Flexible framework for deep distributional regression models.
problem Learning conditional distributions from semi-structured data.
method Combines additive regression models with deep networks using TensorFlow.
result State-of-the-art predictive performance with interpretability.
Deep learning's success is puzzling from a statistical perspective.
problem Deep learning's success is puzzling from a statistical perspective.
method Physics-informed investigation of deep learning features and surprises.
result Neural scaling laws and their interplay with inductive biases.
Statistical field theory aids in understanding deep learning complexities.
problem Complexity and lack of theoretical understanding in deep learning.
method Statistical field theory as a theoretical framework.
result Field theory provides insights into generalization, bias, and feature learning.
The paper provides statistical guarantees for sparse deep learning.
problem Understanding the potential and limitations of sparse deep learning.
method Develops statistical guarantees for different types of sparsity in sparse deep learning.
result Statistical guarantees for sparse deep learning with mild dependence on network widths and depths.
Teaches deep learning to statisticians.
problem Statisticians lack expertise in deep learning.
method Developed a program and taught DL to statistics graduate students.
result Provided tips and resources for teaching DL.
The paper explains how many random seeds are needed for statistical significance in deep reinforcement learning experiments.
problem Ensuring statistical significance in deep reinforcement learning experiments.
method Theoretical guidelines for determining the number of random seeds for t-tests and bootstrap confidence intervals.
result Deviations from statistical test assumptions can lead to inaccurate evaluations of statistical errors.
Paper tackles complex risk in deep neural networks.
problem Complex risk in deep neural networks.
method Developed new approach for complex risk statistics.
result Derived dual representation for complex risk.
MASS Learning trains models to use minimal sufficient statistics, improving performance and uncertainty quantification.
problem Training deep networks to use minimal sufficient statistics for better performance and uncertainty quantification.
method MASS Learning trains models to produce minimal sufficient statistics with respect to a class of functions, using Conserved Differential Information (CDI).
result Deep networks trained with MASS Learning achieve competitive performance on supervised learning and uncertainty quantification benchmarks.
Deep learning used for parameter estimation in hard-to-infer models.
problem Parameter estimation in intractable models like max-stable processes.
method Train deep neural networks on simulated data to estimate parameters.
result Deep learning provides accurate and faster parameter estimation.
Deep models improve spatial and spatio-temporal data analysis.
problem Improving analysis of spatial and spatio-temporal data.
method Hybrid models combining statistical and deep learning approaches.
result Deep models enhance traditional statistical methods for complex data.
Lectures on deep learning properties in infinite and large-width networks.
problem Understanding deep neural networks in extreme width conditions.
method Analysis of random deep neural networks, connections to linear models, kernels, and Gaussian processes, perturbative and non-perturbative treatments.
result Properties and behaviors of deep neural networks in the infinite-width limit and large-width regime.
Study tests if deep hedging differs from delta hedging in a GARCH market model.
problem Whether deep hedging includes speculative components in a GARCH market.
method Tested in a GARCH-based market model, comparing deep hedging and delta hedging.
result The difference between deep hedging and delta hedging is speculative if risk measure does not prioritize adverse outcomes.
Deep learning models complex dependencies using neural networks.
problem Understanding the new characteristics and theoretical foundations of deep learning.
method Introduction of neural network models and training techniques from a statistical perspective.
result Highlight new characteristics of deep learning like depth and over-parametrization.
Statistical methods remain relevant for ODE inverse problems, especially with sparse data.
problem The relevance of statistical methods in the era of deep learning for ODE inverse problems.
method Employed physics-informed neural networks (PINN) and manifold-constrained Gaussian process inference (MAGI) to compare statistical and deep learning approaches.
result Statistically principled methods outperform deep learning models in tasks like parameter inference and trajectory reconstruction.
Study examines how statistical properties of deep learning representations can be adjusted.
problem Improving performance in deep learning models.
method Investigated eight representation regularization methods, including two new rank regularizers.
result Manipulating statistical properties of representations can indirectly improve model performance.
Combines deep and statistical learning for structured data.
problem Structured high-dimensional data challenges.
method Generates nonlinear features via sparse regularization and stochastic optimisation, uses probabilistic output layer for uncertainty.
result Achieves best of scalability and uncertainty quantification.
