arXiv research

Study online monotone density estimation with expert aggregation and log-optimal calibration.

We present a method for constructing the log-optimal portfolio using the well-calibrated forecasts of market values. Dawid's notion of calibration and the Blackwell approachability theorem are used for computing well-calibrated forecasts. We select a portfolio using this "artificial" probability distribution of market …

Develops pathwise analysis for log-optimal portfolios using rough paths theory.

This paper shows how to combine optimal tests into log-optimal processes.

Proposes a sliding window method for better portfolio trading.

This paper addresses the log-optimal portfolio for a general semimartingale model. The most advanced literature on the topic elaborates existence and characterization of this portfolio under no-free-lunch-with-vanishing-risk assumption (NFLVR). There are many financial models violating NFLVR, while admitting the log-op…

Paper proposes a method to solve log-optimal portfolios under ambiguous return distributions.

We proposed a new Portfolio Management method termed as Robust Log-Optimal Strategy (RLOS), which ameliorates the General Log-Optimal Strategy (GLOS) by approximating the traditional objective function with quadratic Taylor expansion. It avoids GLOS's complex CDF estimation process,hence resists the "Butterfly Effect" …

Investigates how rebalancing frequency and transaction costs affect log-optimal portfolios.

The paper analyzes log-optimal portfolios in markets with random time events.

This paper shows a buy-and-hold strategy is asymptotically log-optimal for a market with a dominant asset.

Survival strategies in a market with self-determined prices are closely tied to log-optimal investment.

This paper tackles cost-sensitive portfolio optimization under ambiguous return distributions.

This paper focuses on numéraire portfolio and log-optimal portfolio (portfolio with finite expected utility that maximizes the expected logarithm utility from terminal wealth), when a market model $(S,\mathbb F)$ -specified by its assets' price $S$ and its flow of information $\mathbb F$- is stopped at a random time $τ…

A new portfolio model improves on Kelly's by accounting for estimation error.

Bayes-assisted confidence sequences improve efficiency for bounded means.

Investigates optimal portfolio strategies in markets with latent side information.

The paper analyzes optimal overbetting strategies for a satellite investment account.

Investor optimizes wealth in a market with non-traded endowment, deriving expansions up to second order.

Cover's celebrated theorem states that the long run yield of a properly chosen "universal" portfolio is as good as the long run yield of the best retrospectively chosen constant rebalanced portfolio. The "universality" pertains to the fact that this result is model-free, i.e., not dependent on an underlying stochastic …

In online portfolio optimization the investor makes decisions based on new, continuously incoming information on financial assets (typically their prices). In our study we consider a learning algorithm, namely the Kiefer--Wolfowitz version of the Stochastic Gradient method, that converges to the log-optimal solution in…

Develops a new model-free approach to portfolio theory using rough paths.

Proposes new method for calibrating treatment effect predictors.

Proposes top-label calibration and M2B framework for multiclass to binary calibration.

Study explores calibration properties in neural architectures.

A new perfectly truthful calibration measure improves prediction reliability.

New truthful calibration errors improve model ranking in multiclass prediction.

New framework for evaluating multiclass classifier calibration.

We propose a new framework to improve the calibration of neural networks.

Certified calibration methods protect model confidence from adversarial attacks.

Meta-Cal improves post-hoc calibration of neural networks.

Post-processing predictors reduces calibration errors for decision-making.

A new calibration metric bridges testability and actionability.

New study on neural network calibration, linking it to generalization gap.

A new method for multiclass calibration using vector quantization.

This post introduces model calibration and evaluation measures, highlighting issues with a common measure.

Unified calibration metrics improve forecast sharpness and accuracy.

New decision-theoretic calibration error metric improves prediction reliability.

Cone structures over minimal products can't be calibrated smoothly.

Post-hoc calibration improves uncertainty under domain shift.

Smooth calibration improves forecast reliability even with leaked information.

Planes are the only calibrated submanifolds with flat normal bundles.

We describe a family of calibrations arising naturally on a hyperkähler manifold $M$. These calibrations calibrate the holomorphic Lagrangian, holomorphic isotropic and holomorphic coisotropic subvarieties. When $M$ is an HKT (hyperkaehler with torsion) manifold with holonomy $SL(n, {\Bbb H})$, we construct another fam…

Simple proof shows forecasts can be calibrated in a few periods.

Survey of methods to calibrate neural network predictions.

This paper rethinks confidence calibration under covariate shifts.

New method calibrates neural network predictions for better reliability.

New conditions for calibrated submanifolds in Riemannian geometry.