TraDE uses self-attention for better density estimation of tabular and image data.
problem Improving density estimation for tabular and image data.
method Self-attention-based architecture trained with a penalized maximum likelihood objective.
result TraDE produces significantly better density estimates than existing methods.
Transformer adapts to graphs with adaptive attention and auto-regressive decoding.
problem Transformers struggle with graph data due to non-sequential nature.
method Proposes GRAT, a Transformer variant with adaptive attention and auto-regressive decoding.
result GRAT achieves state-of-the-art performance on molecule property predictions and generation tasks.
A new model tackles language generation issues by using discrete variational attention.
problem Information under-representation and posterior collapse in variational autoencoders.
method Proposes a discrete variational attention model with categorical distribution over attention mechanism.
result Enhances latent space for language generation and avoids posterior collapse.
Generative models speed up complex system simulations.
problem Accurately forecasting the dynamics of complex systems at reduced cost.
method Generative Learning of Effective Dynamics (G-LED) using auto-regressive attention and Bayesian diffusion models.
result Generative models can accurately forecast complex system dynamics at lower computational cost.
Auto-regressive models improve smoothing efficiency with exponentially tapered windows.
problem Improving time-series smoothing efficiency.
method An auto-regressive formulation for time-series smoothing.
result Auto-regressive models result in moving means with exponentially tapered windows.
Proof of Gaussian ML estimator consistency in linear auto-regressive models.
problem Consistency of Gaussian maximum likelihood estimator in linear auto-regressive models.
method Information-theoretic proof without stability assumptions.
result Nearly optimal non-asymptotic rates for parameter recovery.
CAFLOW uses auto-regressive flows to translate images efficiently.
problem Image-to-image translation tasks.
method Transforms conditioning image into latent encodings using normalizing flows, models conditional distribution with auto-regressive distributions.
result Outperforms former conditional flow designs.
Auto-regressive models learn latent states from partially observed linear dynamical systems.
problem Understanding how auto-regressive models learn latent representations from partially observed linear dynamical systems.
method Empirical risk minimization on partially observed linear dynamical systems.
result Two-layer linear auto-regressive models learn to approximate Kalman filtering, coinciding with optimal state estimates.
SpotV2Net forecasts intraday spot volatilities using graph attention networks.
problem Forecasting multivariate intraday spot volatilities accurately.
method Graph Attention Network architecture with Fourier estimates of spot and vol-of-vol volatilities.
result SpotV2Net outperforms other models in forecasting accuracy.
Auto-regressive sequence-to-sequence models with attention mechanism have achieved state-of-the-art performance in many tasks such as machine translation and speech synthesis. These models can be difficult to train. The standard approach, teacher forcing, guides a model with reference output history during training. Th…
VEST automates feature engineering for time series forecasting.
problem Challenges in time series forecasting with improved performance.
method VEST combines auto-regression with statistical summarization of recent past dynamics.
result VEST significantly improves forecasting performance.
In this paper, non-linear time series models are used to describe volatility in financial time series data. To describe volatility, two of the non-linear time series are combined into form TAR (Threshold Auto-Regressive Model) with AARCH (Asymmetric Auto-Regressive Conditional Heteroskedasticity) error term and its par…
Cactus improves auto-regressive decoding speed without sacrificing quality.
problem Accelerating auto-regressive decoding while maintaining output quality.
method Formalizes speculative sampling as constrained optimization and proposes Cactus for controlled divergence from the verifier distribution.
result Empirically validated effectiveness across various benchmarks.
Paper reduces vocabulary losslessly for language model cooperation.
problem Language models struggle to cooperate with different tokenizations.
method Established a theoretical framework for lossless vocabulary reduction.
result Efficiently converts models with different tokenizations to cooperate with maximal common vocabulary.
The paper proposes a new auto-regressive model for multivariate distributional time series.
problem Statistical analysis of multivariate time series of probability measures.
method Wasserstein space, auto-regressive model, iterated random function systems.
result Consistent estimator for auto-regressive coefficients with sparse structure.
DSARF models complex spatio-temporal data with deep switching auto-regressive factors.
problem Forecasting complex spatio-temporal data with recurring patterns.
method Deep switching auto-regressive factorization (DSARF) with stochastic variational inference.
result DSARF outperforms state-of-the-art methods in long- and short-term prediction accuracy.
