Study investigates predictive coding models for phonemic learning.
problem Understanding how predictive coding models generalize to different languages and dataset sizes.
method Investigated Autoregressive Predictive Coding and Contrastive Predictive Coding models in phoneme discrimination tasks for two languages with varying dataset sizes.
result Contrastive Predictive Coding model converges rapidly and outperforms Autoregressive Predictive Coding on both languages.
SHVC improves image compression with fewer parameters.
problem Challenges in VAE compression, especially with bits-back coding.
method Introduces autoregressive sub-pixel convolution and autoregressive initial bits.
result Achieves state-of-the-art compression performance with fewer model parameters.
Non-autoregressive method speeds up protein folding prediction 23 times.
problem Generating protein sequences with higher order interactions.
method Discrete diffusion conditioned on 3D structure using ProteinMPNN.
result 23 times speed up in inference without performance loss.
Non-autoregressive transformer improves speech recognition speed and accuracy.
problem Reducing inference computation cost in speech recognition.
method Two non-autoregressive transformer structures (A-CMLM and A-FMLM) trained with masked tokens and iterative prediction during inference.
result Non-autoregressive transformer can match autoregressive transformer performance with 7x speedup.
mGENRE improves multilingual entity linking with autoregressive sequence prediction.
problem Multilingual Entity Linking (MEL) task of resolving language-specific mentions to a multilingual Knowledge Base.
method Autoregressive sequence-to-sequence system that cross-encodes mention strings and entity names.
result Over 50% improvement in average accuracy in zero-shot settings.
APC overcomes missing data and class imbalance in time series data.
problem Missing data and class imbalance in time series data.
method Self-supervised learning with Autoregressive Predictive Coding (APC).
result APC improves classification performance on real-world medical datasets.
While supervised learning has enabled great progress in many applications, unsupervised learning has not seen such widespread adoption, and remains an important and challenging endeavor for artificial intelligence. In this work, we propose a universal unsupervised learning approach to extract useful representations fro…
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.
Knowledge graph reasoning is a critical task in natural language processing. The task becomes more challenging on temporal knowledge graphs, where each fact is associated with a timestamp. Most existing methods focus on reasoning at past timestamps and they are not able to predict facts happening in the future. This pa…
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.
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.…
Flow-based generative models are a family of exact log-likelihood models with tractable sampling and latent-variable inference, hence conceptually attractive for modeling complex distributions. However, flow-based models are limited by density estimation performance issues as compared to state-of-the-art autoregressive…
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.
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.
We present a recurrent neural network memory that uses sparse coding to create a combinatoric encoding of sequential inputs. Using several examples, we show that the network can associate distant causes and effects in a discrete stochastic process, predict partially-observable higher-order sequences, and enable a DQN a…
This research tackles uncertainty estimation in autoregressive structured prediction tasks.
problem Ensuring safety and robustness of AI systems through accurate uncertainty estimation.
method Develops a unified probabilistic ensemble-based framework for token-level and sequence-level uncertainty estimation.
result Provides baselines for error and out-of-domain detection on translation and speech recognition datasets.
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.
MPP trains a transformer to predict multiple physical systems, improving accuracy across various tasks.
problem Training models for specific physical systems is inefficient and requires fine-tuning.
method MPP trains a shared transformer on multiple heterogeneous physical systems, projecting fields into a shared embedding space.
result A single MPP-pretrained transformer outperforms task-specific models on all pretraining sub-tasks and downstream tasks.
Autoregressive flow models can perform causal discovery and inference tasks.
problem Causal inference tasks such as causal discovery and interventional predictions.
method Using autoregressive flow models to estimate causal directions and make predictions.
result Autoregressive flows can accurately perform causal inference tasks without restrictive assumptions.
Likelihood-based generative models are the backbones of lossless compression due to the guaranteed existence of codes with lengths close to negative log likelihood. However, there is no guaranteed existence of computationally efficient codes that achieve these lengths, and coding algorithms must be hand-tailored to spe…
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.
Latent Block-Diffusion Temporal Point Processes (LBDTPP) is a semi-autoregressive framework for generating asynchronous event sequences.
problem Generating asynchronous event sequences
method Latent Block-Diffusion Temporal Point Processes
result Outperforms state-of-the-art TPP baselines in both unconditional and conditional generation tasks
We describe an optimal adversarial attack formulation against autoregressive time series forecast using Linear Quadratic Regulator (LQR). In this threat model, the environment evolves according to a dynamical system; an autoregressive model observes the current environment state and predicts its future values; an attac…
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.
Generative AI tasks analyzed for text, images, audio, video, code, and molecules.
problem What is the core question when using generative AI?
method Survey of generative model families, probabilistic framework, game-theoretic setup, post-training modifications, socially responsible considerations.
result Generative AI is a distinct machine learning task with connections to prediction, compression, and decision-making.
