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

25.0%50.0%75.0%100.0% · Dec 199219922001200920172026
48 results for optimal value estimation

Policy evaluation is a key process in reinforcement learning. It assesses a given policy using estimation of the corresponding value function. When using a parameterized function to approximate the value, it is common to optimize the set of parameters by minimizing the sum of squared Bellman Temporal Differences errors…

2019-01-23abs ↗pdf ↗

New method estimates minimizer and minimum value of a regression function.

problem Estimating minimizer and minimum value of a regression function from noisy data.
method Projected gradient descent with gradient estimated by regularized local polynomial algorithm, followed by a rate optimal nonparametric procedure.
result Achieves minimax optimal rates of convergence for smooth and strongly convex functions.

Randomized trials, also known as A/B tests, are used to select between two policies: a control and a treatment. Given a corresponding set of features, we can ideally learn an optimized policy P that maps the A/B test data features to action space and optimizes reward. However, although A/B testing provides an unbiased …

2018-06-07abs ↗pdf ↗

New method estimates optimal Q-values with better accuracy for specific problems.

problem Estimating optimal Q-values in reinforcement learning is difficult and varies by problem instance.
method Local minimax framework and variance-reduced Q-learning.
result Sharp lower bounds on estimation accuracy for Q-learning.

This work improves diffusion models by estimating the optimal loss value for better training diagnostics.

problem The optimal loss value of diffusion models is unknown and not indicative of absolute data-fitting quality.
method Derive the optimal loss in closed form and develop effective estimators, including a stochastic variant.
result Unlocking the optimal loss as a metric for diagnosing training quality of diffusion models.

Optimizes bond portfolios to avoid worst-case losses.

problem Finding the worst-case value of a bond portfolio over a range of yield curves and spreads.
method Solves a convex-concave saddle point optimization problem to find the worst-case value and construct a robust portfolio.
result Constructs a bond portfolio that includes the worst-case value, ensuring robustness against market uncertainties.

Estimates personalized treatment response curves using covariates.

problem Flexible estimation of personalized treatment response curves.
method Sieve based nonparametric estimator of smoothed regimen-response curve function.
result Asymptotic linearity and undersmoothing criteria for efficient estimation.

New methods estimate transport-growth pairs in unbalanced optimal transport.

problem Statistical guarantees for Monge-type estimation in unbalanced optimal transport remain limited.
method Developed two estimators for transport-growth pairs under different setups.
result Achieved minimax optimal rate for estimation of transport-growth pairs.

New method estimates optimal personalized treatment rules from mixed data sources.

problem Combining RCT and observational data for personalized treatment rules.
method Doubly robust estimator for value function, maximizing within pre-specified ITR class.
result Consistent and asymptotically normal optimal value estimator with N1/3N^{-1/3} rate of convergence.

Optimizes information acquisition to reduce estimation risk and maximize utility.

problem Estimation risk in investor decision-making.
method Derives closed-form value functions using CARA and CRRA utility functions, employs variational methods to explore optimal acquisition.
result Acquiring information earlier is more valuable in reducing estimation risk and achieving higher utility.

BASIS improves LLM reasoning by sharing batchwise rollout info, reducing MSE by 69%.

problem Improving large language model reasoning with limited rollouts and batch information.
method BASIS samples only one rollout per prompt but uses batch information to improve value function estimation.
result BASIS reduces MSE in value function estimation by 69% compared to REINFORCE++.

In traditional reinforcement learning, an agent maximizes the reward collected during its interaction with the environment by approximating the optimal policy through the estimation of value functions. Typically, given a state s and action a, the corresponding value is the expected discounted sum of rewards. The optima…

2018-06-10abs ↗pdf ↗

New RL algorithm achieves nearly optimal performance for linear MDPs.

problem Optimal reinforcement learning for episodic linear MDPs.
method Weighted linear regression with variance estimator and rare-switching policy.
result Achieves nearly minimax optimal regret ildeO(dH3K) ilde O(d\sqrt{H^3K}).

The paper tackles estimating optimal policy value in linear bandits with general context distributions.

problem Estimating the optimal policy value in linear bandits with general context distributions.
method The paper provides lower bounds and an algorithm for sublinear estimation of VV^* under stronger assumptions.
result A practical algorithm that estimates a problem-dependent upper bound on VV^* with O~(d)\widetilde{\mathcal{O}}(\sqrt{d}) samples.

Develops a new method for statistical optimal allocation problems.

problem Statistical optimal allocation problems with constraints.
method Functional differentiability approach and Hadamard differentiability of value functions.
result Validates margin assumption for fast convergence rate of plug-in methods.

Bayesian optimization improves Monte-Carlo tree search for better state value estimation.

problem Slow convergence in Monte-Carlo tree search due to averaging in backpropagation.
method Softmax MCTS and Monotone MCTS, using Bayesian optimization with Gaussian process prior.
result Our framework outperforms previous methods in computer Go.

