The paper proposes biased advantage estimates for reinforcement learning, improving efficiency and performance.
problem Estimating advantages in reinforcement learning algorithms.
method A family of estimates based on order statistics over the path ensemble.
result Biased estimates can significantly benefit reinforcement learning, especially in environments with sparse rewards or critical actions.
Bayesian estimators for causal inference using hierarchical Gaussian Processes.
problem Estimating causal effects in sharp and fuzzy RD/RK designs.
method Hierarchical Gaussian Process models for regression and classification.
result Hierarchical GP models improve precision and coverage of RD/RK estimations.
Quantum algorithms accelerate financial risk computation.
problem Accelerating the computation of financial market risk.
method Quantum gradient estimation algorithms for market sensitivities.
result Significant reduction in resource requirements for financial quantum advantage.
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.
Quantum advantage in derivative pricing requires 8k qubits and 54M T-depth.
problem Quantum advantage in pricing derivatives.
method Re-parameterization method combining pre-trained variational circuits and fault-tolerant quantum computing.
result Benchmark use cases require 8k logical qubits and a T-depth of 54 million.
Paper introduces DTAE to optimize RL algorithms, balancing exploration and exploitation.
problem Balancing exploration and exploitation in reinforcement learning.
method Soft policy optimization with entropy and dual-track advantage estimator (DTAE).
result DTAE accelerates RL algorithm convergence and improves performance.
Deep neural networks outperform other methods in estimating non-smooth functions with singularities.
problem Estimating functions with singularities on hypersurfaces.
method Developed a minimax rate analysis for DNNs, proving their almost optimal convergence rate.
result DNNs outperform other estimators in estimating non-smooth functions with singularities.
New method learns time-varying home field advantage in football.
problem Discovering causal factors behind home field advantage in sports.
method DYNAMO: a novel causal discovery method for non-stationary processes.
result Time-varying home field advantages influenced by referee bias.
Quantum algorithms improve VaR and CVaR estimation for financial derivatives.
problem Quantum advantage in financial risk analysis of derivatives.
method Two quantum algorithms: QSP and QSP-based approach.
result QSP-based approach requires fewer quantum resources for the same accuracy.
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…
We present a method to derive local estimates for some classes of fully nonlinear elliptic equations. The advantage of our method is that we derive Hessian estimates directly from C0 estimates. Also, the method is flexible and can be applied to a large class of equations.
The problem of estimating the number of sources and their angles of arrival from a single antenna array observation has been an active area of research in the signal processing community for the last few decades. When the number of sources is large, the maximum likelihood estimator is intractable due to its very high c…
Develops a method to efficiently use offline data for RL policy optimization.
problem Lack of online data for offline RL in mobile health applications.
method Advantage learning framework using optimal Q-estimators.
result New policy converges faster than existing methods.
Proposes a new simulator for complex arrival processes.
problem Modeling and simulating complex arrival processes with non-stationary and multi-dimensional rates.
method Integrates Monte Carlo and GANs to model a broad class of arrival processes.
result Consistent and efficient estimation of the simulator using Wasserstein distance.
We propose a simple method that combines neural networks and Gaussian processes. The proposed method can estimate the uncertainty of outputs and flexibly adjust target functions where training data exist, which are advantages of Gaussian processes. The proposed method can also achieve high generalization performance fo…
After presenting Actor Critic Methods (ACM), we show ACM are control variate estimators. Using the projection theorem, we prove that the Q and Advantage Actor Critic (A2C) methods are optimal in the sense of the L2 norm for the control variate estimators spanned by functions conditioned by the current state and acti…
Policy optimization on high-dimensional continuous control tasks exhibits its difficulty caused by the large variance of the policy gradient estimators. We present the action subspace dependent gradient (ASDG) estimator which incorporates the Rao-Blackwell theorem (RB) and Control Variates (CV) into a unified framework…
TROLL improves RL for LLMs by replacing clipping with a trust region projection.
problem Clipping in RL for LLMs causes instability and suboptimal performance.
method TROLL uses a discrete differentiable trust region projection to replace clipping, balancing computational cost and effectiveness.
result TROLL consistently outperforms PPO-like clipping in training speed, stability, and final success rates.
