Deep conditional transformation models unify interpretable and complex predictors.
problem Challenging to learn conditional CDFs in high-dimensional settings.
method Unified deep learning framework for interpretable and complex predictors.
result Efficacy demonstrated through numerical experiments and applications.
Transforms ensemble predictions to maintain interpretability.
problem Loss of interpretability in deep ensembles.
method Proposes transformation ensembles that aggregate predictions while preserving interpretability.
result Transformation ensembles yield better predictions than individual models and maintain interpretability.
Deep learning model estimates uncertainty in complex regression tasks.
problem Uncertainty quantification in probabilistic regression predictions.
method Combines statistical and deep learning transformation models using gradient descent.
result State-of-the-art performance on small datasets and complex image data.
Improves CRRR for better mobility analysis with DCTM.
problem Unclear interpretation of RRRX parameters.
method Uses DCTM for conditional ranks, cross-fitting, and asymptotic theory.
result Clearer interpretation and improved accuracy in mobility analysis.
DGPFM uses deep Gaussian processes to map functions accurately and quantify uncertainty.
problem Learning mappings between functional spaces, especially when data are noisy, sparse, or irregularly sampled.
method Constructs a sequence of GP-based linear and nonlinear transformations directly in function space, leveraging kernel integral transforms, GP conditional means, and nonlinear activations sampled from Gaussian processes.
result Empirical results show DGPFM outperforms existing methods in predictive accuracy and uncertainty calibration.
Paper optimizes urban navigation with deep learning models.
problem Real-time urban pathfinding challenges.
method Enhanced A* algorithm and neural network model.
result Neural network model outperforms traditional methods, reducing travel times by up to 40%.
This paper analyzes deep and wide transformer training dynamics.
problem Understanding the training dynamics of infinitely deep and wide transformers.
method Develops a mean-field framework for gradient-based training of transformers, controlling a neural PDE.
result Establishes a rigorous foundation for gradient-based transformer training, proving convergence to global minima.
The paper studies how noise synchronizes tokens in deep transformer models.
problem Understanding synchronization in deep learning models with noise.
method Proves convergence to a stochastic particle system and identifies the limiting SDE.
result The limiting model displays synchronization by noise and exponential dissipation of interaction energy.
Proposes a new framework for deep learning conditional mean estimation with confidence regions.
problem Lack of asymptotic properties in deep nonparametric regression models.
method Transforms deep estimation into conditional diffusion model for conditional mean estimation.
result Developed end-to-end convergence rate and asymptotic normality for conditional diffusion model.
Deep linear ResNets converge globally with certain transformations.
problem Global convergence of training deep linear ResNets.
method Gradient descent and stochastic gradient descent for training L-hidden-layer linear ResNets. result GD and SGD can converge to global minimum for deep linear ResNets with specific transformations.
The inference of deep hierarchical models is problematic due to strong dependencies between the hierarchies. We investigate a specific transformation of the model parameters based on the multivariate distributional transform. This transformation is a special form of the reparametrization trick, flattens the hierarchy a…
Spectral gradient methods outperform Euclidean in certain deep learning scenarios.
problem When do spectral gradient updates outperform Euclidean in deep learning?
method Layerwise condition comparing squared nuclear-to-Frobenius ratio to stable rank of activations.
result Spectral updates can be more effective than Euclidean in deep networks and transformers.
Transformer model predicts train axle vibrations for safer maintenance.
problem Prevent mechanical failures in railway axles.
method Integrates Deep Autoregressive solution with spectral methods and observation models.
result Transformer model (ShaftFormer) improves predictive maintenance for railway axles.
Model approximates continuous functions in 1-Wasserstein space.
problem Approximating continuous functions in 1-Wasserstein space.
method Probabilistic Transformer (PT) model with three phases: feature map, deep neural network, and probabilistic extension of attention mechanism.
result Can approximate any continuous function from R^d to P1(R^D) uniformly on compact sets.
Transformer model improves asset allocation by unifying forecasting and optimization.
problem Separation of forecasting and optimization leads to suboptimal portfolios.
method Signature Informed Transformer using path signatures and specialized attention.
result Direct minimization of Conditional Value at Risk improves performance.
Deep learning method solves American options with free boundary using Landau transformation.
problem Solving American options with a free boundary using deep learning.
method Landau transformation, dual solution framework, auxiliary function, feed forward deep neural network (DNN).
result Deep learning method efficiently prices options with early exercise features.
