Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,695 papers · 148 categories

Trend · papers per month

119238357476 · Jun 202019922001200920172026
48 results for flow-based estimator

Flow-based models use ODEs to generate complex data distributions.

problem Generating high-dimensional data with complex probability distributions.
method Flow-based models use invertible mappings governed by ODEs to capture these distributions.
result Flow-based models provide exact likelihood estimation and efficient sampling.

Proposes a new method for high-dimensional density estimation.

problem Estimating high-dimensional probability density functions efficiently.
method Tensorizing flow method combining tensor-train and flow-based generative modeling.
result Efficiently constructs an approximate density in tensor-train form and trains a flow model to match empirical distribution.

Improved flow-based models capture dependencies better with multi-scale autoregressive priors.

problem Limited expressiveness of flow-based models for long-range data dependencies.
method Introducing channel-wise dependencies through multi-scale autoregressive priors (mAR) in split coupling flow layers (mAR-SCF).
result Achieves state-of-the-art density estimation results on MNIST, CIFAR-10, and ImageNet.

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…

2019-05-08abs ↗pdf ↗

A normalizing flow models a complex probability density as an invertible transformation of a simple density. The invertibility means that we can evaluate densities and generate samples from a flow. In practice, autoregressive flow-based models are slow to invert, making either density estimation or sample generation sl…

2019-06-05abs ↗pdf ↗

JAPAN uses flow-based models to create adaptive prediction areas with better coverage guarantees.

problem Inadequate prediction areas from existing conformal prediction methods, especially for multimodal distributions.
method JAPAN employs density-based conformity scores using flow-based models to construct context-adaptive prediction areas.
result JAPAN produces more accurate and context-adaptive prediction areas compared to existing methods.

A time schedule simplifies learning in flow-based models for high-dimensional data.

problem Disappearance of relative probability phase in high-dimensional Gaussian mixture sampling.
method Introduces a time dilation schedule to characterize phases of learning.
result Autoencoder learns to simplify by focusing on relevant parameters for each phase.

Flow-based generative models parameterize probability distributions through an invertible transformation and can be trained by maximum likelihood. Invertible residual networks provide a flexible family of transformations where only Lipschitz conditions rather than strict architectural constraints are needed for enforci…

2019-06-06abs ↗pdf ↗

ContextFlow++ improves generative models by conditioning on mixed-variable contexts.

problem Lack of effective methods for context conditioning in flow-based generative models.
method Proposes ContextFlow++ with additive conditioning and mixed-variable architecture.
result ContextFlow++ achieves higher performance metrics and faster training.

Flow-based generative models, conceptually attractive due to tractability of both the exact log-likelihood computation and latent-variable inference, and efficiency of both training and sampling, has led to a number of impressive empirical successes and spawned many advanced variants and theoretical investigations. Des…

2019-02-12abs ↗pdf ↗

This work addresses identifiability in sequential data with switching dynamics, introducing a new estimator.

problem Identifiability of sequential data with regime-switching dynamics under flexible assumptions.
method Introduces ΩΩSDS, a flow-based estimator for exact likelihood optimization.
result Demonstrates improved disentanglement and more accurate forecasting compared to VAE-based estimators.

In this paper, we focus on a prediction-based novelty estimation strategy upon the deep reinforcement learning (DRL) framework, and present a flow-based intrinsic curiosity module (FICM) to exploit the prediction errors from optical flow estimation as exploration bonuses. We propose the concept of leveraging motion fea…

2019-05-24abs ↗pdf ↗

A new flow-based Bayesian filter tackles high-dimensional nonlinear stochastic systems.

problem Bayesian filtering for high-dimensional nonlinear systems is challenging due to non-Gaussian distributions and computational limitations.
method Integrates normalizing flows to construct a latent linear state-space model with efficient density estimation and sampling.
result Demonstrates superior accuracy and efficiency in numerical experiments.

DFMs enable flow-based models for multimodal discrete and continuous data.

problem Combining discrete and continuous data for generative models.
method Discrete Flow Models (DFMs) using Continuous Time Markov Chains.
result DFMs achieve state-of-the-art co-design performance for protein structure and sequence generation.