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.
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.
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.
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.
A new autoregressive SPO method improves decision-making for dependent data.
problem Improving decision-making for dependent data in stochastic optimization.
method An autoregressive Smart Predict-then-Optimize (SPO) method for time series data.
result Generalization bounds and uniform calibration results for the SPO loss in autoregressive models.
ARDMs are a new model class for autoregressive diffusion that generalize existing models and can compress data efficiently.
problem Efficient data compression and generation.
method Autoregressive Diffusion Models (ARDMs) that generalize existing autoregressive models and discrete diffusion models.
result ARDMs require significantly fewer steps for compression compared to discrete diffusion models.
Self-reflective VAE improves inference and generative modeling without complex components.
problem Limitations of typical VAEs in inference and generative modeling.
method Introduces self-reflective inference, a new hierarchical structure that matches variational posterior to exact posterior.
result Self-reflective inference achieves state-of-the-art performance on binarized MNIST without autoregressive layers.
Thermalizer stabilizes autoregressive models for long-term predictions in chaotic systems.
problem Long-term predictions in chaotic spatiotemporal systems are unreliable due to trajectory divergence.
method Diffusion models are used to implicitly estimate the score of an invariant measure, which stabilizes autoregressive emulators by applying denoising during inference.
result Thermalization extends the time horizon of stable predictions by an order of magnitude in chaotic systems.
Representation learning seeks to expose certain aspects of observed data in a learned representation that's amenable to downstream tasks like classification. For instance, a good representation for 2D images might be one that describes only global structure and discards information about detailed texture. In this paper…
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.
Linear autoregressive models serve as basic representations of discrete time stochastic processes. Different attempts have been made to provide non-linear versions of the basic autoregressive process, including different versions based on kernel methods. Motivated by the powerful framework of Hilbert space embeddings o…
Transformers become faster by linearizing self-attention.
problem Quadratic complexity of transformers makes them slow for long sequences.
method Expressed self-attention as a linear dot-product and used matrix product associativity to reduce complexity.
result Linear transformers are up to 4000x faster on long sequences.
A new method for separating mixed signals in space and time.
problem Nonlinear and nonstationary spatio-temporal data challenges.
method Identifiable autoregressive variational autoencoder.
result The method outperforms existing techniques in blind source separation and spatio-temporal prediction.
Efficient methods for answering complex probabilistic queries in sequential data.
problem Complex probabilistic queries in sequential data.
method Broad class of novel approximation techniques for marginalization in sequential models.
result Efficient techniques for answering long-range probabilistic queries.
The paper proposes a new model for predicting and analyzing economic variables.
problem Predicting and analyzing economic variables in developed regions.
method Time-varying parameter global vector autoregressive (TVP-GVAR) framework combined with machine learning models.
result The proposed model provides high precision out-of-sample predictions and novel insights into economic variable connectedness.
We derive generalization error bounds for stationary univariate autoregressive (AR) models. We show that imposing stationarity is enough to control the Gaussian complexity without further regularization. This lets us use structural risk minimization for model selection. We demonstrate our methods by predicting interest…
Bayesian model predicts interest rates with short-term accuracy and long-term stability.
problem Improving short- and long-term prediction of time series with temporary non-stationary behavior.
method Time-varying autoregressive model with Bayesian regularization and MCMC inference.
result Model outperforms existing methods in both short and long-term predictions.
Paper proposes LATC for multivariate time series prediction and missing data imputation.
problem Large-scale, incomplete, and corrupted multivariate time series data.
method Transforms multivariate time series into a tensor structure, models global and local trends, and uses autoregressive norm.
result Integration of global and local trends improves missing data imputation and rolling prediction.
Most machine translation systems generate text autoregressively from left to right. We, instead, use a masked language modeling objective to train a model to predict any subset of the target words, conditioned on both the input text and a partially masked target translation. This approach allows for efficient iterative…
Missing value imputation is a fundamental problem in spatiotemporal modeling, from motion tracking to the dynamics of physical systems. Deep autoregressive models suffer from error propagation which becomes catastrophic for imputing long-range sequences. In this paper, we take a non-autoregressive approach and propose …
A new framework predicts links in time-dependent networks using Bernoulli autoregression.
problem Predicting links in time-dependent networks with additional auxiliary information.
method A Bernoulli autoregressive model with regularization for link discovery.
result The model can discover new links not present in the data.
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, …
Generative model predicts financial market order flow with high accuracy.
problem Creating realistic order flow models for financial markets.
method Token-level autoregressive generative model using deep state space layers.
result Model generates high-quality order flow data with low perplexity.