We identify action representations from video data, proving their statistical benefits.
problem Identifying latent action policies from video data.
method Entropy-regularized LAPO objective, formalizing desiderata for action representations.
result Entropy-regularized LAPO identifies action representations satisfying desiderata under suitable conditions.
Statistical test evaluates if personalizing interventions is cost-effective.
problem Balancing the benefits of personalizing interventions with their potential costs.
method Developed a statistical hypothesis test to assess the performance of personalized interventions.
result The test shows that personalized interventions can outperform standard approaches under certain conditions.
Cost-benefit analysis often assumes accurate estimates, but this study finds significant inaccuracies.
problem Inaccurate cost and benefit estimates in public investments.
method Largest dataset of public investments, statistical analysis of cost overruns and benefit shortfalls.
result Significant inaccuracies in cost and benefit estimates of public investments.
Statistical arbitrage is a class of financial trading strategies using mean reversion models. The corresponding techniques rely on a number of assumptions which may not hold for general non-stationary stochastic processes. This paper presents an alternative technique for statistical arbitrage based on online learning w…
New algorithm balances user reward and statistical inference by mixing TS with UR based on difference size.
problem Combining statistical inference with user reward in adaptive experiments.
method TS-PostDiff algorithm that uses UR when differences are small and TS when large.
result TS-PostDiff reduces false positives and increases statistical power for small differences, while maximizing reward for large ones.
New framework improves cost-benefit analysis of policies.
problem Limitations of MVPF in welfare analysis.
method Developed an axiomatic framework to create RPV.
result RPV provides better equity-efficiency trade-off quantification.
Oil is perceived as a good diversification tool for stock markets. To fully understand this potential, we propose a new empirical methodology that combines generalized autoregressive score copula functions with high frequency data and allows us to capture and forecast the conditional time-varying joint distribution of …
Actuaries tackle loss of earning capacity in Denmark, balancing public benefits and private insurance.
problem Balancing public benefits and private insurance for loss of earning capacity in Denmark.
method Innovative approaches from researchers and practitioners, leveraging actuarial expertise.
result Development of equitable, data-driven solutions to mitigate risk and enhance societal well-being.
We design and study a Contextual Memory Tree (CMT), a learning memory controller that inserts new memories into an experience store of unbounded size. It is designed to efficiently query for memories from that store, supporting logarithmic time insertion and retrieval operations. Hence CMT can be integrated into existi…
The paper studies the benefits of curriculum learning in linear regression tasks.
problem Theoretical understanding of curriculum learning's benefits in machine learning.
method Theoretical analysis of curriculum learning in structured and unstructured multitask linear regression problems.
result Adaptive learning in the unstructured setting is fundamentally harder than oracle learning, but not in the structured setting.
Score matching offers efficient estimation for certain distributions.
problem Estimating probability distributions with intractable constants.
method Score matching as an alternative to maximum likelihood.
result Score matching is computationally and statistically efficient for certain distributions.
Data augmentation can achieve the same statistical benefits as full augmentation up to an approximation error.
problem Data augmentation in learning problems
method Using Fourier analysis and representation theory of finite groups
result Partial data augmentation achieves the same minimax rates as full augmentation
Entropy-based model for hierarchical learning from multiscale data.
problem Learning from data with auxiliary information and multiscale target functions.
method Entropy-based hierarchical learning model with multiscale entropies.
result Entropy-based model yields stronger guarantees than uniform convergence bounds.
This paper explores how entropic regularization improves Wasserstein estimators' performance.
problem Improving the approximation and estimation properties of Wasserstein estimators.
method Entropic regularization of optimal transport costs to smooth Wasserstein estimators.
result Entropic regularization can achieve comparable statistical performance to un-regularized estimators at lower computational cost.
Early stopping improves logistic regression's calibration and consistency in high dimensions.
problem Improving the statistical performance of gradient descent in overparameterized logistic regression.
method Investigates the effects of early stopping on gradient descent in logistic regression.
result Early-stopped gradient descent is well-calibrated and statistically consistent, while asymptotic gradient descent is not.