A new method uses Schrödinger bridges for deep conditional generative learning.
problem Learning conditional distributions with additional information.
method Schrödinger bridge approach with discretized SDE and deep neural network.
result Generated samples have higher quality and can estimate conditional density.
REST improves robustness of black-box models to geometric transformations.
problem Overconfident incorrect predictions on out-of-distribution samples.
method REinforcement Spatial Transform learner (REST) that transforms input data into in-distribution samples.
result Improves robustness to geometric transformations and sample efficiency.
Enformer and GEnformer use Transformers with stochastic learning to forecast multivariate and spatiotemporal data with uncertainty.
problem Uncertainty quantification in multivariate time series and spatiotemporal forecasting.
method Synthesizing Transformer's expressive power with stochastic learning to model conditional distributions directly.
result Enformer and GEnformer yield calibrated probabilistic forecasts and outperform state-of-the-art baselines.
Deep learning improves portfolio optimization in volatile markets.
problem Challenges in long-only, multi-asset strategies across market cycles.
method Training DL models with limited regime data using pre-training techniques and transformer architectures.
result Models show resilience and improved predictive accuracy in volatile markets.
Deep Transformed Gaussian Processes extend TGPs with variational inference for scalable multi-layer modeling.
problem Flexible modeling of complex data distributions.
method DTGPs are a multi-layer model of TGPs using variational inference for scalability.
result DTGPs achieve good scalability and performance in multiple regression datasets.
Study excess risk in statistical inference with transformations.
problem Excess risk in estimating random variables from feature vectors and transformations.
method Characterize lossless transformations, develop test statistics, and information-theoretic bounds.
result Strongly consistent partitioning test statistic for lossless transformations.
Transformers can solve complex filtering problems for non-Gaussian signals.
problem Non-linear and non-Markovian filtering problems for conditionally Gaussian signals.
method Continuous-time transformer models called filterformers.
result Filterformers can approximate the conditional law of non-Markovian and conditionally Gaussian signal processes.
Random Fourier features improve tabular deep learning convergence.
problem Tabular deep learning convergence issues.
method Random Fourier projections as a pre-processing step, projecting inputs into a fixed feature space.
result Random Fourier pre-processing accelerates tabular deep learning convergence.
Image clustering is an important but challenging task in machine learning. As in most image processing areas, the latest improvements came from models based on the deep learning approach. However, classical deep learning methods have problems to deal with spatial image transformations like scale and rotation. In this p…
Deep vanilla transformers trained without shortcuts achieve similar performance to standard models.
problem Training deep vanilla transformers without shortcuts and normalizations.
method Parameter initializations, bias matrices, and location-dependent rescaling.
result Deep vanilla transformers can train at similar speeds and performance to standard models.
Transformers can perform well with less long-range memory.
problem The need for deep long-range memory in Transformers for language modeling.
method Performed interventions to show performance can be achieved with fewer long-range memories and by limiting attention range.
result Comparable performance can be achieved with 6X fewer long-range memories and better performance with limited attention range.
A deep learning framework learns wavelet packet transforms for efficient feature extraction.
problem Efficiently extracting meaningful time-frequency features from high-frequency signals.
method Learnable wavelet packet transforms using deep learning.
result Improved spectral leakage and enhanced anomaly detection performance.
New insights into how depth and width affect in-context learning in deep models.
problem Understanding how various resources impact in-context learning in deep models.
method Analyzed linear regression in a deep linear self-attention model, varying resources like depth, width, context length, and training steps.
result Increasing depth improves in-context learning even at infinite context length, contrary to previous findings.
Deep learning uses layers of transformations to predict structured data with uncertainty.
problem Predicting structured high-dimensional data efficiently and with uncertainty.
method Applying layers of semi-affine input transformations to find features for probabilistic statistical methods.
result Achieves scalable prediction rules with uncertainty quantification and feature selection.
New approach learns image transformations directly for clustering.
problem Learning better deep representations for image clustering.
method Directly learns transformations and clusters in image space without abstract features.
result Jointly learns prototypes and transformations using deep learning modules.
New analysis shows RPE-based Transformers can't approximate all functions.
problem Understanding the limitations of RPE-based Transformers in approximating continuous functions.
method Mathematical analysis and development of a novel attention module (URPE) to overcome limitations.
result RPE-based Transformers can't approximate all continuous sequence-to-sequence functions, even with depth and width.