VAR-GPs solve continual learning by updating posteriors sequentially.
problem Catastrophic forgetting in sequential learning tasks.
method Sparse inducing point approximations and auto-regressive variational distribution.
result VAR-GPs prevent catastrophic forgetting and outperform baselines.
We propose a new family of efficient and expressive deep generative models of graphs, called Graph Recurrent Attention Networks (GRANs). Our model generates graphs one block of nodes and associated edges at a time. The block size and sampling stride allow us to trade off sample quality for efficiency. Compared to previ…
BMBO-DARN optimizes expensive functions with varying fidelities.
problem Optimizing expensive, multi-fidelity functions efficiently.
method Batch Multi-fidelity Bayesian Optimization with Deep Auto-Regressive Networks.
result BMBO-DARN improves surrogate learning and optimization performance.
Improved text generation with constraints using discrete auto-regressive biasing.
problem Balancing fluency and constraint satisfaction in LLM outputs.
method Discrete Auto-regressive Biasing, leveraging gradients in discrete text space.
result Significantly improved constraint satisfaction with comparable fluency.
A new method estimates expectations from subtractive mixture models without sampling.
problem Estimating expectations from multimodal distributions using SMMs.
method Difference representation of SMMs to create unbiased IS estimator (ΔextEx). result Demonstrates that ΔextEx can achieve comparable estimation quality to auto-regressive sampling but is faster. Improved hyperparameter optimization using simplified Transformer blocks.
problem Discovering optimal architectures in high-dimensional search spaces with limited exploration budgets.
method Simplified Transformer block for modeling hyper-parameter dependencies, actor-critic style algorithm, ensembling.
result Outperformed most algorithms on NAS-Bench-101 and Random Search in discovering more accurate model architectures.
MDMs train to decode tokens in a random order, which affects performance; we show they can be optimized for a favorable order.
problem Performance of MDMs is affected by the random order in which tokens are decoded.
method We show that MDMs can be optimized for a favorable decoding order by equipping their continuous-time variational objective with multivariate noise schedules.
result MDMs can be decomposed into a weighted auto-regressive losses over orders, making them auto-regressive models with learnable orders.
Auto-regressive diffusion models improve capturing conditional dependence in data.
problem Vanilla diffusion models struggle to capture important, high-level relationships in real-world data.
method Developed auto-regressive diffusion models to better capture conditional dependence structures.
result AR diffusion models produce samples with a reduced gap in approximating the data conditional distribution.
A new method improves text generation quality and diversity.
problem Exposure bias in Maximum Likelihood Estimation for text generation.
method ψ-MLE, a new training scheme based on density ratio estimation.
result ψ-MLE outperforms Maximum Likelihood Estimation and other models in text generation quality and diversity.
Improves naturalness in TTS samples using quantized VAE and auto-regressive prosody.
problem Discontinuous and unnatural speech from standard VAE priors.
method Discretized latent features using vector quantization (VQ), and separately trained autoregressive (AR) prior model.
result Significantly improves naturalness in random sample generation.
New Feedback Transformer architecture improves model performance by exposing past representations to future.
problem Limitations of Transformers in fully exploiting sequential input.
method Proposes Feedback Transformer exposing all past representations to future.
result Demonstrates improved performance with smaller, shallower models.
Hybrid model combines VAR and neural network for OFI prediction.
problem Accurate prediction of Order Flow Imbalance (OFI) in high frequency trading.
method Combines Vector Auto Regression (VAR) and a simple feedforward neural network (FNN).
result Hybrid model achieves superior predictive accuracy compared to standalone models.
We introduce an auto-regressive model which captures the growing nature of realistic markets. In our model agents do not trade with other agents, they interact indirectly only through a market. Change of their wealth depends, linearly on how much they invest, and stochastically on how much they gain from the noisy mark…
Numerous empirical proofs indicate the adequacy of the time discrete auto-regressive stochastic volatility models introduced by Taylor in the description of the log-returns of financial assets. The pricing and hedging of contingent products that use these models for their underlying assets is a non-trivial exercise due…
Improved language models by incorporating statistical discriminators.
problem Distinguishing model-generated text from real text reliably.
method Energy-Based Model framework to incorporate discriminators.
result Improves language model performance in perplexity and human evaluation.
Enhanced multi-fidelity models improve digital twin accuracy and uncertainty quantification.
problem Lack of detailed application-specific data and inaccurate sensor data hinder surrogate model learning for digital twins.
method Proposes a multi-fidelity surrogate model framework integrating PCFE and GP, and deep-HPCFE with auto-regression schemes.
result Demonstrates improved accuracy and uncertainty quantification in digital twin systems.
