New sample complexity bounds for linear predictors and neural networks, focusing on initialization.
problem Understanding sample complexity for vector-valued linear predictors and neural networks, especially under initialization-dependent conditions.
method Size-independent bounds on Frobenius norm distance from a fixed reference matrix, applying to vector-valued predictors and neural networks.
result Established new sample complexity bounds for feed-forward neural networks, resolving open questions and introducing a new learnable problem.
This paper proposes a method to reduce complexity in GLMs with categorical predictors.
problem Wasteful, hard-to-interpret, and prone to overfitting of traditional one-hot encoding for high-cardinality categorical predictors.
method Clustering categories of categorical predictors through a numerical method that preserves or improves accuracy while reducing the number of coefficients.
result Clustering categories of categorical predictors reduces complexity substantially without harming accuracy.
The paper develops predictors for functional data on manifolds.
problem Functional data prediction on time-varying manifolds.
method Least-squares local linear Fréchet curve predictor and weighted Fréchet mean approach.
result Asymptotical optimality of the proposed predictors.
We analyze the (unconditional) distribution of a linear predictor that is constructed after a data-driven model selection step in a linear regression model. First, we derive the exact finite-sample cumulative distribution function (cdf) of the linear predictor, and a simple approximation to this (complicated) cdf. We t…
Method constructs confidence regions for linear models with arbitrary predictors.
problem Constructing confidence regions for linear models with non-linear predictors.
method Mixed Integer Linear Programming for constraints.
result Empty confidence regions for hypothesis testing.
LIT-LVM improves linear predictors by estimating interaction terms with latent vectors.
problem Accurately estimating coefficients for interaction terms in linear predictors.
method Structured regularization using latent vectors to represent features.
result LIT-LVM achieves superior prediction accuracy compared to other methods.
Linear properties are either universal or absent across language models.
problem Explaining the prevalence of linear properties in language models.
method Proved identifiability of distribution-equivalent next-token predictors and analyzed various notions of linearity.
result Linear properties either hold in all or none distribution-equivalent next-token predictors.
In this work, we study the problem of aggregating a finite number of predictors for nonstationary sub-linear processes. We provide oracle inequalities relying essentially on three ingredients: (1) a uniform bound of the ℓ1 norm of the time varying sub-linear coefficients, (2) a Lipschitz assumption on the predict…
Overparameterized MLR fits hyper-curves, improving model robustness.
problem Improper predictors degrade model generalizability.
method Parameterizing with a scalar and monomial basis, fitting hyper-curves.
result Hyper-curve approach yields robust predictions for noisy data.
Predict covariance from features using convex optimization.
problem Predicting the covariance of a Gaussian vector from another feature vector.
method A generalized linear model with convex optimization for fitting parameters.
result Predicted covariance matrices are symmetric positive definite.
Study on merging predictors in causal and anticausal directions using CMAXENT.
problem Comparing merging predictors in causal and anticausal directions.
method Using CMAXENT as inductive bias, study differences in merging predictors.
result CMAXENT solution reduces to logistic regression in causal direction and LDA in anticausal direction.
In machine learning and data mining, linear models have been widely used to model the response as parametric linear functions of the predictors. To relax such stringent assumptions made by parametric linear models, additive models consider the response to be a summation of unknown transformations applied on the predict…
We study online linear regression problems in a distributed setting, where the data is spread over a network. In each round, each network node proposes a linear predictor, with the objective of fitting the \emph{network-wide} data. It then updates its predictor for the next round according to the received local feedbac…
Least squares estimator fails to achieve optimal risk in bounded distributions, but non-linear predictors can.
problem Optimal risk in bounded distributions for constrained least squares.
method Comparison of least squares and non-linear predictors.
result Non-linear predictors can achieve optimal risk O(d/n) in bounded distributions. The study finds a trade-off between model size, test loss, and training loss for linear predictors.
problem Finding the optimal balance between model size, test loss, and training loss for linear predictors.
method Established an algorithm and distribution-independent trade-off using non-asymptotic analysis.
result Models with low test loss are either classical (close to noise level training loss) or modern (large number of parameters).
Random imputation is surprisingly effective for linear predictors in missing data scenarios.
problem The effectiveness of naive imputation in missing data scenarios for linear predictors.
method A unique random features model framework to study predictive performances.
result Naive imputation is negligible in bias for linear predictors under MCAR assumption.
