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.

168,742 papers · 148 categories

Trend · papers per month

63126188251 · Jun 202019922001200920172026
48 results for two-stage policy decomposition

POTEC tackles off-policy learning in large action spaces, improving effectiveness.

problem Existing OPL methods fail in large discrete action spaces due to bias or variance issues.
method Two-stage algorithm: cluster selection via policy-based approach, action selection via regression-based approach.
result POTEC provides substantial improvements in off-policy learning effectiveness, especially in large and structured action spaces.

CASP selects reliable policies for two-stage recommender systems by considering both value and support.

problem The selection of a generator in two-stage recommender systems affects both the policy value and the data support used to estimate it.
method CASP combines doubly robust value estimation with a support-burden penalty.
result CASP selects lower-burden policies when estimated value and support credibility are in tension.

Develops a reinforcement learning algorithm for learning deterministic equilibrium policies in time-inconsistent control problems.

problem Learning equilibrium policies in time-inconsistent control problems.
method Continuous-time model-free reinforcement learning algorithm using deterministic policy gradient approach.
result Learned equilibrium policies in general time-inconsistent control problems.

The paper addresses statistical estimation in MDPs with confounders using instrumental variables.

problem Statistical estimation of value functions in MDPs with unobservable confounders.
method Two-stage estimator based on instrumental variables for confounded linear MDPs.
result Established statistical properties of the two-stage estimator, including error bounds and asymptotic normality.

Machine learning can improve 2SLS first stage predictions, but nonlinear methods often introduce bias.

problem Improving the first stage of 2SLS using machine learning.
method Decomposed bias into three components, investigated through simulation.
result Nonlinear machine learning methods can introduce substantial bias in second-stage estimates.

We consider a multi-objective risk-averse two-stage stochastic programming problem with a multivariate convex risk measure. We suggest a convex vector optimization formulation with set-valued constraints and propose an extended version of Benson's algorithm to solve this problem. Using Lagrangian duality, we develop sc…

2017-11-17abs ↗pdf ↗

Trust-aware MAB improves learning performance by accounting for human deviation.

problem Learning performance suffers when humans deviate from recommended policies due to lack of trust.
method Integrates a dynamic trust model into MAB framework, establishing minimax regret and proposing a two-stage trust-aware procedure.
result Proves near-optimal statistical guarantees for trust-aware MAB algorithms.

A new conformal prediction framework for two-stage models identifies stage-wise uncertainty.

problem Limited coverage guarantees and lack of modular structure understanding in existing conformal prediction methods.
method Decomposes prediction residuals into stage-specific components, calibrates parameters using FWER control, and adapts to non-stationary settings.
result Improves coverage and identifies stage-wise error contributions compared to standard conformal methods.

DML-IV improves IV regression for learning decision policies by reducing bias.

problem Spurious correlations in offline datasets caused by hidden confounders.
method Double/debiased machine learning (DML) framework to reduce bias in two-stage IV regression.
result DML-IV outperforms state-of-the-art methods and learns high-performing policies.

Study on QQ-function estimation for continuous state-action MDPs, deriving rates and conditions.

problem Estimating QQ-function in off-policy evaluation for continuous state-action Markov decision processes.
method Reformulated as nonparametric instrumental variables (NPIV) problem, derived minimax lower bounds, proposed sieve two-stage least squares estimator.
result First minimax lower bounds for QQ-function and its derivatives in sup-norm and L2L^2-norm, same as classical nonparametric regression.

PS framework selects best policy from library for CSO problems.

problem Policy selection in CSO with heterogeneous performance across covariate space.
method PS framework constructs library of candidate policies and learns a meta-policy to select the best one.
result PS consistently outperforms best single policy in heterogeneous CSO problems.

SDM Policy accelerates inference for robotic tasks while maintaining high action quality.

problem Prolonged inference times in diffusion-based policies for high-frequency control tasks.
method Two-stage optimization: score matching and distribution matching; dual-teacher mechanism.
result 6x inference speedup with state-of-the-art action quality.