New approach predicts tokens in context, explaining how ICL emerges.
problem Limited understanding of in-context learning emergence.
method Auto-regressive next-token prediction (AR-NTP) with prompt token-dependency and a two-level expectation.
result ICL emerges from the generalization of sequences and topics.
We propose a generic confidence-based approximation that can be plugged in and simplify the auto-regressive generation process with a proved convergence. We first assume that the priors of future samples can be generated in an independently and identically distributed (i.i.d.) manner using an efficient predictor. Given…
A new RG approach connects discrete and continuous time descriptions of Gaussian processes.
problem Discretization of continuous stochastic processes for accurate simulation or model inference.
method Renormalization Group (RG) approach for Gaussian time series generated by auto-regressive models.
result RG fixed points correspond to discretizations of linear SDEs, providing insights into process accuracy.
We present a new classification method for quasar identification in the EROS-2 and MACHO datasets based on a boosted version of Random Forest classifier. We use a set of variability features including parameters of a continuous auto regressive model. We prove that continuous auto regressive parameters are very importan…
Study error bounds and optimal schedules for Masked Diffusions with factorized approximations.
problem Analyzing trade-offs between computation and accuracy in Masked Diffusion Models.
method Provided general error bounds and identified optimal schedules based on data distribution information profiles.
result Identified optimal schedule sizes for Masked Diffusion Models.
With latent variables, stochastic recurrent models have achieved state-of-the-art performance in modeling sound-wave sequence. However, opposite results are also observed in other domains, where standard recurrent networks often outperform stochastic models. To better understand this discrepancy, we re-examine the role…
Breaks down complex nonlinear dynamics into simpler components.
problem Control of nonlinear dynamical systems remains challenging.
method Inspired by hybrid switching systems, decomposes dynamics into simpler stochastic switching linear dynamical systems.
result Extracts hierarchies of Markovian and auto-regressive locally linear controllers from nonlinear experts.
Rhino learns causal relationships from time series data with history-dependent noise.
problem Discovering causal relationships from time series data with non-linear relations, instantaneous effects, and history-dependent noise.
method Combines vector auto-regression, deep learning, and variational inference.
result Demonstrates better causal relationship discovery performance compared to baselines.
Energy-based models (EBMs), a.k.a. un-normalized models, have had recent successes in continuous spaces. However, they have not been successfully applied to model text sequences. While decreasing the energy at training samples is straightforward, mining (negative) samples where the energy should be increased is difficu…
Evidential Softmax preserves multimodality in sparse probability distributions for generative models.
problem Sparse probability distributions in deep generative models make exact marginalization computationally intractable.
method Introduce ev-softmax, a sparse normalization function that preserves multimodality and can be trained with probabilistic loss functions.
result ev-softmax outperforms existing techniques in distributional accuracy and dimensionality reduction.
One popular approach for nonstructural economic and financial forecasting is to include a large number of economic and financial variables, which has been shown to lead to significant improvements for forecasting, for example, by the dynamic factor models. A challenging issue is to determine which variables and (their)…
Consider a multi-variate time series (Xt)t=0T where Xt∈Rd which may represent spike train responses for multiple neurons in a brain, crime event data across multiple regions, and many others. An important challenge associated with these time series models is to estimate an influence network be…
New model controls memory in seq2seq tasks, revealing learning regimes.
problem Understanding memory in seq2seq tasks using neural networks.
method Introducing a stochastic switching-Ornstein-Uhlenbeck (SSOU) model to control memory and a measure of non-Markovianity.
result Two learning regimes emerge from the interplay of time scales in the SSOU process.
A method for identifying NPWARX models with arbitrary domains using probabilistic mixture models.
problem Identifying hybrid system models with discontinuous maps.
method Probabilistic mixture model with a neural network for nonlinear partitioning and Expectation Maximization for parameter estimation.
result Demonstrated on a nonlinear piece-wise problem with discontinuous maps.
In recent years, deep learning has proven to be a viable methodology for surrogate modeling and uncertainty quantification for a vast number of physical systems. However, in their traditional form, such models can require a large amount of training data. This is of particular importance for various engineering and scie…
We introduce a spatio-temporal convolutional neural network model for trajectory forecasting from visual sources. Applied in an auto-regressive way it provides an explicit probability distribution over continuations of a given initial trajectory segment. We discuss it in relation to (more complicated) existing work and…