A new Bayesian approach to linear system identification has been proposed in a series of recent papers. The main idea is to frame linear system identification as predictor estimation in an infinite dimensional space, with the aid of regularization/Bayesian techniques. This approach guarantees the identification of stab…
We present a method to stop the evaluation of a prediction process when the result of the full evaluation is obvious. This trait is highly desirable in prediction tasks where a predictor evaluates all its features for every example in large datasets. We observe that some examples are easier to classify than others, a p…
Improved classification model for high-cardinality categorical predictors.
problem Handling high-cardinality categorical predictors and non-linear data.
method Data-driven binning of spline functions and shrinkage estimators.
result Improved classification precision with interpretable predictors.
The problem of forecasting conditional probabilities of the next event given the past is considered in a general probabilistic setting. Given an arbitrary (large, uncountable) set C of predictors, we would like to construct a single predictor that performs asymptotically as well as the best predictor in C, on any data.…
In this short note, we provide a sample complexity lower bound for learning linear predictors with respect to the squared loss. Our focus is on an agnostic setting, where no assumptions are made on the data distribution. This contrasts with standard results in the literature, which either make distributional assumption…
Study examines how body segments respond to random vibrations.
problem Understanding human body responses to random vibrations.
method 35 participants were tested with random noise signals. Multiple linear regression models were created to determine influential predictors of peak translational gains.
result Multiple predictors, including motion direction and body segment, significantly influence peak translational gains.
New bounds show linear predictors rarely overfit with certain optimization methods.
problem Bounding test error for linear predictors with stochastic optimization methods.
method Coupling argument for fixed point methods like stochastic and batch mirror descent.
result Locally-adapted rates that depend on predictor properties, not global problem structure.
New insights into when benign overfitting occurs in linear and classification tasks.
problem Understanding when benign overfitting happens in linear and classification models.
method Analysis of a generic data model and comparison of predictors (minimum-norm interpolating and max-margin).
result The minimum-norm interpolating predictor is biased towards an inconsistent solution, preventing benign overfitting in linear regression.
New probabilistic complexity measures for linear and kernel methods.
problem Limitations of linear and kernel methods in machine learning.
method Introducing approximate notions of dimensional and margin complexity.
result Approximate complexity measures are both sufficient and necessary for learning.
Ensemble methods that average over a collection of independent predictors that are each limited to a subsampling of both the examples and features of the training data command a significant presence in machine learning, such as the ever-popular random forest, yet the nature of the subsampling effect, particularly of th…
We consider building predictors when the data have missing values. We study the seemingly-simple case where the target to predict is a linear function of the fully-observed data and we show that, in the presence of missing values, the optimal predictor may not be linear. In the particular Gaussian case, it can be writt…
Deep neural networks improve AFT model for non-linear predictors.
problem Nonlinearity in predictors of AFT models.
method Apply DNNs to fit AFT models using Gehan-type loss and sub-sampling.
result DeepR-AFT outperforms parametric and semiparametric models.
Recent results in the literature indicate that a residual network (ResNet) composed of a single residual block outperforms linear predictors, in the sense that all local minima in its optimization landscape are at least as good as the best linear predictor. However, these results are limited to a single residual block …
This paper provides estimation and inference methods for the best linear predictor (approximation) of a structural function, such as conditional average structural and treatment effects, and structural derivatives, based on modern machine learning (ML) tools. We represent this structural function as a conditional expec…
Paper proposes a sparse synthetic control method to select important predictors.
problem Choosing and weighting predictors affects synthetic control estimator performance.
method Sparse synthetic control procedure that penalizes predictors, derived in a linear factor model.
result Sparse synthetic control achieves lower bias and better post-treatment performance.
New method selects sparse predictors in large LMMs.
problem Sparse learning for LMMs is computationally infeasible for large datasets.
method Developed an ℓ0 regularized method with coordinate descent and local search algorithms. result Method selects thousands of predictors in seconds to minutes.
This work precisely characterizes and improves the tradeoff between robustness and accuracy in linear regression.
problem Tradeoff between robustness and accuracy in adversarial training.
method Characterizes the effect of augmentation on standard error in linear regression; proves RST improves robust error without sacrificing standard error.
result RST improves both standard and robust error for neural networks under various perturbations.
