The paper proposes autoregressive models for better offline RL.
problem Offline RL policy evaluation and optimization challenges.
method Autoregressive dynamics models for sequential state and reward prediction.
result Autoregressive models outperform standard methods in log-likelihood and RL tasks.
ARPs improve exploration and sample efficiency in continuous control tasks.
problem Limited exploration in continuous control tasks leading to low sample efficiency.
method Introduce autoregressive policies (ARPs) with temporally coherent standard normal distributions.
result ARPs enhance exploration and sample efficiency in both simulated and real-world domains.
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.
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.
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.
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.
This paper provides theoretical foundations for using quantized actions in behavior cloning.
problem Applying autoregressive models to continuous control requires discretizing actions through quantization, which is poorly understood.
method The paper analyzes quantization error propagation and statistical sample complexity, and proposes model-based augmentation.
result Behavior cloning with quantized actions achieves optimal sample complexity, matching existing lower bounds.
In recent years, deep reinforcement learning has been shown to be adept at solving sequential decision processes with high-dimensional state spaces such as in the Atari games. Many reinforcement learning problems, however, involve high-dimensional discrete action spaces as well as high-dimensional state spaces. This pa…
Paper uses non-linear dimension reduction for better economic forecasting.
problem Analyzing economic effects of shocks in large datasets.
method Non-linear dimension reduction in factor-augmented vector autoregressions.
result Non-linear dimension reduction techniques improve forecasting, especially in volatile data.
SymCircuit learns PC structure via entropy-regularized RL, improving inference efficiency and accuracy.
problem Greedy algorithms in PC structure learning lead to suboptimal solutions.
method Entropy-regularized reinforcement learning to train a learned generative policy for PC structure inference.
result SymCircuit learns the optimal policy as a tempered Bayesian posterior, improving inference efficiency and accuracy.
Study shows oil prices but not COVID-19 cases affect US economic policy uncertainty.
problem Effect of COVID-19 and crude oil prices on US economic policy uncertainty.
method Used ARDL model with daily data from January 21-March 13, 2020.
result Crude oil price dynamics increase US economic policy uncertainty, while COVID-19 cases have mixed effects.
This paper proposes a parsimoniously time varying parameter vector autoregressive model (with exogenous variables, VARX) and studies the properties of the Lasso and adaptive Lasso as estimators of this model. The parameters of the model are assumed to follow parsimonious random walks, where parsimony stems from the ass…
We propose a general framework for solving statistical mechanics of systems with finite size. The approach extends the celebrated variational mean-field approaches using autoregressive neural networks, which support direct sampling and exact calculation of normalized probability of configurations. It computes variation…
This paper shows ARMs and EBMs are equivalent, revealing ARM lookahead capabilities.
problem Understanding the lookahead capabilities of next-token prediction models.
method Unified view of ARMs and EBMs, establishing a bijection and deriving equivalence.
result ARMs and EBMs are equivalent, revealing ARM lookahead capabilities.
Estimators computed from adaptively collected data do not behave like their non-adaptive brethren. Rather, the sequential dependence of the collection policy can lead to severe distributional biases that persist even in the infinite data limit. We develop a general method -- W-decorrelation -- for transformi…
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 …
Study analyzes climate impact on agricultural prices, offering insurance solutions.
problem Financial risk from climate-induced agricultural price volatility.
method Historical and future climate projections, EGARCH and SARIMAX models, Black-Scholes framework.
result Improved agricultural risk modeling and insurance mechanisms.
Behavior cloning can achieve horizon-independent sample complexity in offline imitation learning.
problem Sample complexity in imitation learning increases with problem horizon.
method New analysis of behavior cloning with logarithmic loss.
result Behavior cloning can achieve linear dependence on horizon in offline IL under dense rewards.
New framework for dynamic causal graph modeling and effect estimation.
problem Dynamic changes in causal relationships over time.
method Score-based causal discovery with autoregressive model structure.
result Dynamic causal graph with time-varying causal relations.
