimating autoregressive models only for selected data.
result Significant improvement in forecasting accuracy compared to existing methods.
Many applications in different domains produce large amount of time series data. Making accurate forecasting is critical for many decision makers. Various time series forecasting methods exist which use linear and nonlinear models separately or combination of both. Studies show that combining of linear and nonlinear mo…
PARNN improves ARNN with ARIMA feedback for accurate long-range forecasting.
problem Accurate long-range forecasting of complex time series data.
method Improves ARNN using ARIMA feedback, providing uncertainty quantification.
result PARNN outperforms state-of-the-art forecasters across various horizons.
We present a simple hybrid dynamical model as a tool to investigate behavioral strategies based on trend following. The multiplicative symbolic dynamics are generated using a lognormal diffusion model for the at-the-money implied volatility term structure. Thus, are model exploits information from derivative markets to…
Time Series forecasting (univariate and multivariate) is a problem of high complexity due the different patterns that have to be detected in the input, ranging from high to low frequencies ones. In this paper we propose a new model for timeseries prediction that utilizes convolutional layers for feature extraction, a r…
Paper proposes a hybrid model for financial time series prediction using sentiment analysis.
problem Challenges in forecasting in non-stationary, complex environments with heterogeneous data.
method Hybrid model combining GANs with NLP-based sentiment analysis.
result Hybrid model enhances robustness in non-stationary environments.
Having a sequence-to-sequence model which can operate in an online fashion is important for streaming applications such as Voice Search. Neural transducer is a streaming sequence-to-sequence model, but has shown a significant degradation in performance compared to non-streaming models such as Listen, Attend and Spell (…
A hybrid model combines machine learning with a land surface model to improve soil moisture predictions.
problem Improving soil moisture predictions in climatological situations.
method Noah land-surface model integrated with Gaussian Processes, using autoregressive model for out-of-sample results.
result 3-fold reduction in RMSE using one-year leave-one-out cross-validation.
Study compares ARIMA, ETS, NNAR and hybrids for COVID-19 hospitalizations.
problem Forecasting the second wave of COVID-19 hospitalizations in Italy.
method ARIMA, ETS, NNAR, and hybrid models.
result Hybrid models outperform single models in capturing epidemic patterns.
Develops STC for sequential data with missing labels.
problem Learning from partially labeled and unsegmented sequential data.
method Introduces Star Temporal Classification (STC) using a star token and GTN framework.
result Recover most of supervised baseline performance with up to 70% missing labels.
The 2006 sudden and immense downturn in U.S. House Prices sparked the 2007 global financial crisis and revived the interest about forecasting such imminent threats for economic stability. In this paper we propose a novel hybrid forecasting methodology that combines the Ensemble Empirical Mode Decomposition (EEMD) from …
Streamable model improves speech recognition performance.
problem Improving speech recognition in long-form audio.
method Chunk-based attention model for streaming speech recognition.
result Streamable model maintains competitive performance and generalizes well to long-form speech.
Estimates hybrid dynamical systems with polynomial expansions and Markovian switching.
problem Identifying hybrid dynamical systems with nonlinear autoregressive exogenous (NARX) components and Markovian switching.
method Probabilistic framework using Expectation Maximization for parameter estimation, including submodel coefficients, hidden state values, and transition probabilities. Disentangles mode classification and NARX regression tasks. Uses soft-labels and coordinate descent approach for parameter fitting.
result Demonstrated on a SMNARX problem with three nonlinear sub-models, achieving parsimonious models through l1-norm bridge estimation and hard-thresholding.
The paper investigates non-linear and heavy-tailed predictability in transition-energy financial markets.
problem Incomplete representation of dependence structure in Gaussian-linear forecasting frameworks.
method Develops a hybrid forecasting framework combining Student-t Vector Autoregressions with nonlinear recurrent residual learning architectures.
result The proposed framework consistently improves predictive accuracy relative to conventional models, especially during macro-financial stress.
Hybrid GARCH-LSTM models predict covariance matrices better than GARCH alone.
problem Predicting covariance matrices of high-dimensional asset returns.
method Combining GARCH processes with neural networks to forecast volatilities and correlations.
result The hybrid model outperforms both equally weighted portfolios and univariate GARCH models.
A new framework improves ASR alignment accuracy via optimal transport.
problem Peaky behavior and alignment inaccuracies in E2E ASR models.
method Differentiable alignment framework based on 1D optimal transport.
result Significant improvement in ASR alignment performance compared to CTC.
Parallelizes feedforward computation using nonlinear equation solving.
problem Sequential nature of feedforward computation limits parallelization.
method Frame feedforward computation as solving nonlinear equations; use Jacobi or Gauss-Seidel methods for parallel updates.
result Accelerates feedforward computation with reduced parallelizable iterations.
Paper proposes a hybrid model for VaR forecasting using SVR, GARCH, and KDE.
problem Inaccurate VaR estimates due to time-varying volatility and distributional characteristics.
method SVR-GARCH-KDE hybrid model combining nonlinear and nonparametric approaches.
result The SVR-GARCH-KDE hybrid outperforms benchmark models in VaR forecasting, especially for longer horizons.