New bounds prevent degradation in high-dimensional signal estimation.
problem Statistical learning bounds degradation with increasing dimensionality.
method Investigates linear prediction rules under structural assumptions.
result Derives upper and lower bounds on generalization error.
PARC uses piecewise linear predictors for regression and classification.
problem Multivariate regression and classification problems.
method Alternates between ridge and softmax regression, and cluster assignment based on accuracy and separability.
result Converges to a local minimum in a finite number of steps.
Efficient oblique RSF method improves prediction and interpretability.
problem Limited computational efficiency and difficulty in interpreting oblique RSF ensembles.
method Newton-Raphson scoring for computational efficiency and negation importance for variable importance estimation.
result The method reduces computational overhead by 450 times and improves prediction accuracy.
High-dimensional data pose challenges in statistical learning and modeling. Sometimes the predictors can be naturally grouped where pursuing the between-group sparsity is desired. Collinearity may occur in real-world high-dimensional applications where the popular l1 technique suffers from both selection inconsisten…
Optimal trading strategy with predictor and costs, derived equations and shape.
problem Optimal trading strategy in presence of price predictor, costs, and risk control.
method Path-integral method to derive equations for band edges, solved explicitly for Ornstein-Uhlenbeck predictor.
result Explicit equations and shape of the optimal band strategy derived and analyzed.
Technology and collaboration enable dramatic increases in the size of psychological and psychiatric data collections, but finding structure in these large data sets with many collected variables is challenging. Decision tree ensembles like random forests (Strobl, Malley, and Tutz, 2009) are a useful tool for finding st…
Derives bounds for deterministic predictors using smooth loss functions.
problem Generalizing probabilistic predictors to deterministic ones.
method Exploits smoothness properties of loss and predictor classes, controlling the Jensen gap class through Rademacher complexity.
result Derives bounds for deterministic predictors involving flatness quantities from Jacobians and Hessians.
Proposes extensions to semi-parametric models using BART for shared covariates.
problem Avoiding poor coverage properties and reducing bias in linear predictor estimates.
method Modifies tree-generation moves in BART to handle shared covariates between linear and non-parametric components.
result Competitive performance in modelling complex interactions and predicting student achievements.
New method converts LVAs into linear projections for better understanding of complex models.
problem Limited interpretability of nonlinear machine learning models.
method Animated linear projections and radial tours.
result Improved understanding of variable importance in complex models.
The paper examines how deep linear neural networks behave as they become infinitely wide.
problem Understanding the behavior of deep linear neural networks as they approach infinite width.
method Analyzes the infinite-width limit of deep linear neural networks, proving convergence to deterministic models and providing precise laws for random weights.
result The training dynamics of deep linear neural networks converge to those of a deterministic model, and the weights' behavior is precisely described.
Model improves mortgage credit risk prediction with spatio-temporal machine learning.
problem Improving accuracy of default probabilities and loan portfolio loss distributions in mortgage credit risk.
method Combines tree-boosting with a latent spatio-temporal Gaussian process model.
result Predictive models outperform conventional methods due to non-linear and spatio-temporal effects.
New theory validates the use of invariant predictors for OOD generalization.
problem Ensuring predictors generalize well across unseen environments.
method Developed new theoretical conditions and derived an Inter Gradient Alignment algorithm.
result Validated the necessity of invariant predictors for OOD optimality.
Multiclass prediction is the problem of classifying an object into a relevant target class. We consider the problem of learning a multiclass predictor that uses only few features, and in particular, the number of used features should increase sub-linearly with the number of possible classes. This implies that features …
We carefully study how well minimizing convex surrogate loss functions, corresponds to minimizing the misclassification error rate for the problem of binary classification with linear predictors. In particular, we show that amongst all convex surrogate losses, the hinge loss gives essentially the best possible bound, o…
New bounds explain deterministic non-smooth deep nets without large Lipschitz constants.
problem Challenges in explaining generalization of deterministic non-smooth deep nets.
method De-randomized PAC-Bayes margin bounds for deterministic non-convex and non-smooth predictors.
result New bounds avoid large Lipschitz constants, providing generalization guarantees.