Behavior cloning training instabilities amplified by SGD noise over long horizons.
problem Training instabilities in behavior cloning with deep neural networks.
method Empirical dissection of minibatch SGD updates and their effects on long-horizon rewards.
result Exponential moving average (EMA) of iterates effectively mitigates gradient variance amplification (GVA).
Automatically finds effective security strategies through reinforcement learning and self-play.
problem Finding effective security strategies for intrusion prevention.
method Modeling interaction as a Markov game, evolving attack and defense strategies through reinforcement learning and self-play.
result Effective security strategies emerge from self-play, reflecting common-sense knowledge.
Transformer learns long-term dependencies from real-world data.
problem Sample inefficiency in deep reinforcement learning.
method Transformer architecture applied to autoregressive real-world episodes.
result Transformer-based world model generates meaningful experience.
A new approach to distill unnormalized EBM for energy-based seq2seq models.
problem Training unnormalized EBM for energy-based seq2seq models is challenging.
method Relating the problem to distributional RL, proposing a general distillation approach.
result General approach applicable to any sequential EBM, illustrated on GAM experiments.
Paper combines latent state space with CRF for improved autoregressive text generation.
problem Autoregressive models expose hidden state trajectory to biases.
method Combines latent state space model with CRF observation model.
result Improved performance on unconditional sentence generation compared to RNN and GAN baselines.
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…
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.
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.
We empirically test the effects of unanticipated fiscal policy shocks on the growth rate and the cyclical component of real private output and reveal different types of asymmetries in fiscal policy implementation. The data used are quarterly U.S. observati ons over the period 1967:1 to 2011:4. In doing so, we use both …
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.
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.
GAMs combine autoregressive and log-linear components for data-efficient sequence learning.
problem Poor performance of standard autoregressive models under small-data conditions.
method Introduce Global Autoregressive Models (GAMs) combining autoregressive and log-linear components, trained in two steps.
result GAMs show a strong perplexity reduction over standard models in language modelling.
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.
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.
Enhances FAVAR models with autoencoder for better economic forecasting and interpretability.
problem Limitations of linear FAVAR models in forecasting and structural analysis.
method Introduces Grouped Sparse autoencoder with time-varying parameters.
result The Grouped Sparse autoencoder produces more interpretable factors and superior forecasting performance.
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.
New method identifies cause-effect relations in multivariate time series data.
problem Identifying cause-effect relations in multivariate time series data.
method Fictitious vector autoregressive model to identify long-run relations and causality strength.
result High accuracy in identifying true cause-effect relations in simulations and climate change analysis.
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.
DLF combines autoregressive and flow-based methods for efficient and high-performance image generation.
problem Limited density estimation performance and parallelizability of flow-based and autoregressive models.
method Dynamic Linear Flow (DLF) with partially autoregressive structure.
result DLF achieves state-of-the-art performance on ImageNet 32x32 and 64x64 images.
This study evaluates prewar Japanese financial market efficiency using time-varying models.
problem Determining when prewar Japanese financial market lost its price formation function.
method Time-varying parameter model, generalized least squares-based time-varying vector autoregressive model.
result The prewar Japanese financial market lost its price formation function in 1932.
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…
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
Compact autoregressive network reduces parameter count and improves learning efficiency.
problem High computational cost and low learning efficiency in autoregressive networks with high-dimensional inputs and outputs.
method Rearranged weight matrices into a tensor form and used Tucker decomposition to represent low-rank structures.
result The proposed Tucker AutoRegressive (TAR) net requires fewer samples for model training and improves learning efficiency.
Normalizing flows and autoregressive models have been successfully combined to produce state-of-the-art results in density estimation, via Masked Autoregressive Flows (MAF), and to accelerate state-of-the-art WaveNet-based speech synthesis to 20x faster than real-time, via Inverse Autoregressive Flows (IAF). We unify a…