Importance Sampling

Follow this topic Ask about this topic

Importance sampling studies how to estimate expectations, probabilities, or gradients under a target distribution by drawing samples from another distribution and correcting them with weights. Adaptive and defensive proposals, sequential Monte Carlo, and self-normalized or tempered weights are used in settings ranging from rare-event estimation and Bayesian inference to off-policy evaluation and language-model policy optimization. Applications include estimating rare failures, reweighting data under distribution shift, and making learning or inference more computationally efficient. A central tension is that better correction can reduce bias but high-variance weights destabilize estimates, so current work develops clipping, calibration, effective-sample-size diagnostics, and guarantees for when reweighting is reliable.

Latest papers

74 papers22 papers in the last four weeks, up 340% on the four weeks before. 0.1% of all new papers.

Numerical Integration on Bounded Domains via Learned Reflected Diffusions
Oct 29, 2026Kirill Korolev, Artur Goldman, Timofei Gritsaev +2Numerical Integration Importance Sampling
HSE University · ETH Zürich, ETH AI Center · Constructor University
Multiple Importance Sampling for Guided Speculative Inference
Oct 23, 2026Joseph Rowan, Ashish J. KhistiLLM Inference Acceleration Inference-Time Guidance
Department of Electrical and Computer Engineering, University of Toronto
Asynchronous, Generation-Free ABC: Streaming AMIS Reweighting for Heterogeneous Simulator Workloads on HPC
Oct 21, 2026Julian Herold, Markus Götz, Alexander SchugSimulation-Based Inference Posterior Sampling
Scientific Computing Center, Karlsruhe Institute of Technology, Karlsruhe, Germany
ART-MPG: Autoregressive R/T Manifold Path Guiding
Oct 21, 2026Zehao Zhao, Yanyang Yang, Xiaole Zhang +1Physically Based Rendering Importance Sampling
Ming Hsieh Department of Electrical and Computer Engineering, University of Southern California · Computational Science and Engineering, Georgia Institute of Technology · Department of Electrical and Computer Engineering, Carnegie Mellon University
Stratified Sparse Attention: Reducing the Sparse-to-Dense Gap at Extreme Sparsity
Oct 20, 2026Sahil Joshi, Prithvi Dixit, Aryan Katiyar +5Sparse Attention Long-Context Language Model Inference
Department of Computer Science, Rice University, TX, USA. · Department of Electrical Engineering and Computer Sciences, UC Berkeley, CA, USA. · Department of Computer Science, Stanford University, CA, USA. +1
Baselines and Score Centering in Policy Gradient Estimation
Oct 15, 2026Shuo Han, Ziqing HuPolicy Gradient Policy Gradient Methods
University of Illinois Chicago · Perplexity AI
Enabling Token-wise Importance Sampling in Off-Policy RLVR with Proximal KL Regularization
Oct 13, 2026Hao Bai, Jiarui Yao, Tong ZhangOff-Policy RL Reinforcement Learning with Verifiable Rewards
University of Illinois Urbana-Champaign
Amortised adaptive importance sampling
Oct 12, 2026Arran Carter, Víctor Elvira, Esmeralda S. WhitammerImportance Sampling Adaptive Sampling
University of Edinburgh
ML-CLAPPS: A Probabilistic Framework for Imbalanced Multilabel Learning under Class Prioritization
Oct 11, 2026Priel Hazan, Nir Almog, Noam Keidar +2Multi-Label Classification Class-Imbalanced Learning
Technion – Israel Institute of Technology, Haifa, Israel
Target-ESS Tempered Policy Optimization (TETPO): Smooth Variance Control via Bridge Importance Sampling
Oct 10, 2026Shayan Mohajer Hamidi, Kayhan Behdin, Wenhui Zhu +4RL for Language Models RL Post-Training
LinkedIn
Universal Bounds for Self-Normalized Kullback-Leibler Estimation
Oct 9, 2026Buu Phan, Lester Mackey, David Alvarez-MelisKullback-Leibler Divergence Importance Sampling
University of Toronto · Microsoft Research · Harvard University
Sampling SU(N) gauge theory on a 2D lattice from independent plaquettes via holonomies and corner reweighting
Oct 6, 2026Javad KomijaniLattice Field Theory High-Energy Physics
Steering Diffusion Models to Rare Events with Sequential Monte Carlo
Oct 6, 2026Aavash Subedi, Tim Reichelt, Christopher Williams +3Diffusion Model Sampling Importance Sampling
Department of Statistics, University of Oxford · Department of Physics, University of Oxford · Department of Statistics, University of British Columbia
Robust Importance Sampling for Rare Events via Constrained Gaussian Mixtures
Oct 5, 2026Paweł Lorek, Rafał Nowak, Rafał Topolnicki +2Gaussian Mixture Models Importance Sampling
University of Wrocław · Tooploox · TRAILS University of Warsaw +3
Risk-Calibrated Proposal Transport for Finite-Particle Diffusion Steering
Oct 3, 2026Ziseok Lee, Jaehyeon Kim, Seungwon Kim +6Inference-Time Guidance Importance Sampling
Seoul National University · Asteromorph
Sample complexity of variance-reduced policy gradient: weaker assumptions and lower bounds
Oct 2, 2026Gabor Paczolay, Matteo Papini, Alberto Maria Metelli +2Policy Gradient Policy Gradient Methods
Politecnico di Milano. · Budapest University of Technology and Economics. · University of Milan.
Probe the Harness: Setup Checks for Stale-Data RL Comparisons in Language Models
Oct 2, 2026Taiheng PanRL for Language Models Importance Sampling
The University of Melbourne
Efficient Neural Field Learning via Adaptive Coverage and Focused Sampling
Oct 1, 2026Guang Zhao, Xihaier Luo, Huan-Hsin Tseng +4Adaptive Sampling Implicit Neural Representations
Computing and Data Sciences, Brookhaven National Laboratory Upton, NY 11973, USA
Free Everywhere, Exact on Trees: PPO's Dropped Correction Buys Sample Efficiency Under Aggressive Reuse
Sep 30, 2026Nima H. SiboniImportance Sampling Proximal Policy Optimization
Juna.ai, Kastanienallee 32, 10435 Berlin, Germany
Search Shapes Conclusions: Auditing Evidence Selection Bias in Deep Research Agents
Sep 30, 2026Shuyao Xiao, Shengling Wang, Xuan Chen +8Causal Effect Estimation Deep Research Agents
Beijing Normal University · Ke Holdings
The Advantages of Fresh Sketching for Ridge Regression
Sep 29, 2026Linkai Ma, Qilin Li, Petros DrineasImportance Sampling Randomized Sketching
Purdue University · University of Wisconsin-Madison
Cool the Sampler, Not the Learner: Sampling Temperature Moves the Staleness Cliff of Importance-Corrected GRPO
Sep 29, 2026Taiheng PanRL for Language Models Reinforcement Learning
The University of Melbourne
One Proposal for Every Margin: Zero-Shot Amortized Sequential Importance Sampling for Binary Matrices
Sep 28, 2026Ruishuo Chen, Weijia Li, Xun Wang +3Importance Sampling Generative Flow Networks
Institute for Interdisciplinary Information Sciences, Tsinghua University · Department of Statistics and Data Science, Tsinghua University
Rethinking Training-Inference Mismatch in LLM Reinforcement Learning: Where It Arises and How to Correct It
Sep 26, 2026Tianrun Yu, Kaixiang Zhao, Shangzhe Li +4Reinforcement Learning RL for Language Model Reasoning
Brigham Young University · University of North Carolina at Chapel Hill
Bridging Stochastic Flow Maps and Boltzmann Generators with Normalizing Flows
Sep 25, 2026Louis Grenioux, RuiKang OuYang, Luhuan WuBoltzmann Sampling Molecular Generation
Center for Computational Mathematics, Flatiron Institute, New York, NY, USA · Department of Engineering, University of Cambridge, Cambridge, UK · Department of Applied Mathematics and Statistics, Johns Hopkins University, Baltimore, MD, USA
Learning to Bias: Machine Learning-Enhanced Particle Filters
Sep 24, 2026Apoorv Srivastava, Eric DarveParticle Filtering Bayesian Filtering
Stanford University Stanford, CA 94305
Scalable Subgraph Sampling via Resistance Curvature
Sep 23, 2026Chaoqun Fei, Tinglve Zhou, Tianyong Hao +1Graph Neural Networks Importance Sampling
School of Artificial Intelligence, South China Normal University · School of Computer Science, South China Normal University · Academy of Mathematics and Systems Science, Chinese Academy of Sciences
Rare Event Estimation via Iterative Unalignment
Sep 21, 2026Hanming Yang, Daksh Mittal, Jing Dong +1Importance Sampling LLM Safety
Decision, Risk, and Operations Division, Columbia Business School
Bellman Calibration for Marginalized Importance Weighting in Offline Reinforcement Learning
Aug 25, 2026Lars van der Laan, Nathan KallusOff-Policy Evaluation Offline RL
Stanford University · Netflix and Cornell University
RAPID: Reliability-Aware Pair Importance Distillation
Aug 23, 2026Ali Mahdavi, Azadeh Zamanifar, Amirfarhad Farhadi +1Relational Knowledge Distillation Importance Sampling
Department of Computer Engineering SRC, Islamic Azad University Tehran, Iran · School of Computer Engineering Iran University of Science and Technology Tehran, Iran · Meta CA, USA

