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.
Efficiently improves non-autoregressive sequence models for better translation performance.
problem Heavy inference latency and inconsistent output sentences in non-autoregressive models.
method Incorporates a structured inference module with an efficient CRF approximation and dynamic transition technique.
result Significantly better translation performance (BLEU score 26.80) compared to previous non-autoregressive models.
A new online learning setting for autoregressive processes with sublinear regret.
problem Sequential decision-making with temporal dependence in autoregressive processes.
method Autoregressive Bandits (ARBs) and AutoRegressive Upper Confidence Bound (AR-UCB) algorithm.
result Sublinear regret of order $\widetilde{\mathcal{O}} \left( \frac{(k+1)^{3/2}\sqrt{nT}}{(1-Γ)^2}
ight)$ for optimal policy.
EventFlow forecasts event sequences without autoregression, improving accuracy.
problem Forecasting errors in autoregressive models for event sequences.
method EventFlow uses flow matching to learn joint distributions over event times directly.
result EventFlow reduces forecast error by 20%-53% compared to baselines.
This work improves NAT translation accuracy through fine-tuning with curriculum learning.
problem Improving NAT translation accuracy while maintaining inference speed.
method Curriculum learning applied to fine-tuning of a pre-trained AT model to a NAT model.
result Significant improvement in translation accuracy (over 1 BLEU score) and speedup in inference.
A new autoregressive model learns the order of graph generation tasks.
problem Generating graphs in a meaningful order when the canonical order is not obvious.
method Introduces a variant of autoregressive models that dynamically decides the autoregressive order based on data.
result Achieves state-of-the-art results on molecular graph generation benchmarks.
Autoregressive generative models of images tend to be biased towards capturing local structure, and as a result they often produce samples which are lacking in terms of large-scale coherence. To address this, we propose two methods to learn discrete representations of images which abstract away local detail. We show th…
Modified asymmetric hidden Markov models for time series with autoregressive components.
problem Dynamic relationships between variables in time series data.
method Introducing an asymmetric autoregressive component to recent asymmetric hidden Markov models.
result The model can choose the optimal autoregressive order for better likelihood.
Standard autoregressive seq2seq models are easily trained by max-likelihood, but tend to show poor results under small-data conditions. We introduce a class of seq2seq models, GAMs (Global Autoregressive Models), which combine an autoregressive component with a log-linear component, allowing the use of global \textit{a…
ARMA nets expand receptive fields for dense prediction tasks.
problem Global information in dense prediction problems is challenging for traditional convolutional layers.
method ARMA layers with adjustable autoregressive coefficients replace traditional convolutions.
result ARMA networks improve dense prediction tasks including video prediction and semantic segmentation.
Optimized variable orderings improve autoregressive model performance.
problem Challenges in variable ordering affect autoregressive model efficiency.
method Learn graphical model structure to inform optimal variable orderings.
result Graph-informed orderings yield higher-fidelity samples.
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 makes machine learning approximations unbiased and efficient.
problem Efficient sampling of complex probability distributions.
method Uses autoregressive neural networks with cluster updates and physical symmetries.
result Shows unbiased and low-variance approximations for phase transitions.
Transformers learn a mesa-optimizer to implement in-context learning.
problem Understanding the convergence of autoregressive training to a mesa-optimizer.
method Investigated a one-layer linear causal self-attention model autoregressively trained by gradient flow.
result Proved that autoregressive training converges to a gradient descent step for an OLS problem, validating the mesa-optimizer hypothesis.
Autoregressive networks can achieve promising performance in many sequence modeling tasks with short-range dependence. However, when handling high-dimensional inputs and outputs, the huge amount of parameters in the network lead to expensive computational cost and low learning efficiency. The problem can be alleviated …
Single autoregressive model outperforms ensemble methods in offline reinforcement learning.
problem Offline reinforcement learning with limited data and model errors.
method Infer system dynamics from data and optimize policies on model rollouts, using a single autoregressive model.
result Single autoregressive model achieves better performance than ensembles on the D4RL benchmark.
Neural density estimators are flexible families of parametric models which have seen widespread use in unsupervised machine learning in recent years. Maximum-likelihood training typically dictates that these models be constrained to specify an explicit density. However, this limitation can be overcome by instead using …
The optimal predictor for a linear dynamical system (with hidden state and Gaussian noise) takes the form of an autoregressive linear filter, namely the Kalman filter. However, a fundamental problem in reinforcement learning and control theory is to make optimal predictions in an unknown dynamical system. To this end, …
This paper explores how Transformers predict next tokens in autoregressive tasks.
problem Understanding the success of Transformers in autoregressive learning.
method Trained a Transformer on a next-token prediction task, focusing on commuting orthogonal matrices.
result Trained Transformers can be seen as implementing gradient descent for a specific objective function.