Deep-learning method improves hypothesis testing for independence.
problem Improving hypothesis testing for independence using deep learning.
method Proposes deep-testing, a novel procedure that uses a deep neural network to distinguish between data generated under and outside a given statistical model.
result Deep-testing achieves the highest overall power against nineteen competing methods across various dependence structures.
New framework tackles deep learning issues like local traps and miscalibration.
problem Local traps and miscalibration in deep neural networks.
method Sparse deep learning framework with prior annealing algorithms.
result Proposed method successfully addresses local traps and miscalibration.
Deep learning uncovers patterns between knot types.
problem Discovering connections between combinatorial and hyperbolic knot invariants.
method Statistical approach using linear regression and deep learning.
result Revealed empirical connections between knot types.
AdaStop improves statistical testing for Deep RL algorithm comparisons.
problem Statistical reproducibility issues in Deep RL.
method AdaStop, a new statistical test based on multiple group sequential tests.
result AdaStop ensures theoretically sound comparisons of Deep RL algorithms.
CRL uses causality to build interpretable AI models from complex data.
problem Interpreting deep neural networks' implicit representations.
method Causal representation learning (CRL) synthesizing latent variable models, causal graphical models, and nonparametric statistics.
result CRL can improve interpretability of generative AI models.
The study characterizes how deep learning models transform data.
problem Understanding how deep learning models transform data and their performance.
method Multivariate nonparametric estimator of class separation (HP statistic) to analyze layer-induced representations.
result Characterization of the distributional change to class separation induced at each layer of the model.
Develops a deep learning approach for statistical arbitrage.
problem Temporal price differences between similar assets.
method Constructs arbitrage portfolios using latent asset pricing factors and a convolutional transformer for time series signals.
result High risk-adjusted returns and Sharpe ratios with optimal trading policy.
DNA-SE uses deep learning to solve semiparametric problems efficiently.
problem Solving semiparametric integral equations in high dimensions.
method Formulates semiparametric estimation as a bi-level optimization problem and uses DNN to approximate solutions.
result Demonstrates numerical and statistical advantages over traditional methods.
Paper introduces a new gradient statistic to improve deep learning convergence.
problem Fluctuation effect of gradient updates between iterations.
method Introduces an unbiased stratified statistic \(\bar{G}_{mst}\) and a new algorithm MSSG.
result MSSG algorithm outperforms other sgd-like algorithms in training deep models.
Study reveals universal statistics of Fisher information in deep neural networks.
problem Characterizing Fisher information in deep neural networks.
method Used mean field theories with random weights and large width limits.
result Most eigenvalues of Fisher information matrix are close to zero, while the maximum eigenvalue is large.
In this paper we develop a statistical theory and an implementation of deep learning models. We show that an elegant variable splitting scheme for the alternating direction method of multipliers optimises a deep learning objective. We allow for non-smooth non-convex regularisation penalties to induce sparsity in parame…
Deep learning depends on tuning layers near critical points.
problem Understanding how deep learning architectures depend on tuning parameters.
method Random energy approach to analyze statistical dependence in deep belief networks.
result Statistical dependence can propagate only if layers are tuned near critical points.
This paper introduces a novel measure-theoretic theory for machine learning that does not require statistical assumptions. Based on this theory, a new regularization method in deep learning is derived and shown to outperform previous methods in CIFAR-10, CIFAR-100, and SVHN. Moreover, the proposed theory provides a the…
Deep neural networks identify robust arbitrage strategies in financial markets.
problem Identifying profitable trading strategies under model ambiguity.
method Data-driven deep neural networks considering high-dimensional financial markets.
result Empirical investigations show profitable trading performances in various market conditions.
p-DkNN uses deep representations to detect out-of-distribution data with statistical tests.
problem Lack of reliable confidence estimates in neural networks for safety-critical applications.
method Statistical testing of deep neural network's intermediate hidden representations.
result p-DkNN enables more accurate and reliable predictions by abstaining from incorrect predictions.
PENs learn summary statistics for ABC using invariant neural architectures.
problem Learning summary statistics for approximate Bayesian computation (ABC).
method Partially exchangeable networks (PENs) that are invariant to block-switch transformations.
result PENs provide more reliable posterior samples with less training data.