High-dimensional sparse modeling via regularization provides a powerful tool for analyzing large-scale data sets and obtaining meaningful, interpretable models. The use of nonconvex penalty functions shows advantage in selecting important features in high dimensions, but the global optimality of such methods still dema…
Fragmented exchanges arise due to speed advantages in high-activity regions.
problem Fragmentation of distributed securities exchanges due to speed advantages in high-activity regions.
method Economic model and Monte Carlo simulations of a decentralized exchange with two miner clusters.
result Speed advantage increases with infrastructure asymmetry between regions.
Paper reduces variance in infinite horizon off-policy evaluation with bias reduction.
problem High variance in infinite horizon off-policy evaluation.
method Doubly robust augmentation of Liu et al. (2018a) method using learned value function.
result Significant reduction in bias with higher accuracy when either density ratio or value function is accurate.
Entrocraft addresses RL performance saturation in LLMs by customizing entropy curves.
problem Performance saturation in RL algorithms for LLMs.
method Entrocraft uses rejection sampling to bias advantage distributions for customized entropy schedules.
result Entrocraft significantly improves generalization, output diversity, and long-term training in 4B models.
New federated method preserves privacy and estimates treatment effects.
problem Privacy-preserving causal inference for multi-site studies.
method Multiply robust nuisance function estimation, transfer learning.
result Efficient and optimal treatment effect estimation under different scenarios.
The estimation of normalizing constants is a fundamental step in probabilistic model comparison. Sequential Monte Carlo methods may be used for this task and have the advantage of being inherently parallelizable. However, the standard choice of using a fixed number of particles at each iteration is suboptimal because s…
Quantum method speeds up risk estimation for insurance tail risks.
problem Sample-sparsity in classical Monte Carlo methods for tail risk pricing.
method Quantum Amplitude Estimation (QAE) with Grover amplification.
result Quantum method achieves convergence approaching order reciprocal N, enabling high-resolution tail estimation within practical budgets.
GANICE improves GAN-based causal inference by minimizing averaged Wasserstein risk.
problem Estimating interventional outcome distributions and quantiles in causal inference.
method GANICE uses extended Wasserstein distance and a cellwise critic to minimize averaged Wasserstein risk.
result GANICE achieves minimax optimality and consistently outperforms existing methods.
The scalability of statistical estimators is of increasing importance in modern applications. One approach to implementing scalable algorithms is to compress data into a low dimensional latent space using dimension reduction methods. In this paper we develop an approach for dimension reduction that exploits the assumpt…
We study the problem of finding the most mutually correlated arms among many arms. We show that adaptive arms sampling strategies can have significant advantages over the non-adaptive uniform sampling strategy. Our proposed algorithms rely on a novel correlation estimator. The use of this accurate estimator allows us t…
We propose and analyze estimators for statistical functionals of one or more distributions under nonparametric assumptions. Our estimators are based on the theory of influence functions, which appear in the semiparametric statistics literature. We show that estimators based either on data-splitting or a leave-one-out t…
In this work, we present direction-of-arrival (DoA) estimation algorithms based on the Krylov subspace that effectively exploit prior knowledge of the signals that impinge on a sensor array. The proposed multi-step knowledge-aided iterative conjugate gradient (CG) (MS-KAI-CG) algorithms perform subtraction of the unwan…
New proof for stability estimates in complex equations without pluripotential theory.
problem Stability estimates for complex Monge-Ampère and Hessian equations.
method New proof using general degenerations of background metrics.
result Uniform stability estimates for both equations under various degenerations.
The authors propose a parametric model called the arena model for prediction in paired competitions, i.e. paired comparisons with eliminations and bifurcations. The arena model has a number of appealing advantages. First, it predicts the results of competitions without rating many individuals. Second, it takes full adv…
New method estimates mutual information using normalizing flows.
problem Mutual information estimation in high-dimensional data.
method Normalizing flows to map data to target distributions with known MI.
result Theoretical guarantees and practical advantages demonstrated.
