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.

168,878 papers · 148 categories

Trend · papers per month

192384576768 · Jun 202019922001200920172026
48 results for finite sample behavior

This work analyzes IRM and ERM from sample complexity perspective, revealing different behaviors under various distribution shifts.

problem Choosing between IRM and ERM for OOD generalization.
method Sample complexity analysis comparing IRM and ERM under different data generation mechanisms.
result IRM is preferred over ERM for certain distribution shifts, leading to better OOD generalization.

The paper explains why estimating a history-dependent policy can reduce MSE in reinforcement learning.

problem Understanding why history-dependent policies can improve MSE in off-policy evaluation.
method The paper derives a bias-variance decomposition of MSE for various OPE estimators, showing how history-dependent policies can decrease variance and increase bias.
result History-dependent policies can decrease the variance of importance sampling estimators, leading to lower MSE.

The paper improves PCS approximation for ranking and selection under limited simulation budgets.

problem Improving finite sample performance in Ranking and Selection.
method Develops a Bahadur-Rao type expansion for PCS, proposes a novel FCBA policy.
result FCBA policy achieves superior PCS performance compared to traditional methods.

The study reveals a transition in neural network performance from infinite-width to variance-limited behavior as dataset size increases.

problem Understanding the transition from infinite-width to variance-limited behavior in neural networks.
method Empirical study of the transition from infinite-width to variance-limited behavior as a function of sample size and network width.
result The critical sample size \( P^* \) is approximately \( \sqrt{N} \) for polynomial regression with ReLU networks.

Paper provides convergence guarantees for off-policy NAC with finite sample complexity.

problem Convergence analysis of off-policy natural actor-critic algorithm.
method Finite-sample analysis with Importance Sampling and Q-trace algorithm.
result Converges to global optimal policy with sample complexity O(ε3log2(1/ε))\mathcal{O}(ε^{-3}\log^2(1/ε)).

Study on estimating class probabilities using empirical risk minimization.

problem Estimating class probabilities within binary classification.
method Empirical risk minimization (ERM) for class probability estimation.
result The estimator converges to true class probabilities under certain conditions.

New framework predicts AMP behavior in spiked models for finite iterations.

problem Understanding AMP dynamics in high-dimensional spiked models.
method Developed a non-asymptotic framework for AMP in spiked matrix estimation.
result Predicted AMP behavior for up to O(npolylogn)O\big(\frac{n}{\mathrm{poly}\log n}\big) iterations in Z2\mathbb{Z}_2 synchronization.

Study non-parametric frequency-domain system identification from finite samples.

problem Frequency-domain system identification from limited data.
method Empirical Transfer Function Estimate (ETFE) under sub-Gaussian colored noise and stability assumptions.
result ETFE estimates are concentrated around true values with a finite-sample rate of Ntot1/3N_{\mathrm{tot}}^{-1/3} for all frequencies in the H \mathcal{H}_{\infty} norm.

This work analyzes tree-based methods from a ranking perspective, providing insights and new statistics.

problem Understanding the effectiveness of tree-based methods in finite-sample settings, especially symbolic feature selection.
method Local ranking perspective, finite-sample analysis, oracle bounds, posterior contraction results, concordant divergence statistics.
result New insights and statistics for evaluating symbolic feature mappings.

Proposes a neural network method to combine nonprobability and probability survey samples.

problem Combining nonprobability and probability survey samples for accurate population mean estimation.
method Uses a deep neural network to estimate sampling scores from nonprobability samples and combines them with probability sample information.
result Proposed estimators improve robustness to parametric propensity-score misspecification, especially for nonlinear selection mechanisms.

Study learns dynamics of linear systems from multiple short trajectories.

problem Learning dynamics of autonomous linear systems from multiple short trajectories.
method Finite sample analysis for stable and unstable systems, adjusting trajectory length for marginally stable systems.
result Learning rate of O(1N)\mathcal{O}(\frac{1}{\sqrt{N}}) for both stable and unstable systems.

Unified framework for solving fixed-point equations in deterministic and stochastic settings.

problem Solving fixed-point equations for seminorm-contractive operators in both deterministic and stochastic contexts.
method Fixed-point theorem and stochastic approximation analysis.
result Unified finite-sample bounds for various reinforcement learning algorithms.

Learning the minimum/maximum mean among a finite set of distributions is a fundamental sub-task in planning, game tree search and reinforcement learning. We formalize this learning task as the problem of sequentially testing how the minimum mean among a finite set of distributions compares to a given threshold. We deve…

2018-06-04abs ↗pdf ↗

CoinDICE estimates confidence intervals for unknown behavior policies in reinforcement learning.

problem Estimating value of a target policy using only behavior policy data.
method Function space embedding, generalized empirical likelihood method, Lagrangian optimization.
result Valid confidence intervals with tighter and more accurate estimates than existing methods.

SARSA is an on-policy algorithm to learn a Markov decision process policy in reinforcement learning. We investigate the SARSA algorithm with linear function approximation under the non-i.i.d.\ data, where a single sample trajectory is available. With a Lipschitz continuous policy improvement operator that is smooth eno…

2019-02-06abs ↗pdf ↗

Unified bounds for iterative algorithms with Gaussian data matrices.

problem Establishing non-asymptotic bounds for iterative algorithms with Gaussian data.
method Explicit coupling between iterates and Gaussian process with deterministic covariance.
result Tight, dimension-free bounds for generalized first-order methods.