A fixed point theorem is proved for inverse transducers, leading to an automata-theoretic proof of the fixed point subgroup of an endomorphism of a finitely generated virtually free group being finitely generated. If the endomorphism is uniformly continuous for the hyperbolic metric, it is proved that the set of regula…
Amortized variational inference (AVI) replaces instance-specific local inference with a global inference network. While AVI has enabled efficient training of deep generative models such as variational autoencoders (VAE), recent empirical work suggests that inference networks can produce suboptimal variational parameter…
Paper proposes Multi-Transformer for more accurate stock volatility forecasts.
problem Accurate equity risk models needed for effective risk management.
method Introduces Multi-Transformer neural network architecture, adapted from Transformer models.
result Empirical results show Multi-Transformer leads to more accurate risk measures.
Autoregressive models are among the best performing neural density estimators. We describe an approach for increasing the flexibility of an autoregressive model, based on modelling the random numbers that the model uses internally when generating data. By constructing a stack of autoregressive models, each modelling th…
This work proposes an efficient autoregressive model for text generation.
problem The challenge of generating high-quality text with autoregressive models.
method Introduces a cascaded decoding approach using Markov transformers to achieve sub-linear parallel time generation.
result Shows competitive accuracy/speed tradeoff compared to existing methods on five machine translation datasets.
Autoregressive sequence models achieve state-of-the-art performance in domains like machine translation. However, due to the autoregressive factorization nature, these models suffer from heavy latency during inference. Recently, non-autoregressive sequence models were proposed to reduce the inference time. However, the…
Bayesian method for multivariate autoregressive models with exogenous inputs.
problem Estimating uncertainties in autoregressive models with exogenous inputs.
method Recursive Bayesian estimation via message passing in a factor graph.
result Produces full posterior distributions for autoregressive coefficients and noise precision.
We stabilize the activations of Recurrent Neural Networks (RNNs) by penalizing the squared distance between successive hidden states' norms. This penalty term is an effective regularizer for RNNs including LSTMs and IRNNs, improving performance on character-level language modeling and phoneme recognition, and outperfor…
Autoregressive state transitions, where predictions are conditioned on past predictions, are the predominant choice for both deterministic and stochastic sequential models. However, autoregressive feedback exposes the evolution of the hidden state trajectory to potential biases from well-known train-test discrepancies.…
Alternative sampling method for autoregressive models using Langevin dynamics.
problem Efficiently sampling from autoregressive models.
method Initialize sequences with white noise and follow Langevin dynamics on global log-likelihood.
result Parallelizes and generalizes sampling process for autoregressive models.
Conformal Prediction Regions match Imprecise Highest Density Regions under consonance.
problem Matching conformal prediction regions with highest density regions.
method Using consonance and the Imprecise Probability theory of clouds.
result Imprecise Highest Density Regions are equivalent to Conformal Prediction Regions under consonance.
Paper proposes AXE loss for non-autoregressive machine translation, improving performance.
problem Challenges in training non-autoregressive models due to lack of autoregressive factors and cross entropy loss penalties.
method Proposes aligned cross entropy (AXE) loss function using a differentiable dynamic program for better word order alignment.
result AXE-based training improves performance on major WMT benchmarks and sets a new state of the art for non-autoregressive models.
Hybrid model combines deep learning and agent-based methods for synthetic LOB generation.
problem Generating realistic financial time series data for model training.
method Combining TABL model with Chiarella model for intraday trading activity simulation.
result Hybrid model generates realistic price dynamics but fails to accurately recreate market microstructure.
SMART training improves mask-predict translations.
problem Closing the performance gap between semi-autoregressive and autoregressive models.
method SMART training method for conditional masked language models.
result SMART-trained models produce higher-quality translations.
Linear attention in Transformers can be interpreted as dynamic VAR models.
problem Misalignment between Transformers and autoregressive forecasting objectives.
method Interpreting linear attention as VAR, rearranging MLP, attention, and flow.
result SAMoVAR improves performance, interpretability, and efficiency.
Paper proposes a self-supervised method to denoise autoregressive signals with heavy-tailed noise.
problem Denoising autoregressive signals corrupted by heavy-tailed noise.
method Self-supervised learning approach without requiring full noise distribution knowledge.
result Strong denoising performance compared to baseline methods, especially for impulsive noise.
Parallelizes autoregressive generation using VSSM.
problem Autoregressive models' inability to parallelize generation.
method Variational SSM (VSSM) with parallelizable sampling and decoding.
result Parallel generation possible with VSSM.
We develop methods to estimate lag and parameters for multiple stable autoregressive processes.
problem Estimating lag and parameters for multiple stable autoregressive processes with unknown lag.
method Use convex programming to simultaneously select lag and estimate parameters across multiple processes.
result The estimated process is stable, and forecasting errors can outperform known rates.
Efficiently combines autoregressive and set-based models for joint distributions.
problem Joint distributions over multiple predictions from set-based models.
method Causal autoregressive buffer that caches context and captures dependencies.
result Up to 20x faster joint sampling and density evaluation, up to 7x lower memory usage.
New method for identifying autoregressive systems on manifolds.
problem Identifying autoregressive systems on Stiefel and Grassmann manifolds.
method Defining parameters as orthogonal group elements, averaging over observations, conjugate gradient descent on manifolds.
result System parameters can be estimated efficiently using the proposed algorithm.
A new clustering method for vector time series using autoregressive dynamics.
problem Clustering of vector time series based on their dynamics is challenging.
method System identification approach using mixture autoregressive models.
result Developed a computationally manageable algorithm k-LMVAR for clustering vector time series.