New approach optimizes policies in adversarial MDPs using adversarial learning.
problem Optimizing policies in adversarial Markov decision processes.
method Adversarial learning on advantage functions, extending previous reductions.
result Stronger regret criteria and performance guarantees for policy optimization.
New estimator improves mutual information estimation.
problem Estimating mutual information in data science and machine learning.
method Proposes a new estimator that uses a preliminary estimate of the data distribution.
result A preliminary estimate helps in estimating mutual information more accurately.
We propose an estimation method for the conditional mode when the conditioning variable is high-dimensional. In the proposed method, we first estimate the conditional density by solving quantile regressions multiple times. We then estimate the conditional mode by finding the maximum of the estimated conditional density…
Estimates time-varying parameters from two OLS estimates.
problem Time-varying linear regression with hidden dynamics.
method Combines two OLS estimates for stable linear dynamics.
result Finite sample guarantee on estimation error.
DRL agents perform poorly at high decision frequencies, but a new algorithm improves performance.
problem DRL agents struggle at high decision frequencies, leading to poor performance.
method Proved that DRL agents' action-conditioned return distributions collapse to their policy's return distribution as decision frequency increases. Defined superiority as a probabilistic generalization of advantage for high-frequency value-based RL.
result Proper modeling of superiority distribution improves performance of controllers at high decision frequencies.
Bayesian SAE model with spectral clustering and uncertainty quantification.
problem Small Area Estimation (SAE) with uncertainty quantification.
method Spectral clustering with external covariates, posterior projections, and CPMSE.
result Closed form expressions for posterior mean estimators and CPMSE.
New model learning objective improves continuous control tasks.
problem Challenges in solving continuous control tasks using model-based reinforcement learning.
method Derived a novel value-aware model learning objective and identified and addressed stale value estimates issue.
result Value-aware objectives can be successfully deployed in solving continuous control tasks without tuning hyper-parameters.
Paper develops a new estimator for high-dimensional panel data with common shocks.
problem Cross-sectionally dependent errors driven by common shocks in high-dimensional panel data.
method Factor-augmented sparse-group LASSO estimator combining MIDAS aggregation with latent factors.
result The estimator outperforms standard LASSO for prediction and estimation in settings with cross-sectional dependence.
A new DDPM for link prediction using sub-graph likelihood estimation.
problem Link prediction in graph domains.
method Sub-graph based diffusion model with DDPMs, decomposing likelihood estimation.
result Our model achieves superior performance in link prediction across various datasets.
Deep learning solves and estimates complex financial models.
problem Estimating and solving continuous-time financial models.
method Uses deep learning to solve and estimate models simultaneously.
result Demonstrates advantages like generality and large state space handling.
We extend CS divergence to conditional distributions and show its advantages in time series data and sequential decision making.
problem Quantifying the closeness between conditional distributions.
method Developed and estimated a conditional Cauchy-Schwarz divergence using kernel density estimation.
result Conditional CS divergence outperforms previous methods in time series clustering and sequential decision making.
Uniform bounds for complex equations using Monge-Ampère method.
problem Bounding solutions to complex equations.
method Auxiliary Monge-Ampère equation method.
result Uniform bounds remain valid even as background metrics degenerate.
New method tightens variational representations of divergences for faster learning.
problem Improving tightness of variational representations of divergences for faster statistical estimation.
method Improved objective functionals constructed via an auxiliary optimization problem, leveraging neural network approximation.
result Tighter variational representations can result in significantly faster learning and more accurate estimation of divergences.
Develops a novel fast bootstrap for dependent data with higher-order accuracy.
problem Estimation of parametric and semi-parametric models for dependent data.
method i.i.d. resampling of smoothed moment indicators, asymptotic refinements under mild assumptions.
result Higher-order correct asymptotic confidence distributions and confidence intervals.
SALT models combine ARHMM and SLDS for efficient, interpretable time-series analysis.
problem Efficient modeling of systems with time-varying dynamics and long-range dependencies.
method Switching autoregressive low-rank tensor models parameterized with a low-rank factorization.
result SALT models provide a balance of interpretability and efficiency, outperforming ARHMMs and SLDSs.