Oct 29, 2026J/K move · Enter open · S save

Numerical Integration on Bounded Domains via Learned Reflected Diffusions

Kirill Korolev, Artur Goldman, Timofei Gritsaev, Tigran Ramazyan+1

HSE University · ETH Zürich, ETH AI Center · Constructor University

Numerical Integration Importance Sampling Diffusion Models Constrained Sampling

Open paper AskPDF arXiv

We study high-dimensional integration on bounded convex domains. Given a non-negative integrand

r

, the goal is to estimate

Z=\int_{D}r(x)\,\mathrm dx

D\subset\mathbb R^d

. Standard Quasi-Monte Carlo does not adapt its evaluation points to the integrand, while effective importance sampling requires a proposal that captures its concentration. Learned diffusion samplers can supply such a proposal, but existing methods are formulated on

\mathbb R^d

and do not respect the domain constraint

x\in D

. We instead build the proposal from reflected dynamics that stay in

D

by construction. A reflected diffusion progressively transforms the target distribution toward the uniform distribution on

D

, and a neural score model is trained to reverse this process. A change-of-measure formula for reflected diffusions yields a training objective without additional boundary terms and an unbiased importance-sampling estimator of

Z

. For non-smooth integrands, where reparameterization gradients may be undefined or uninformative, we derive a REINFORCE estimator of the training gradient using Gaussian proposal densities before reflection, without evaluating reflected transition densities or differentiating

r

. We evaluate on numerous synthetic targets and real-world problems, demonstrating strong performance of the proposed method, as well as favorable scaling with the dimension of the problem and the number of points used for the Monte Carlo estimate.