Study shows offline RL with partial coverage and weak function classes is possible.

problem Learning optimal policies from logged data with function approximation.
method Marginalized Importance Sampling (MIS) with additional covering distribution.
result Finite-sample guarantees for sample-efficient offline RL for general MDPs.

Although consistency is a minimum requirement of any estimator, little is known about consistency of the mean partition approach in consensus clustering. This contribution studies the asymptotic behavior of mean partitions. We show that under normal assumptions, the mean partition approach is consistent and asymptotic …

2015-12-18abs ↗pdf ↗

New method stabilizes FQE by reweighting Bellman targets.

problem Stability guarantees for FQE often rely on Bellman completeness, which can fail with function approximation.
method Proposes stationary-weighted FQE, reweighting Bellman targets by stationary target-to-behavior density ratio.
result Proves finite-sample linear convergence to stationary projected Bellman fixed point without Bellman completeness.

Extends JKO scheme for iterative algorithms with unknown parameters.

problem Computational and statistical analysis of iterative algorithms with unknown parameters.
method Develops statistical methods to estimate unknown parameters and adapts JKO scheme.
result Establishes asymptotic theory for the statistical JKO scheme.

The paper improves off-policy evaluation in contextual bandits using conformal prediction.

problem Quantifying the performance of a target policy using data from a different behavior policy.
method Proposes a novel algorithm based on a PAC-valid conformal prediction framework to construct probably approximately correct prediction intervals.
result Establishes PAC-type bounds on coverage, improving theoretical guarantees.

New econometric results for financial duration models under varying tail behaviors.

problem Estimation and inference challenges in financial durations models with random event counts.
method Analysis of likelihood estimators for ACD models, focusing on tail behavior and stationarity.
result Asymptotic normality breaks down for tail indices smaller than one, leading to mixed Gaussian estimators with non-standard rates of convergence.

Study proposes efficient estimators for matrix-valued linear regression under sparsity assumptions.

problem Estimation of parameters in matrix-valued linear regression models.
method Explicit optimization-free estimators for matrix-valued linear regression models with sparsity assumptions.
result Established non-asymptotic convergence rates for the proposed estimators.

Estimates time-series drifts from i.i.d. data using a direct Nadaraya-Watson plug-in method.

problem Nonparametric estimation of Schrödinger bridge drifts from single time interval data.
method Direct Nadaraya-Watson plug-in estimator based on kernelized numerator and denominator terms.
result Uniform non-asymptotic bound, CLT under undersmoothing, and adaptive bandwidth selector.

Corrects distribution shift in target shift scenarios using importance weighting.

problem Analyzes importance weighting for correcting distribution shift under target shift.
method Analyzed importance-weighted kernel ridge regression under target shift.
result Shows that importance weighting corrects the train-test mismatch without altering input-space complexity.

New meta-reinforcement learning method improves performance in finite-horizon MDPs.

problem Improving meta-reinforcement learning in finite-horizon MDPs with shared optimal action-value functions.
method Proposes MTSRL and MTSRL+ algorithms with learned priors and covariance, coupled with prior-alignment technique for meta-regret guarantees.
result Achieves meta-regret guarantees with learned priors and covariance, outperforming prior-independent RL and bandit-only meta-baselines.

Convolutional neural networks handle rotated image symmetries without dimensionality issues.

problem Binary image classification with rotational symmetry.
method Least squares plug-in classifiers based on convolutional neural networks under rotationally symmetric assumptions.
result Convolutional neural networks can circumvent the curse of dimensionality in binary image classification with rotational symmetry.

Wide networks with polynomial activations have proven asymptotic behavior.

problem Understanding the behavior of neural networks in the large width limit.
method Proving a conjecture for deep networks with polynomial activation functions.
result Tight bounds on the behavior of wide networks during stochastic gradient descent and derivation of their finite-width dynamics.

Paper explores Thompson Sampling for heavy-tailed distributions in sequential decision-making.

problem Sequential decision-making with heavy-tailed rewards.
method Revisit Thompson Sampling for symmetric α\alpha-stable distributions, presenting algorithms and proving regret bounds.
result Thompson Sampling outperforms in heavy-tailed reward settings.

MAFLA improves sampling from heavy-tailed distributions using MH-inspired corrections.

problem Sampling from heavy-tailed and multimodal distributions when neither target nor proposal densities can be evaluated.
method Metropolis-Adjusted Fractional Langevin Algorithm (MAFLA) with Score Balance Matching.
result MAFLA significantly improves finite-time sampling accuracy over unadjusted fractional Langevin dynamics.

The paper improves conformal prediction by analyzing the beta law of conditional coverage.

problem Improving finite-sample marginal coverage guarantees for non-i.i.d. data.
method The method uses Wasserstein distances to quantify deviations from the beta law of conditional coverage.
result The framework provides direct bounds on marginal coverage gaps and bad-calibration probabilities.

In this paper we propose a new approach to estimation of the tail exponent in financial stock markets. We begin the study with the finite sample behavior of the Hill estimator under α-stable distributions. Using large Monte Carlo simulations, we show that the Hill estimator overestimates the true tail exponent and can …

2012-01-23abs ↗pdf ↗

New method improves robustness in partially observable domains by training against latent distribution shifts.

problem Challenges in robustness under latent distribution shift in partially observable reinforcement learning.
method Formalizes adversarial latent-initial-state POMDP, proves minimax principle, derives best-response inequalities.
result Reduces robustness gaps from 10.3 to 3.1 shots with targeted exposure to shifted latent distributions.