Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,657 papers · 148 categories

Trend · papers per month

4285127169 · Jun 202019922001200920172026
48 results for High-Dimensional Portfolios

A machine learning model manages portfolio risk in high dimensions.

problem Managing risk in high-dimensional financial portfolios.
method A supervised learning approach using replicating martingales and polynomial/neural network bases.
result The model outperforms naive Monte Carlo and least-squares Monte Carlo methods.

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

problem Analyzing risks in high-dimensional portfolios using empirical variance.
method Derives asymptotic behavior of out-of-sample variance and relative loss in high-dimensional settings.
result Empirical out-of-sample relative loss is more reliable than variance in high-dimensional portfolios.

Deep RL algorithm trades high-dimensional stock portfolios.

problem Trading high-dimensional stock portfolios with data gaps and non-unique history lengths.
method Deep Q-learning algorithm, sequentially setting up environments, rewarding based on asset returns and cash reservation.
result Algorithm outperforms all passive and active benchmarks by a large margin.

Bayesian model reduces stock volatility by identifying key cointegrated relationships.

problem Constructing low volatility stock portfolios from a large number of stocks.
method High dimensional Bayesian cointegration estimation.
result Portfolios with reduced volatility and persistence of cointegration relationships.

Study high-dimensional covariance matrix estimators for complex portfolios, improving financial metrics.

problem Estimating covariance matrices in high-dimensional portfolios with nested and one-factor structures.
method Combining random matrix theory, free probability, deterministic equivalents, and two-step covariance estimators.
result Two-step estimators improve financial metrics in complex and one-factor covariance models.

New method optimizes portfolios with options, addressing asymmetry, dimensionality, and dependence.

problem Optimizing portfolios with options, especially when distributions are asymmetric, dimensions are high, and payoffs are dependent.
method Developed a new dependency matrix based on conditional probabilities of options' payoffs, computed using copula structures.
result Empirical evidence shows the approach is efficient, fast, and scalable to large portfolios of options.

New shrinkage estimator for GMV portfolio reduces risk in high-dimensional asset settings.

problem Estimating the global minimum variance portfolio in high-dimensional settings with limited data.
method Dynamic shrinkage of the GMV portfolio using previous data as a target.
result The new estimator outperforms traditional methods in high-dimensional asset settings.

Deep BSDE method for pricing and hedging complex financial portfolios.

problem Simultaneous pricing and delta-gamma hedging of large portfolios of multi-asset Bermudan options.
method Discretely reflected BSDEs, One Step Malliavin scheme, neural network regression Monte Carlo method.
result Efficient and accurate pricing and hedging strategies for high-dimensional portfolios.

New AI platform screens portfolios for desirable firms and news.

problem Optimizing portfolio selection with AI.
method Two LLM agents screen for firm fundamentals and news sentiment. Agents deliberate to generate buy/sell signals. High-dimensional estimation determines optimal weights.
result Screened portfolio's Sharpe ratio consistently estimates target, superior to baseline and conventional approaches.

Framework uses RL with dynamic embedding to outperform benchmarks in volatile markets.

problem Challenges in high-dimensional, non-stationary, and noisy market information.
method Dynamic embedding of market information using generative autoencoders and online meta-learning in a reinforcement learning framework.
result Framework outperforms common portfolio benchmarks and PTO approach during market stress.

New methods improve portfolio risk minimization by estimating covariance matrix more accurately.

problem Uncertainty in estimating covariance matrix leads to unreliable hedge trades.
method Proposes two new estimators of the inverse covariance matrix using l2 and l1 norms.
result Portfolio formed using proposed estimators achieves substantial risk reduction and improved returns.

Study portfolio selection with exogenous and endogenous transaction costs using deep learning.

problem Portfolio selection with both exogenous and endogenous transaction costs.
method Deep learning-driven policy iteration scheme for high-dimensional HJB equations.
result Proposes a scheme to address the curse of dimensionality and adapt to high-dimensional control spaces.

Proposes a model to generate high-dimensional financial returns using latent factor structure.

problem Challenges in financial scenario simulation, especially in high-dimensional and small data settings.
method Integrates latent factor structure into generative diffusion processes, decomposing the score function using time-varying orthogonal projections.
result Establishes rigorous statistical guarantees for score estimation and generated distribution, surpassing dimension-dependent limits.

A new model optimizes portfolios by learning stock return distributions conditioned on factors.

problem Optimizing portfolios with high-dimensional asset-specific factors.
method Conditional Diffusion Transformer architecture linking each asset's return to its factor vector.
result The model outperforms benchmarks in mean-variance and mean-CVaR optimization.

In this article we deal with the problem of portfolio allocation by enhancing network theory tools. We use the dependence structure of the correlations network in constructing some well-known risk-based models in which the estimation of correlation matrix is a building block in the portfolio optimization. We formulate …

2019-07-02abs ↗pdf ↗

The paper analyzes constrained optimal portfolios in high dimensions using novel statistical learning techniques.

problem Forming optimal portfolios with constraints in high-dimensional asset spaces.
method CROWN method integrating factor models with nodewise regression for estimation in large dimensions.
result Demonstrates estimation consistency and convergence rates for constrained portfolio weights, risk, and Sharpe Ratio.