Roundtrip uses deep generative models for flexible density estimation.
problem Density estimation in statistics and machine learning.
method Roundtrip is a deep generative neural density estimator that uses flexible mappings.
result Roundtrip achieves state-of-the-art performance in density estimation tasks.
This study examines how model architecture affects deep learning model privacy.
problem Privacy concerns in deep learning models due to potential leakage of sensitive information.
method Investigation of CNNs and Transformers, focusing on activation layers, stem layers, LN layers, and attention modules.
result Transformers generally exhibit higher vulnerability to privacy attacks than CNNs.
Due to their flexibility and predictive performance, machine-learning based regression methods have become an important tool for predictive modeling and forecasting. However, most methods focus on estimating the conditional mean or specific quantiles of the target quantity and do not provide the full conditional distri…
Variational autoencoders (VAEs), that are built upon deep neural networks have emerged as popular generative models in computer vision. Most of the work towards improving variational autoencoders has focused mainly on making the approximations to the posterior flexible and accurate, leading to tremendous progress. Howe…
Bayesian model for discrete data with conditional transformations.
problem Handling discrete ordinal and count data with excess zeros.
method Bayesian framework with conditional transformation functions and modular MCMC algorithm.
result Flexible modeling of linear and nonlinear covariate effects for ordinal and count data.
Transformer model forecasts electricity price spread for virtual bidding.
problem Volatility in renewable energy causes price forecasting challenges.
method Transformer-based deep learning model using various time-series features.
result Trading strategy at peak hour yields nearly consistent profit.
Deep structured models are widely used for tasks like semantic segmentation, where explicit correlations between variables provide important prior information which generally helps to reduce the data needs of deep nets. However, current deep structured models are restricted by oftentimes very local neighborhood structu…
Paper proposes a method for estimating tropical cyclone intensity distribution using deep learning.
problem Lack of full accounting of prediction variability in single-point forecasts.
method Smooth model over target and covariates, logistic transformation for conditional density, case-control sampling approximation.
result Method provides insights into predicted response behavior, improving decision-making and policy.
Single-layer Transformer can approximate any sequence mapping.
problem Lack of theoretical understanding of Transformers.
method Review of linear algebra, probability, and optimization concepts; detailed analysis of Transformer architecture.
result A single-layer Transformer can approximate any continuous sequence-to-sequence mapping to arbitrary precision.
This paper studies transformer learning dynamics and initialization.
problem Understanding how transformers learn Markov chains and the role of initialization.
method First-order Markov chains and single-layer transformers, proving learning dynamics and conditions for convergence.
result Transformer parameters can converge to global or local minima based on initialization and Markovian data properties.
Woodbury transformations improve deep generative models with efficient invertibility and determinant calculation.
problem Efficiently invertible and determinant-calculable functions for deep generative models.
method Introducing Woodbury transformations that leverage matrix identities for efficient invertibility and determinant calculation.
result Woodbury transformations enable high-dimensional interactions, efficient sampling, and likelihood evaluation, outperforming other flow architectures.
Transformer architecture improved with credibility mechanism for better model performance.
problem Improving predictive models in tabular data.
method Introducing a credibility mechanism to the Transformer architecture.
result Credibility Transformer leads to superior predictive models compared to state-of-the-art models.
Deep generative models for graphs have shown great promise in the area of drug design, but have so far found little application beyond generating graph-structured molecules. In this work, we demonstrate a proof of concept for the challenging task of road network extraction from image data. This task can be framed as im…
New insights show stochastic initialization prevents token clustering in deep Transformers.
problem Understanding token dynamics in deep stochastic Transformers.
method Analysis of deep Transformers with random initialization noise, proving convergence to an interacting-particle system on the sphere.
result Initialization noise prevents token clustering, leading to antipodal formations.
The signature is an infinite graded sequence of statistics known to characterise a stream of data up to a negligible equivalence class. It is a transform which has previously been treated as a fixed feature transformation, on top of which a model may be built. We propose a novel approach which combines the advantages o…
New model learns symmetry transformations from complex data.
problem Learning symmetry transformations in complex domains like chemical space.
method Two latent subspaces, deep information bottleneck, continuous mutual information regularizer.
result Model outperforms state-of-the-art methods on artificial and molecular datasets.