arXiv research

Paper introduces DOO models to outperform SAA out-of-sample.

Optimizes decisions without knowing the true distribution using historical data.

OTSL improves structure learning accuracy with out-of-sample and resampling strategies.

Optimal data-driven formulations are found for learning and decision-making with historical data.

This paper proposes an out-of-sample extension framework for a global manifold learning algorithm (Isomap) that uses temporal information in out-of-sample points in order to make the embedding more robust to noise and artifacts. Given a set of noise-free training data and its embedding, the proposed framework extends t…

New model optimizes portfolios over multiple periods using predictive control.

Paper presents a new way to analyze machine learning generalization without probabilistic assumptions.

We consider the multi-class classification problem when the training data and the out-of-sample test data may have different distributions and propose a method called BCOPS (balanced and conformal optimized prediction sets). BCOPS constructs a prediction set $C(x)$ as a subset of class labels, possibly empty. It tries …

We study the out-of-sample properties of robust empirical optimization problems with smooth $φ$-divergence penalties and smooth concave objective functions, and develop a theory for data-driven calibration of the non-negative "robustness parameter" $δ$ that controls the size of the deviations from the nominal model. Bu…

Downsampling can improve generalization in ridgeless linear regression, especially with optimal sketching size.

We study the profitability of optimal mean reversion trading strategies in the US equity market. Different from regular pair trading practice, we apply maximum likelihood method to construct the optimal static pairs trading portfolio that best fits the Ornstein-Uhlenbeck process, and rigorously estimate the parameters.…

New framework for learning policies that converge in out-of-sample regions.

Improved portfolio optimization using machine learning and hierarchical clustering.

Optimal number of voters for a voting ensemble can be estimated from the distribution of classifier errors.

Several popular graph embedding techniques for representation learning and dimensionality reduction rely on performing computationally expensive eigendecompositions to derive a nonlinear transformation of the input data space. The resulting eigenvectors encode the embedding coordinates for the training samples only, an…

We provide a general theoretical analysis of expected out-of-sample utility, also referred to as decision-theoretic classification, for non-decomposable binary classification metrics such as F-measure and Jaccard coefficient. Our key result is that the expected out-of-sample utility for many performance metrics is prov…

We address the problem of prescribing an optimal decision in a framework where the cost function depends on uncertain problem parameters that need to be learned from data. Earlier work proposed prescriptive formulations based on supervised machine learning methods. These prescriptive methods can factor in contextual in…

Proposes a new model to maximize out-of-sample Sharpe ratios by forecasting tangency portfolios.

RandALO speeds up risk estimation for large datasets.

A new hyperparameter optimization method reduces overfitting.

Sparse modeling improves portfolio optimization by reducing errors in complex market systems.

Proposes a new framework to optimize portfolios with reduced estimation errors.

Paper analyzes high-dimensional portfolio risks and finds empirical out-of-sample relative loss is more reliable.

Random Forests automatically prune a latent 'true' tree, explaining their overfitting without tuning.

In this paper we estimate the mean-variance portfolio in the high-dimensional case using the recent results from the theory of random matrices. We construct a linear shrinkage estimator which is distribution-free and is optimal in the sense of maximizing with probability $1$ the asymptotic out-of-sample expected utilit…

We consider the problem of vertex classification for graphs constructed from the latent position model. It was shown previously that the approach of embedding the graphs into some Euclidean space followed by classification in that space can yields a universally consistent vertex classifier. However, a major technical d…

New method for estimating out-of-sample R² from gene expression data.

The paper optimizes portfolios using a new GARCH model with regime switching and tempered stable innovations.

In the past decade many researchers have proposed new optimal portfolio selection strategies to show that sophisticated diversification can outperform the naïve 1/N strategy in out-of-sample benchmarks. Providing an updated review of these models since DeMiguel et al. (2009b), I test sixteen strategies across six empir…

When the in-sample Sharpe ratio is obtained by optimizing over a k-dimensional parameter space, it is a biased estimator for what can be expected on unseen data (out-of-sample). We derive (1) an unbiased estimator adjusting for both sources of bias: noise fit and estimation error. We then show (2) how to use the adjust…

Graph embeddings, a class of dimensionality reduction techniques designed for relational data, have proven useful in exploring and modeling network structure. Most dimensionality reduction methods allow out-of-sample extensions, by which an embedding can be applied to observations not present in the training set. Appli…

Stochastic Gradient Descent can overfit after just a few passes, contrary to initial expectations.

Two strategies for embedding new data points from proximity data are explored.

New method improves feature selection in tree-based models.

Many popular dimensionality reduction procedures have out-of-sample extensions, which allow a practitioner to apply a learned embedding to observations not seen in the initial training sample. In this work, we consider the problem of obtaining an out-of-sample extension for the adjacency spectral embedding, a procedure…

The paper analyzes the generalization performance of spectral clustering algorithms and proposes new methods to improve their effectiveness.

A note on learning with agents having global perspectives and a principal optimizing their performance.

This study compares three portfolio design approaches for stock selection.

Dimensionality reduction methods are very common in the field of high dimensional data analysis. Typically, algorithms for dimensionality reduction are computationally expensive. Therefore, their applications for the analysis of massive amounts of data are impractical. For example, repeated computations due to accumula…

Paper proposes a diagnostic tool for evaluating model performance out-of-sample.

Study integrates machine learning with SAA for optimizing decisions based on uncertain parameters and covariates.

dboost optimizes prediction models for convex cone problems.

This study optimizes trading strategy parameters using walk-forward techniques and finds robust performance.

Proposes a bond portfolio solution for managing interest rate risk.

We identify and validate a model for PCR in high dimensions, improving prediction guarantees.

New method optimises worst-case risk under model uncertainty.

Dimensionality reduction is a topic of recent interest. In this paper, we present the classification constrained dimensionality reduction (CCDR) algorithm to account for label information. The algorithm can account for multiple classes as well as the semi-supervised setting. We present an out-of-sample expressions for …

Study the impact of overfitting on linear predictive models' performance.