The paper introduces a method to measure the benefits of incidental supervision signals.
problem Lack of a principled way to measure the benefits of various types of incidental supervision signals.
method Unified PAC-Bayesian motivated informativeness measure, PABI.
result Demonstrates PABI's effectiveness in quantifying the value added by various types of incidental signals.
This paper derives -- considering a Gaussian setting -- closed form solutions of the statistics that Adrian and Brunnermeier and Acharya et al. have suggested as measures of systemic risk to be attached to individual banks. The statistics equal the product of statistic specific Beta-coefficients with the mean corrected…
National statistical systems are the enterprises tasked with collecting, validating and reporting societal attributes. These data serve many purposes - they allow governments to improve services, economic actors to traverse markets, and academics to assess social theories. National statistical systems vary in quality, …
Framework for discovering treatment benefits in user segments.
problem Discovering differential impacts of treatments across user subgroups.
method Combines causal inference and machine learning for user segment discovery.
result Unified approach for treatment benefit discovery and assignment.
This dissertation shows that careful injection of noise into sample data can substantially speed up Expectation-Maximization algorithms. Expectation-Maximization algorithms are a class of iterative algorithms for extracting maximum likelihood estimates from corrupted or incomplete data. The convergence speed-up is an e…
Distributions over permutations arise in applications ranging from multi-object tracking to ranking of instances. The difficulty of dealing with these distributions is caused by the size of their domain, which is factorial in the number of considered entities (n!). It makes the direct definition of a multinomial dist…
This article introduces a framework to estimate the value of evidence-based decision making.
problem Lack of empirical tools to assess the value of evidence-based decision making and optimize statistical precision.
method Empirical framework using parametric and nonparametric empirical Bayes methods.
result The value of statistical evidence depends on how organizations translate it into policy decisions.
Data balancing reduces variance in machine learning models.
problem Reduction of variance in machine learning models.
method Non-asymptotic statistical bound and eigenvalue decay of Markov operators.
result Data balancing across modalities and sources reduces variance.
A wide variety of machine learning algorithms such as support vector machine (SVM), minimax probability machine (MPM), and Fisher discriminant analysis (FDA), exist for binary classification. The purpose of this paper is to provide a unified classification model that includes the above models through a robust optimizat…
One of the most surprising and exciting discoveries in supervised learning was the benefit of overparameterization (i.e. training a very large model) to improving the optimization landscape of a problem, with minimal effect on statistical performance (i.e. generalization). In contrast, unsupervised settings have been u…
The authors argue against the classification of forecasting methods as machine learning or statistical.
problem The classification of forecasting methods as machine learning or statistical limits insights into their appropriateness and effectiveness.
method Alternative characteristics of forecasting methods are proposed to draw meaningful conclusions.
result The distinction between machine learning and statistical forecasting methods is not fundamental.
New methods stabilize EEG classification performance across subjects.
problem Large performance drop in EEG classification models on unseen subjects.
method Regularization techniques using divergence estimation.
result Significant increase in balanced accuracy on test subjects.
The Maximum Mean Discrepancy (MMD) has found numerous applications in statistics and machine learning, most recently as a penalty in the Wasserstein Auto-Encoder (WAE). In this paper we compute closed-form expressions for estimating the Gaussian kernel based MMD between a given distribution and the standard multivariat…
New methods solve tensor-on-tensor regression with unknown rank, revealing benefits of over-parameterization.
problem Connecting tensor responses to tensor covariates with unknown intrinsic rank.
method Riemannian gradient descent and Riemannian Gauss-Newton methods for tensor-on-tensor regression.
result Riemannian optimization methods converge linearly and quadratically to a statistically optimal estimate in rank over-parameterized settings.
Enhanced ROOT-SGD optimizes stochastic optimization with diminishing stepsizes.
problem Improving statistical efficiency in stochastic optimization.
method Integrates a diminishing stepsize strategy into ROOT-SGD.
result Achieves optimal convergence rates with improved stability and precision.
Research creates a machine learning model for predicting TAVI patient mortality.
problem Lack of robust risk scores for TAVI patients.
method Gradient boosting on decision trees, feature analysis and selection, model validation.
result Model outperforms existing risk scores with AUC of 0.83.