BiGG model efficiently generates sparse graphs with reduced complexity.
problem Challenges in scalable deep learning for sparse graphs.
method BiGG model, an autoregressive model that leverages graph sparsity.
result Graph generation time complexity reduced from O(n2) to O((n+m)logn). Vector autoregressive models characterize a variety of time series in which linear combinations of current and past observations can be used to accurately predict future observations. For instance, each element of an observation vector could correspond to a different node in a network, and the parameters of an autoregr…
Optimal sample complexity for autoregressive chain-of-thought learning proven.
problem Determining the minimum number of samples needed for accurate autoregressive chain-of-thought learning.
method Proved upper bound on sample complexity using Daniely-Shalev-Shwartz dimension and roll-out stable parity dimension.
result The sample complexity is bounded by the local next-token class rate, with no dependence on rollout length.
Proposes a non-autoregressive Transformer for time series forecasting.
problem Autoregressive errors and spatial-temporal dependencies in time series forecasting.
method Introduces a Non-Autoregressive Transformer with a learned temporal influence map.
result Demonstrates state-of-the-art performance on time series forecasting datasets.
Efficient autoregressive entity linking with correction for faster, more accurate results.
problem High computational cost and non-parallelizable decoding in autoregressive entity linking.
method Parallelizes autoregressive linking across all mentions, uses a shallow decoder, and adds a discriminative correction term.
result 70 times faster and more accurate than previous methods, outperforming state-of-the-art approaches.
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…
Survey of graph learning methods for combinatorial optimization problems.
problem Efficient and effective analysis of graphs for combinatorial optimization problems.
method Two-stage framework: Graph representation learning followed by machine learning.
result Recent studies have shown promise in using machine learning to solve graph-based combinatorial optimization problems.
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.
New approach uses autoregressive models to explore and quantify uncertainty in decision-making.
problem Quantifying and exploring uncertainty in online decision-making.
method Reformulates uncertainty as missing future outcomes, training autoregressive models for next-outcome prediction.
result Establishes a reduction from online learning to offline next-outcome prediction, controlling Bayesian regret by sequence prediction loss.
This paper improves autoregressive model training by focusing on test metrics, not just likelihood.
problem Training autoregressive models to perform better on specific metrics like METEOR score.
method Follows the learning-to-search approach, constructing a reference policy and choosing test metric-related costs.
result The standard KL loss only learns high-probability tokens and can be improved with ranking objectives.
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.
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.
Study reveals issues with neural autoregressive models and proposes mode recovery cost.
problem Unreasonable affinity of neural autoregressive models to short and long sequences.
method Investigates modes of ground-truth, empirical, and decoding-induced distributions via mode recovery cost.
result Mode recovery cost varies depending on ground-truth distribution and impacts decoding-induced distribution.
Improved language generation with faster sampling speed.
problem Speed and coherence issues in autoregressive language models.
method Introduces Neural Flow Diffusion Models (NFDM) for discrete state spaces.
result Substantially reduces likelihood gap with autoregressive models.
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.
A new drift detection method based on autoregressive models.
problem Concept drift in real-world data leads to decreased model performance.
method Autoregressive based drift detection method (ADDM).
result ADDM outperforms state-of-the-art drift detection methods.
Diffusion models generate music sequences without autoregressive loops.
problem Generating music sequences from symbolic data using diffusion models.
method Parameterize discrete symbolic data in continuous latent space, train diffusion model, generate sequences through reverse process.
result Strong unconditional generation and post-hoc conditional infilling compared to autoregressive models.
Causal autoregressive flows enable accurate causal inference and prediction.
problem Causal discovery and interventional predictions in machine learning.
method Autoregressive normalizing flows with fixed variable orderings.
result Causal models derived from autoregressive flows are identifiable and allow for accurate interventional and counterfactual predictions.
Study evaluates stock price forecasting models during the pandemic.
problem Forecasting stock prices during the Covid-19 pandemic.
method Four models (Long-Short Term Memory, XGBoost, Autoregression, Last Value) were tested on stock prices of Facebook, Amazon, Tesla, Google, and Apple.
result Autoregression and Last Value models outperform other models due to strong correlation between prices.
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 explores variable skipping to speed up range density estimation.
problem Efficiently estimating range densities over high-dimensional data.
method Variable skipping technique to accelerate range density estimation.
result 10-100x efficiency improvements in challenging high-quantile error metrics.
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.
ARCNPs improve CNPs by autoregressively modeling dependencies.
problem CNPs struggle with modeling dependencies in predictions.
method Autoregressive deployment of factorized Gaussian CNPs.
result ARCNPs significantly outperform non-AR CNPs in various tasks.
LMConv improves autoregressive models for image generation and completion.
problem Limited generation order in autoregressive models restricts their applicability.
method Introduces LMConv, a modified 2D convolution that allows arbitrary masks to be applied to weights.
result LMConv achieves improved performance on image density estimation and coherent completions.
Normalizing flows are a powerful class of generative models for continuous random variables, showing both strong model flexibility and the potential for non-autoregressive generation. These benefits are also desired when modeling discrete random variables such as text, but directly applying normalizing flows to discret…
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.
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.