Don't Forget Its Variance! The Minimum Path Variance Principle for Accurate and Stable Score-Based Density Ratio Estimation

• URL: http://arxiv.org/abs/2602.00834v1
• Date: Sat, 31 Jan 2026 17:57:53 GMT
• Title: Don't Forget Its Variance! The Minimum Path Variance Principle for Accurate and Stable Score-Based Density Ratio Estimation
• Abstract summary: We show that tractable training objectives differ from the ideal, ground-truth objective by a crucial, overlooked term: the path variance of the time score.<n>We propose MinPV (textbfMinimum textbfPath textbfVariance) Principle, which introduces a principled performance to minimize the path variance.
• Score: 15.094412534684116
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Score-based methods have emerged as a powerful framework for density ratio estimation (DRE), but they face an important paradox in that, while theoretically path-independent, their practical performance depends critically on the chosen path schedule. We resolve this issue by proving that tractable training objectives differ from the ideal, ground-truth objective by a crucial, overlooked term: the path variance of the time score. To address this, we propose MinPV (\textbf{Min}imum \textbf{P}ath \textbf{V}ariance) Principle, which introduces a principled heuristic to minimize the overlooked path variance. Our key contribution is the derivation of a closed-form expression for the variance, turning an intractable problem into a tractable optimization. By parameterizing the path with a flexible Kumaraswamy Mixture Model, our method learns a data-adaptive, low-variance path without heuristic selection. This principled optimization of the complete objective yields more accurate and stable estimators, establishing new state-of-the-art results on challenging benchmarks.

Related papers

• LambdaPO: A Lambda Style Policy Optimization for Reasoning Language Models [34.349722314481824]
  Group Relative Policy Optimization is prized for its efficacy in foregoing an explicit value-critic.<n>The method's reliance on a monolithic statistical baseline, such as the group mean, collapses the relational topology of the trajectory space into a single scalar.<n>We introduce a novel framework, Lambda Policy Optimization (LambdaPO), that addresses this information-theoretic bottleneck.
  arXiv  Detail & Related papers  (2026-05-19T06:10:24Z)
• Bridging the Gap Between Average and Discounted TD Learning [14.556544278062793]
  We introduce a novel algorithm designed explicitly for policy evaluation in the average-reward setting.<n>Our proposed method overcomes previous limitations by guaranteeing convergence to the unique solution of a properly defined Bellman equation.
  arXiv  Detail & Related papers  (2026-05-03T23:54:36Z)
• From Noisy Traces to Stable Gradients: Bias-Variance Optimized Preference Optimization for Aligning Large Reasoning Models [90.45197506653341]
  Large reasoning models generate intermediate reasoning traces before producing final answers.<n> aligning LRMs with human preferences, a crucial prerequisite for model deployment, remains underexplored.<n>A common workaround optimized a single sampled trajectory, which introduces substantial gradient variance from trace sampling.
  arXiv  Detail & Related papers  (2025-10-06T17:58:01Z)
• Aligning Latent Spaces with Flow Priors [72.24305287508474]
  This paper presents a novel framework for aligning learnable latent spaces to arbitrary target distributions by leveraging flow-based generative models as priors.<n> Notably, the proposed method eliminates computationally expensive likelihood evaluations and avoids ODE solving during optimization.
  arXiv  Detail & Related papers  (2025-06-05T16:59:53Z)
• Contextual Optimization under Covariate Shift: A Robust Approach by Intersecting Wasserstein Balls [18.047245099229325]
  We propose a novel approach called Intersection Wasserstein-balls DRO (IW-DRO)<n>IW-DRO integrates multiple estimation methods into the distributionally robust optimization framework.<n>We show that IW-DRO achieves superior performance compared to single Wasserstein-ball DRO models.
  arXiv  Detail & Related papers  (2024-06-04T15:46:41Z)
• Optimal Baseline Corrections for Off-Policy Contextual Bandits [61.740094604552475]
  We aim to learn decision policies that optimize an unbiased offline estimate of an online reward metric. We propose a single framework built on their equivalence in learning scenarios. Our framework enables us to characterize the variance-optimal unbiased estimator and provide a closed-form solution for it.
  arXiv  Detail & Related papers  (2024-05-09T12:52:22Z)
• Nearest Neighbor Sampling for Covariate Shift Adaptation [7.940293148084844]
  We propose a new covariate shift adaptation method which avoids estimating the weights. The basic idea is to directly work on unlabeled target data, labeled according to the $k$-nearest neighbors in the source dataset. Our experiments show that it achieves drastic reduction in the running time with remarkable accuracy.
  arXiv  Detail & Related papers  (2023-12-15T17:28:09Z)
• A unified algorithm framework for mean-variance optimization in discounted Markov decision processes [7.510742715895749]
  This paper studies the risk-averse mean-variance optimization in infinite-horizon discounted Markov decision processes (MDPs) We introduce a pseudo mean to transform the untreatable MDP to a standard one with a redefined reward function in standard form. We propose a unified algorithm framework with a bilevel optimization structure for the discounted mean-variance optimization.
  arXiv  Detail & Related papers  (2022-01-15T02:19:56Z)
• Learning to Estimate Without Bias [57.82628598276623]
  Gauss theorem states that the weighted least squares estimator is a linear minimum variance unbiased estimation (MVUE) in linear models. In this paper, we take a first step towards extending this result to non linear settings via deep learning with bias constraints. A second motivation to BCE is in applications where multiple estimates of the same unknown are averaged for improved performance.
  arXiv  Detail & Related papers  (2021-10-24T10:23:51Z)
• Estimation of Local Average Treatment Effect by Data Combination [3.655021726150368]
  It is important to estimate the local average treatment effect (LATE) when compliance with a treatment assignment is incomplete. Previously proposed methods for LATE estimation required all relevant variables to be jointly observed in a single dataset. We propose a weighted least squares estimator that enables simpler model selection by avoiding the minimax objective formulation.
  arXiv  Detail & Related papers  (2021-09-11T03:51:48Z)
• Variational Refinement for Importance Sampling Using the Forward Kullback-Leibler Divergence [77.06203118175335]
  Variational Inference (VI) is a popular alternative to exact sampling in Bayesian inference. Importance sampling (IS) is often used to fine-tune and de-bias the estimates of approximate Bayesian inference procedures. We propose a novel combination of optimization and sampling techniques for approximate Bayesian inference.
  arXiv  Detail & Related papers  (2021-06-30T11:00:24Z)
• KL Guided Domain Adaptation [88.19298405363452]
  Domain adaptation is an important problem and often needed for real-world applications. A common approach in the domain adaptation literature is to learn a representation of the input that has the same distributions over the source and the target domain. We show that with a probabilistic representation network, the KL term can be estimated efficiently via minibatch samples.
  arXiv  Detail & Related papers  (2021-06-14T22:24:23Z)
• Risk-Sensitive Markov Decision Processes with Combined Metrics of Mean and Variance [3.062772835338966]
  This paper investigates the optimization problem of an infinite stage discrete time Markov decision process (MDP) with a long-run average metric. A performance difference formula is derived and it can quantify the difference of the mean-variance combined metrics of MDPs under any two different policies. A necessary condition of the optimal policy and the optimality of deterministic policies are derived.
  arXiv  Detail & Related papers  (2020-08-09T10:35:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.