Improved statistical inference for adaptive Thompson Sampling.
problem Statistical inference challenges in Thompson Sampling.
method Inflating posterior variance in Thompson Sampling.
result Asymptotically normal estimates of arm means with logarithmic regret increase.
Extreme value theory enhances statistical learning extrapolation for rare events.
problem Challenges in traditional machine learning methods for extreme data.
method Asymptotic theory and statistical tools for tail behavior.
result Effective extrapolation methods for extreme quantiles and anomalies.
This paper presents a class of new algorithms for distributed statistical estimation that exploit divide-and-conquer approach. We show that one of the key benefits of the divide-and-conquer strategy is robustness, an important characteristic for large distributed systems. We establish connections between performance of…
Non-linear image reconstruction and signal analysis deal with complex inverse problems. To tackle such problems in a systematic way, I present information field theory (IFT) as a means of Bayesian, data based inference on spatially distributed signal fields. IFT is a statistical field theory, which permits the construc…
Paper proposes a statistical test for transfer learning in linear regression.
problem Theoretical framework for parameter transfer in linear regression.
method Developed a statistical test to predict transfer quality.
result The test can predict if a fine-tuned model has lower prediction risk.
The paper establishes limits of transfer learning with neural networks.
problem Understanding the fundamental limits of transfer learning.
method Statistical minimax framework for regression with linear and neural network models.
result Lower bounds for target generalization error.
Theoretical guarantees for neural estimators in parametric statistics are derived.
problem Lack of theoretical guarantees for neural estimators in parametric statistics.
method Decompose risk into terms and verify assumptions for convergence.
result Derive theoretical guarantees for neural estimators.
A number of results have recently demonstrated the benefits of incorporating various constraints when training deep architectures in vision and machine learning. The advantages range from guarantees for statistical generalization to better accuracy to compression. But support for general constraints within widely used …
This work presents a methodology to design trajectory tracking feedback control laws, which embed non-parametric statistical models, such as Gaussian Processes (GPs). The aim is to minimize unmodeled dynamics such as undesired slippages. The proposed approach has the benefit of avoiding complex terramechanics analysis …
The two key issues of modern Bayesian statistics are: (i) establishing principled approach for distilling statistical prior that is consistent with the given data from an initial believable scientific prior; and (ii) development of a Bayes-frequentist consolidated data analysis workflow that is more effective than eith…
Neural networks speed up statistical inference.
problem Efficient statistical inference for complex models.
method Neural networks for learning complex mappings.
result Amortized inference speeds up inference processes.
A neural network approach unifies Lasso for variable selection.
problem Combining statistical and machine learning techniques for variable selection.
method Representing Lasso through a neural network and developing a new optimization algorithm.
result The new optimization algorithm achieves better performance than previous methods.
New algorithms improve Bayesian linear regression with spike-and-slab priors.
problem Efficiently sampling from Bayesian linear regression models with sparsity-inducing priors.
method Design of two sampling algorithms: Gibbs sampling and Stochastic Localization.
result Stochastic Localization sampler shows significant advantage for poorly designed data matrices.
Causal ML predicts treatment outcomes, aiding personalized medicine.
problem Predicting individualized treatment effects for personalized medicine.
method Flexible, data-driven methods using causal inference with clinical trial and real-world data.
result Causal ML allows for estimating individualized treatment effects.
Simple methods combine statistical tests for out-of-distribution detection.
problem Detecting data points not following the training distribution.
method Combining classical parametric tests (Rao's score test) and a typicality test.
result Combining Fisher's method of test statistics improves out-of-distribution detection accuracy.
PAS improves estimation of multiple means using ML predictions and shrinkage.
problem Improving statistical estimates with limited gold-standard data and noisy ML predictions.
method Prediction-Powered Adaptive Shrinkage (PAS) that combines PPI with empirical Bayes shrinkage.
result PAS adapts to the reliability of ML predictions and outperforms traditional methods in large-scale applications.
This article presents results from the first statistically significant study of cost escalation in transportation infrastructure projects. Based on a sample of 258 transportation infrastructure projects worth US$90 billion and representing different project types, geographical regions, and historical periods, it is fou…