A new method reduces variance in training early-stage rankers for large-scale search systems.

problem Training early-stage rankers for large-scale search systems is challenging due to exploding variance in policy gradient methods.
method Proposes credit-assigned policy gradient (CA-PG) to mitigate variance in training early-stage rankers.
result CA-PG significantly reduces variance in training early-stage rankers compared to vanilla policy gradient.

Proposes a faster Isomap algorithm by reducing eigenvalue decomposition complexity.

problem High computational complexity of Isomap, especially in eigenvalue decomposition stage.
method Introduces a projection operator to reduce the complexity of the eigenvalue decomposition stage to linear order.
result Reduces Isomap's computational complexity to linear order while preserving structural information.

A new policy learning method allows policies to abstain when uncertain, improving safety and applicability.

problem Risk of making decisions without full confidence in uncertain predictions.
method Policy learning with abstention, identifying near-optimal policies and constructing an abstention rule.
result Improved safety and applicability in policy learning, with theoretical guarantees.

Lo-Hp decouples weight generation into local and global policies to improve flexibility and efficiency.

problem Over-coupling and long-horizon issues in current optimization methods.
method Hybrid-Policy Sub-Trajectory Balance objective.
result Learning local optimization policies addresses long-horizon issues and enhances global weight generation.

New ARIMA framework improves forecast accuracy for economic and financial time series.

problem Improving forecast accuracy for nonlinear dynamics in time series data.
method Projection-based ARIMA framework using Galerkin basis expansions.
result Galerkin-SARIMA matches or improves forecast accuracy compared to classical ARIMA/SARIMA.

A new reinforcement learning method for medical decisions with limited data.

problem Learning high-performing policies from partially observed data in healthcare.
method Optimization objective that combines policy and generative model quality, suitable for batch off-policy settings.
result Demonstrated improved performance on synthetic and medical decision-making problems.

The paper uncovers the mathematical structure enabling value decomposition in multi-agent systems.

problem Theoretical justification for why value decomposition works effectively in multi-agent systems remains underexplored.
method The paper introduces the concept of Markov entanglement to measure the underlying structure and demonstrates how it can be used to bound the decomposition error.
result The widely-used class of index policies is weakly entangled and enjoys a sublinear O(N)\mathcal O(\sqrt{N}) scale of decomposition error for NN-agent systems.

This paper improves Q-learning bounds using reference-advantage decomposition.

problem Improving Q-learning bounds in MDPs with positive suboptimality gaps.
method Develops a novel error decomposition framework to prove gap-dependent regret bounds.
result Establishes logarithmic gap-dependent regret bounds for Q-learning.

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.

Study tackles OPE in confounded settings, estimating policy value from proxies.

problem Difficulty in OPE due to unobserved confounders in infinite-horizon RL.
method Two-stage approach: estimating stationary distribution ratios and combining optimal balancing.
result Policy value can be identified from off-policy data with proxies and latent variable model.

The paper analyzes methods for estimating linear functionals from observational data, proving upper bounds and showing optimal procedures.

problem Estimating linear functionals from observational data in causal inference and bandit literature.
method Two-stage procedures that first estimate treatment effect function, then use it to estimate the linear functional.
result Proves non-asymptotic upper bounds on mean-squared error for two-stage procedures and shows instance-dependent optimality.

New method combines value function decomposition and policy gradients for cooperative multi-agent reinforcement learning.

problem Challenges in cooperative multi-agent reinforcement learning, especially credit assignment and large action spaces.
method Decomposed Soft Actor-Critic (mSAC) method with Q network architecture, discrete probabilistic policy, and counterfactual advantage function.
result Significantly outperforms policy-based approach COMA and achieves competitive results with SOTA value-based approach Qmix.

A new multi-agent learning method improves performance in complex games.

problem Performance gap between MAPG and value-based multi-agent approaches.
method Introduces value function decomposition into multi-agent actor-critic framework for off-policy learning.
result DOP significantly outperforms state-of-the-art multi-agent reinforcement learning algorithms.

A new PCR method using SVD with sparse regularization.

problem Lack of response variable information in traditional PCR.
method One-stage SVD approach with two loss functions and sparse regularization.
result Obtains principal component loadings with response variable information.