FCI method uses flow-based techniques to improve prediction confidence.

problem Limited applicability of exchangeable assumptions in predicting contaminated data.
method Adversarial flow to transform data into known distributions, then map to low-dimensional space.
result FCI produces effective predictive sets and accurate outlier detection.

Flow based models such as Real NVP are an extremely powerful approach to density estimation. However, existing flow based models are restricted to transforming continuous densities over a continuous input space into similarly continuous distributions over continuous latent variables. This makes them poorly suited for m…

2019-03-18abs ↗pdf ↗

Flow-based generative models leverage invertible generator functions to fit a distribution to the training data using maximum likelihood. Despite their use in several application domains, robustness of these models to adversarial attacks has hardly been explored. In this paper, we study adversarial robustness of flow-b…

2019-11-20abs ↗pdf ↗

VFG model embeds flow-based models with hierarchical structures using variational inference.

problem Flow-based models struggle with high-dimensional latent spaces and lack of tractable inference for graphical structures.
method Integrates flow-based functions through variational inference with aggregation nodes for hierarchical information integration.
result VFG models achieve improved ELBO and likelihood values on multiple datasets.

Improved NPE with conditional diffusions and summary networks.

problem Approximating complex posterior distributions efficiently and accurately.
method Conditional diffusions coupled with high-capacity summary networks.
result Conditional diffusions offer improved stability, accuracy, and faster training times.

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…

2019-01-29abs ↗pdf ↗

Flow-based models generate data with improved theoretical guarantees.

problem Theoretical analysis of flow-based generative models.
method Proximal gradient descent in Wasserstein space for JKO flow model.
result KL guarantee of data generation by JKO flow model is O(ε2)O(\varepsilon^2).

Augmented KRnet improves flow-based generative modeling by maintaining exact invertibility.

problem Maintaining exact invertibility in flow-based generative models.
method Integrates augmented dimensions into KRnet to achieve full nonlinear updates in two iterations, keeping exact invertibility.
result Augmented KRnet achieves full nonlinear updates in two iterations, maintaining exact invertibility.

AlignFlow improves FGMs by optimizing noise and data alignment.

problem Optimal Transport methods for FGMs are limited by scalability issues.
method Introduces Semi-Discrete Optimal Transport (SDOT) to enhance FGM training.
result AlignFlow scales well to large datasets and model architectures.

A new method speeds up sampling of Boltzmann distribution in high-dimensional systems.

problem High computational cost of obtaining Jacobian of flow-based models in high dimensions.
method Flow perturbation method that incorporates stochastic perturbations and reweighting.
result Achieves unbiased sampling of Boltzmann distribution with orders of magnitude speedup.

In this paper, we integrate VAEs and flow-based generative models successfully and get f-VAEs. Compared with VAEs, f-VAEs generate more vivid images, solved the blurred-image problem of VAEs. Compared with flow-based models such as Glow, f-VAE is more lightweight and converges faster, achieving the same performance und…

2018-09-16abs ↗pdf ↗

Study evaluates Tree-Ring Watermarking in rectified flow-based models, revealing detection and separability limitations.

problem Detecting and separating Tree-Ring Watermarks in rectified flow-based models.
method Extensive experimentation comparing SD 2.1 and FLUX.1-dev models with various text guidance configurations and augmentation attacks.
result Inversion limitations affect watermark recovery and statistical separation.

SCALLOP improves likelihood flow maps for efficient Boltzmann generation.

problem Efficient estimation of model likelihood in flow-based generative models.
method SCALLOP introduces a Hutchinson-free likelihood distillation objective for scalable flow-based models.
result SCALLOP achieves up to 10x inference speedup while improving performance.

Flow-based deep generative models learn data distributions by transforming a simple base distribution into a complex distribution via a set of invertible transformations. Due to the invertibility, such models can score unseen data samples by computing their exact likelihood under the learned distribution. This makes fl…

2019-06-17abs ↗pdf ↗

We introduce TzK (pronounced "task"), a conditional probability flow-based model that exploits attributes (e.g., style, class membership, or other side information) in order to learn tight conditional prior around manifolds of the target observations. The model is trained via approximated ML, and offers efficient appro…

2018-11-05abs ↗pdf ↗