Paper uses deep reinforcement learning for optimal stock portfolio management.

problem Optimizing stock portfolio choices in complex market environments.
method Direct deep reinforcement learning to learn factor representations and make optimal decisions.
result Deep learning outperforms average market performance in portfolio allocation.

The paper optimizes portfolios with transaction costs in a large asset universe.

problem Optimizing portfolios with transaction costs in a large asset universe.
method Mean-variance optimization with nonconvex penalty for proportional and quadratic transaction costs.
result The proposed models show satisfactory performance and highlight the importance of transaction costs.

In this paper we propose a cyclical coordinate descent (CCD) algorithm for solving high dimensional risk parity problems. We show that this algorithm converges and is very fast even with large covariance matrices (n > 500). Comparison with existing algorithms also shows that it is one of the most efficient algorithms.

2013-11-16abs ↗pdf ↗

The paper examines extreme value statistics of high-dimensional sample covariances, with applications in finance and image analysis.

problem Statistical validation of normal conditions in high-dimensional time series data.
method Generalizes the maximal deviation of sample autocovariances to high dimensions and applies Gumbel-type extreme value asymptotics.
result Gumbel-type extreme value asymptotics holds true for high-dimensional sample covariances.

Develops FGL for better portfolio allocation under common factor influence.

problem Sparsity assumption fails for stock returns driven by common factors.
method Integrates graphical models with factor structure to estimate portfolio weights and risk exposure robust to heavy-tailed distributions.
result FGL-based portfolios outperform equal-weighted and Index portfolios in empirical applications.

Study long-only minimum variance portfolio in one-factor market with arbitrary sign betas.

problem Characterize the long-only minimum variance portfolio in a one-factor market with mixed-sign betas.
method Explicit solution for long-only minimum variance portfolio, explicit characterization of active set, asymptotic analysis in high-dimensional regime.
result Proportion of active assets in LOMV portfolio converges to F(β)F(β^*) in high-dimensional regime, with rate O(F(0)1/3)O(F(0)^{1/3}) when F(0)>0F(0) > 0.

Empirical study shows Randomized Signature Methods improve portfolio optimization in financial markets.

problem Drift estimation in non-linear, non-parametric financial markets is challenging.
method Applied Randomized Signature Methods for non-linear, non-parametric drift estimation in multi-variate financial markets.
result Randomized Signature Methods provide features on the same scale and improve portfolio optimization in real-world settings.

Develops a dynamic latent-factor model for high-dimensional asset characteristics.

problem Estimating asset pricing tests with high-dimensional data.
method Dynamic latent-factor model with Double Selection Lasso regularization.
result The inflation-mimicking portfolio in the crypto asset class has positive risk compensation.

RL accelerates portfolio optimization and option pricing by dynamically adjusting preconditioner sizes.

problem Large linear systems in portfolio optimization and option pricing lead to slow convergence.
method Reinforcement Learning (RL) dynamically adjusts block-preconditioner sizes to accelerate convergence.
result RL-driven solver significantly reduces computational cost and accelerates convergence.

Bayesian Parametric Portfolio Policies corrects overestimation of utility and risk in traditional PPP.

problem Traditional Parametric Portfolio Policies ignore policy risk, leading to overestimation of expected utility and understatement of portfolio risk.
method Developed Bayesian Parametric Portfolio Policies (BPPP) by placing a prior on policy coefficients to correct the decision rule.
result BPPP delivers higher Sharpe ratios, lower turnover, larger investor welfare, and lower tail risk compared to traditional PPP.

Study improves forecast accuracy of daily volatility to enhance portfolio performance.

problem Improving predictability of realized variance from market views.
method High-dimensional machine learning models and low-dimensional factor models used to forecast firm-level volatility.
result Marginal improvements in forecast error lead to significant gains in portfolio performance.

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 11 the asymptotic out-of-sample expected utilit…

2016-11-07abs ↗pdf ↗

Spatial statisticians and quantitative investors use the same mathematical object: a Schur complement, damped by one parameter.

problem The Schur complement is used in both spatial modeling and portfolio allocation, but the parameters are different.
method The Schur complement is interpreted as reliability shrinkage of a conditional Gaussian.
result The Schur complement is the same in both applications.

Closed-form optimal portfolios for exponential utility in small/large markets.

problem Optimal portfolios maximizing exponential utility in small/large financial markets.
method Closed-form expressions for optimal portfolios in small markets, convergence to large market optimal utility, numerical procedure for general utility functions.
result Optimal utility in large markets converges to optimal utility in small markets, requiring infinite diversification.

Model improves covariance estimation from shared and distinct datasets.

problem Limited sample sizes and shared covariance structure across related datasets.
method Spiked covariance model with shared subspace, closed-form pooling weight, and asymptotic guarantees.
result Improves estimation of high-dimensional covariance matrices from related datasets.

BPASGM uses sparse graphical models to optimize portfolio selection.

problem Portfolio optimization in high-dimensional settings with estimation error.
method BPASGM extends BPA to a sparse graphical model, screening assets for diversification.
result BPASGM portfolios outperform standard mean-variance portfolios in risk-adjusted performance.

Bayesian approach for constructing and rebalancing sparse index-tracking portfolios.

problem Sparse tracking of a reference index with uncertainty quantification.
method Sparse linear regression with Laplace prior, empirical-Bayes calibration, Langevin-type MCMC, threshold-based rules.
result Posterior uncertainty on tracking error, portfolio composition, and rebalancing moves.