A low rank matrix X has been contaminated by uniformly distributed noise, missing values, outliers and corrupt entries. Reconstruction of X from the singular values and singular vectors of the contaminated matrix Y is a key problem in machine learning, computer vision and data science. In this paper we show that common…

2017-10-26abs ↗pdf ↗

New methods for evaluating and optimizing policies in offline RL with unobserved confounders.

problem Evaluating and optimizing policies in the presence of unobserved confounders.
method Characterized settings and algorithms for consistent value estimates and lower bounds, with sample complexity guarantees.
result Proved local convergence guarantees for offline policy improvement.

A new estimator for evaluating policies in unknown environments.

problem Evaluating policies when both logging policy and value function are unknown.
method Doubly-Robust (DR) off-policy evaluation (OPE) estimator, DRUnknown, that estimates both the logging policy and value function.
result DRUnknown achieves the smallest asymptotic variance and is optimal when both models are correctly specified.

Model-free reinforcement learning methods such as the Proximal Policy Optimization algorithm (PPO) have successfully applied in complex decision-making problems such as Atari games. However, these methods suffer from high variances and high sample complexity. On the other hand, model-based reinforcement learning method…

2018-11-18abs ↗pdf ↗

New method for estimating value of optimal policies in uncertain scenarios.

problem Inference for optimal policies when they are non-unique or nearly deterministic.
method Semiparametric efficiency bound, uniformly weighted estimator, NSAVE method.
result Proposes NSAVE method for robust inference in uncertain optimal policies.

Paper introduces a new value function for state transitions and optimal policy learning.

problem Learning optimal policies from state transitions and actions.
method Develops a forward dynamics model to maximize a novel value function Q(s,s)Q(s, s').
result Demonstrates benefits in value function transfer, redundant action spaces, and off-policy learning.

POWSS simplifies Q-value estimation in POMDPs with continuous observations.

problem Lack of theoretical justification for online sampling-based algorithms in POMDPs with continuous observation spaces.
method Developed POWSS, a simplified algorithm that estimates Q-values accurately with high probability and can approach optimality with increased computational power.
result POWSS provides formal theoretical guarantees for Q-value estimation in POMDPs with continuous observations.

A new method improves policy evaluation in RL by tracking value uncertainties.

problem Limitations in existing policy evaluation methods for deep RL tasks.
method KOVA (Kalman Optimization for Value Approximation) based on extended Kalman filter.
result KOVA minimizes a regularized objective function that considers parameter and noisy return uncertainties.

Paper tackles RL with continuous actions and unmeasured confounders.

problem Offline policy learning with continuous actions and unmeasured confounders.
method Developed a novel identification result and a minimax estimator for nonparametric policy value estimation.
result Introduced a policy-gradient-based algorithm to identify the optimal policy.

New algorithms minimize regret in repeated auctions by estimating values and optimizing bids.

problem Minimizing regret in repeated first-price auctions with limited feedback.
method Incorporates causal inference to estimate private values and optimize bidding strategies under different feedback types.
result Achieves near-optimal regret bounds for both full and binary feedback types.

New methods estimate policy value and gradients for deterministic policies from off-policy data.

problem Estimating policy value and gradients for deterministic policies from off-policy data.
method Proposed new doubly robust estimators based on kernelization approaches.
result Demonstrated a rate independent of horizon length for policy value and gradient estimation.

The paper develops methods to estimate value functions in reinforcement learning for infinite horizon problems.

problem Constructing confidence intervals for value functions in infinite horizon reinforcement learning.
method Modeling the Q-function using series/sieve method and recursively updating the policy using SAVE method.
result The proposed CI achieves nominal coverage even when the optimal policy is not unique.

Sparse reduced-rank regression selects variables and ranks via manifold optimization.

problem Traditional rank selection fails when true rank is high.
method Sparse regularization and manifold optimization for rank and variable selection.
result Accurate estimation of coefficient parameter with high true rank.

An online decision-making algorithm using stochastic gradient descent for big data.

problem Efficiently updating decision rules in online decision making with big data.
method Stochastic gradient descent for online updates, asymptotic normality of estimators.
result Asymptotic normality of parameter and value estimators, enabling statistical inference.

This article introduces a framework to estimate the value of evidence-based decision making.

problem Lack of empirical tools to assess the value of evidence-based decision making and optimize statistical precision.
method Empirical framework using parametric and nonparametric empirical Bayes methods.
result The value of statistical evidence depends on how organizations translate it into policy decisions.

Iterative procedures for parameter estimation based on stochastic gradient descent allow the estimation to scale to massive data sets. However, in both theory and practice, they suffer from numerical instability. Moreover, they are statistically inefficient as estimators of the true parameter value. To address these tw…

2015-05-10abs ↗pdf ↗