Bayesian Neural Networks help quantify uncertainty in deep learning predictions.
problem Uncertainty quantification in deep learning predictions.
method Bayesian statistics applied to neural networks.
result Design, implementation, training, and evaluation of Bayesian Neural Networks.
This study compares deep learning and statistical models for stock price forecasting.
problem Accurate stock price prediction is challenging due to market volatility.
method Used deep learning (LSTM, RNN, CNN, FULL CNN) and statistical models (ARIMA, Moving Averages) on S&P 500 data.
result LSTM model showed the lowest Mean Absolute Error (MAE), indicating highest accuracy.
Boltzmann Generators use deep learning to efficiently sample complex systems.
problem Sampling equilibrium states in many-body systems like proteins is computationally challenging.
method Combining deep learning and statistical mechanics, Boltzmann Generators learn a coordinate transformation to generate unbiased samples.
result Boltzmann Generators can generate one-shot equilibrium samples of complex systems and proteins.
Approximate Bayesian Computation (ABC) methods are used to approximate posterior distributions in models with unknown or computationally intractable likelihoods. Both the accuracy and computational efficiency of ABC depend on the choice of summary statistic, but outside of special cases where the optimal summary statis…
Deep morphing detects bone structures in low-quality X-ray images.
problem Detecting bone structures in low-quality fluoroscopic X-ray images.
method Two-stage deep learning approach using deep segmentation networks and statistical shape models.
result Efficiently detects bone structures in low-quality X-ray images.
New method quantifies deep kNN anomaly detection significance.
problem Lack of uncertainty quantification in deep kNN AD.
method Selective Inference for anomaly scoring.
result Validates AD reliability with controlled false positives.
Deep RL evaluation underestimates uncertainty, leading to misleading conclusions.
problem Statistical uncertainty in deep RL performance evaluations is underestimated, leading to misleading conclusions.
method Advocates for reporting interval estimates of aggregate performance and proposes performance profiles to account for variability.
result Substantial discrepancies in prior performance comparisons are revealed, highlighting the need for more rigorous evaluation methods.
Automated rock fragmentation assessment using deep learning and spatial statistics.
problem Assessing post-blast rock fragmentation in real-time.
method Fine-tuned YOLO12l-seg model for instance segmentation, followed by spatial statistics.
result Framework accurately assesses rock fragmentation patterns in real-time.
MegazordNet combines stats and ML for better financial time series forecasting.
problem Forecasting financial time series is challenging due to its chaotic nature.
method MegazordNet integrates statistical features with a deep learning model.
result MegazordNet outperforms single statistical and machine learning methods in S&P 500 stock price prediction.
Deep learning networks learn complex data structures.
problem Understanding the internal functioning of deep learning networks.
method Using complex network analysis techniques to study deep belief networks.
result Gained insights into the structural and functional properties of deep learning networks.
Backdoors in deep neural networks are undetectable and enable invariance-based adversarial examples.
problem Statistically undetectable backdoors in deep neural networks.
method Adversarial model trainer method to plant backdoors, showing invariance-based adversarial examples.
result Backdoors are statistically undetectable and enable generation of adversarial examples for every input.
Survey of deep learning methods for time series forecasting.
problem Improving accuracy in time series predictions across various domains.
method Analysis of common encoder and decoder designs, hybrid models, and decision support.
result Advancements in deep learning for time series forecasting.
Improved deep learning performance in financial markets by using rank space.
problem High volatility and low signal-to-noise ratio in equity market dynamics.
method Transformed equity market data from name space to rank space, enabling better learning by DNNs.
result DNNs achieve superior performance in statistical arbitrage in rank space compared to name space.
Paper proposes FedPer to combat statistical heterogeneity in federated learning for personalized tasks.
problem Statistical heterogeneity in federated learning data degrades performance of traditional federated averaging.
method FedPer: a base + personalization layer approach for federated training of deep feedforward neural networks.
result FedPer effectively combats statistical heterogeneity in non-identical data partitions of CIFAR datasets and personalized image aesthetics datasets.
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.
In this paper, we present a statistical-mechanical analysis of deep learning. We elucidate some of the essential components of deep learning---pre-training by unsupervised learning and fine tuning by supervised learning. We formulate the extraction of features from the training data as a margin criterion in a high-dime…