arXiv research

Study compares adaptive vs fixed query learning methods.

Improved multi-group learning with group-realizable concepts.

New active learning framework for multiclass classification beyond realizability assumption.

Characterizes statistical complexity of realizable regression in PAC and online learning.

Enhanced volatility model using LSTM and realized volatility.

Unified framework for realizable and agnostic learning.

Study shows realizable learnability doesn't imply agnostic learnability for distributions.

Theory extends optimal learning rates without realizability assumption.

In this paper we formulate a regression problem to predict realized volatility by using option price data and enhance VIX-styled volatility indices' predictability and liquidity. We test algorithms including regularized regression and machine learning methods such as Feedforward Neural Networks (FNN) on S&P 500 Index a…

The study compares econometric and deep learning models for forecasting COMEX copper futures volatility.

Boosts weak online learners to strong ones with sublinear regret.

Study of loss functions for learning to defer, proving consistency.

New method improves dictionary recovery from over-realized models.

New algorithms estimate Q-functions under partial coverage and realizability, improving offline RL guarantees.

We consider the problem of learning a realization for a linear time-invariant (LTI) dynamical system from input/output data. Given a single input/output trajectory, we provide finite time analysis for learning the system's Markov parameters, from which a balanced realization is obtained using the classical Ho-Kalman al…

New DP algorithms achieve near-optimal regret bounds for online learning problems.

Neural network training is usually accomplished by solving a non-convex optimization problem using stochastic gradient descent. Although one optimizes over the networks parameters, the main loss function generally only depends on the realization of the neural network, i.e. the function it computes. Studying the optimiz…

New RL method learns to skip states in linearly $q^π$-realizable MDPs, simplifying to linear MDPs.

Paper proposes a deep learning method for better covariance matrix forecasting.

New offline RL method works with limited data and function approximators.

New algorithms for interactive learning match minimax bounds efficiently.

New algorithms improve label complexity for active multi-distribution learning.

Lower bounds on Bayes risk for realizable models derived using information theory.

Criterion for realizing groups on Enriques manifolds.

GEEN uses deep learning to estimate unobserved variables from observed data.

Breaks the hardness conjecture for batch RL with a novel tournament-based approach.

New method efficiently evaluates policies using trajectory data.

This paper studies universal rates of ERM for binary classification under agnostic learning.

Bayesian realized EGARCH models improve tail risk forecasting.

Study robust online learning with adversarial perturbations.

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

The realized GARCH framework is extended to incorporate the two-sided Weibull distribution, for the purpose of volatility and tail risk forecasting in a financial time series. Further, the realized range, as a competitor for realized variance or daily returns, is employed in the realized GARCH framework. Further, sub-s…

This paper tackles deferral learning with multiple experts, providing strong theoretical guarantees.

We study realizations of Lie algebras by vector fields. A correspondence between classification of transitive local realizations and classification of subalgebras is generalized to the case of regular local realizations. A reasonable classification problem for general realizations is rigorously formulated and an algori…

A new model framework called Realized Conditional Autoregressive Expectile (Realized-CARE) is proposed, through incorporating a measurement equation into the conventional CARE model, in a manner analogous to the Realized-GARCH model. Competing realized measures (e.g. Realized Variance and Realized Range) are employed a…

Enhanced volatility forecasting using options data and rough volatility model.

Comparative learning combines realizable and agnostic settings for two hypothesis classes, reducing sample complexity.

The paper examines circle graphs of Gauss diagrams and finds counterexamples to previous descriptions.

VOLARE provides standardized realized volatility measures from financial data.

Incorrect parity-based descriptions of realizable Gauss diagrams found, but bipartite graphs provide a valid approach.

The abstract discusses convergent realizations of Lie subalgebras in control theory.

Paper tackles sample-efficient RL for linearly realizable MDPs with limited revisiting.

Improved private agnostic learning with near-optimal sample complexity.

Efficient RL algorithm for MDPs with linear $Q^π$ realizability, achieving optimal regret bound.

HAR model outperforms ML in stock forecasting with correct fitting schemes.

Paper integrates real data into probabilistic models using Fourier transform.

We give a characterization of conformal classes realizing a compact manifold's Yamabe invariant. This characterization is the analogue of an observation of Nadirashvili for metrics realizing the maximal first eigenvalue, and of Fraser and Schoen for metrics realizing the maximal first Steklov eigenvalue.

New bandit algorithm works without realizability assumption.