SPEDER extracts state-action abstraction from dynamics for reinforcement learning.

problem Curse of dimensionality and limited applicability of spectral methods.
method Spectral Decomposition Representation (SPEDER) that extracts state-action abstraction from dynamics without policy dependence.
result Theoretical analysis establishes sample efficiency in online and offline settings.

BCRL learns a Bellman complete representation for offline RL policy evaluation.

problem Learning a Q-function efficiently from offline data.
method BCRL learns a linear Bellman complete representation directly from data, enabling efficient OPE.
result BCRL achieves competitive OPE error and outperforms FQE in certain scenarios.

The study examines how different interpolation methods affect the decomposition of life insurance surplus.

problem The impact of different interpolation methods on the decomposition of life insurance surplus.
method The study uses the IASU decomposition method to analyze the effects of different interpolation methods (Lee-Carter and linear) on the surplus decomposition.
result Lee-Carter and linear interpolation yield almost identical decompositions, while constant approximations result in different decompositions.

NOHD optimizes multi-agent systems by decomposing dynamics into irrotational and solenoidal components.

problem Non-stationarity and conflicting interests in multi-agent learning problems.
method NOHD (Newton Optimization on Helmholtz Decomposition) decomposes system dynamics into irrotational and solenoidal components.
result NOHD ensures quadratic convergence in purely irrotational and solenoidal systems and attracts to stable fixed points in general multi-agent systems.

The paper tackles non-stationary MAB with periodic rewards.

problem Non-stationary mean rewards over time in a business context.
method Combines Fourier analysis with confidence-bound learning to estimate periods and minimize regret.
result Proposes a near-optimal policy with a regret bound of O(Tk=1KTk)O(\sqrt{T\sum_{k=1}^K T_k}).

DFPV improves PCL for confounded bandit policy evaluation.

problem Estimating causal effects in confounded settings with high-dimensional data.
method Deep feature proxy variable method (DFPV) for high-dimensional, nonlinear relationships.
result DFPV outperforms state-of-the-art methods on synthetic benchmarks and confounded bandit problems.

Study on efficient estimation of Gaussian mean with limited communication.

problem Estimating Gaussian mean under communication constraints.
method Decomposition into localization and refinement stages, development of communication-efficient and statistically optimal procedures.
result Established minimax rates of convergence and developed optimal procedures.

Tensor completion estimates missing components by exploiting the low-rank structure of multi-way data. The recently proposed methods based on tensor train (TT) and tensor ring (TR) show better performance in image recovery than classical ones. Compared with TT and TR, the projected entangled pair state (PEPS), which is…

2019-03-12abs ↗pdf ↗

A framework for navigating environments with spatially correlated obstacles and uncertain blockage status.

problem Navigation in environments with spatially correlated obstacles of uncertain blockage status.
method Modeling spatial correlation with Gaussian Random Field, developing Bayesian belief updates, proposing a two-stage learning framework with offline and online phases.
result Consistent performance gains over baselines in environments with adversarial interruptions or clustered natural hazards.

MetaTrader combines diverse expert strategies to optimize portfolio performance.

problem Optimizing portfolio performance in changing financial markets.
method Two-stage RL approach: imitation learning followed by a meta-policy.
result MetaTrader significantly outperforms state-of-the-art baselines in balancing profits and risks.

The study analyzes how neural reward models learn features for policy optimization in a Gaussian single-index model.

problem Reward modeling in policy optimization and its impact on downstream value.
method Two-stage neural reward model: first learns hidden direction, then fits readout layer.
result For any feature-learning temperature above a dimension-free threshold, a constant fraction of neurons recover the hidden direction.

Many advanced Learning from Demonstration (LfD) methods consider the decomposition of complex, real-world tasks into simpler sub-tasks. By reusing the corresponding sub-policies within and between tasks, they provide training data for each policy from different high-level tasks and compose them to perform novel ones. E…

2018-03-02abs ↗pdf ↗

In this paper, we propose a general framework for sparse and low-rank tensor estimation from cubic sketchings. A two-stage non-convex implementation is developed based on sparse tensor decomposition and thresholded gradient descent, which ensures exact recovery in the noiseless case and stable recovery in the noisy cas…

2018-01-29abs ↗pdf ↗