Variance

Follow this topic Ask about this topic

Recent momentum

-57%

3 papers in the last 28 days · 0.1% of indexed attention

Twelve weeks of publication activity for this topic as it is defined today.

Weekly history

Recent digests

What was published in this topic, kept on the site without email delivery.

Period ending 2026-09-14

1 new paper

A weekly snapshot of new work published in Variance.

Period ending 2026-09-07

2 new papers

A weekly snapshot of new work published in Variance.

84 papers

Latest in Variance

Open your feed →

Oracle Complexity of Stochastic Fixed-Point Equations with Nonexpansive Maps
Sep 8, 2026Jelena Diakonikolas, Cristóbal Guzmán, David Martínez-RubioFixed-Point Iteration Optimal Sample Complexity
Posterior Tempering Explains Variance Inflation in Linear and Generalized Linear Thompson Sampling
Sep 2, 2026Prateek Jaiswal, Debdeep Pati, Anirban Bhattacharya +1Thompson Sampling Generalized Linear Bandit
Generative Diffusion Surrogates with Analytical Variance Schedule
Sep 1, 2026Patrick Reichherzer, Gianluca Gregori, David N. Hosking +1Diffusion Models Plasma Shape Control
Deployment Decision Reliability: A Generalizability-Theory Framework for Sizing Long-Horizon Agent Evaluations
Aug 11, 2026Vasundra SrinivasanReliability Leaderboard
Design Choices That Matter: A Functional ANOVA Analysis for Remote Sensing Multi-Label Classification
Aug 5, 2026Maryam Gholami Shiri, Eva Tuba, Sašo Džeroski +2Multi-Label Classification Remote Sensing
QASP: Query-Adaptive Robust Vector Search Policy
Jul 31, 2026Hakan Ferhatosmanoglu, Kushal Kumar, Tal Wagner +1Vector Database Conflict-Based Search
Who Wins Where? Conformal Model Comparison for Local Superiority
Jul 31, 2026Yi Zhou, Baishi Li, Xuan Yao +1Conformal Inference Comparison
Understanding Submodular Information Measure Based Objectives for Representation Learning: A Variance and Separation Perspective
Jul 30, 2026Rishabh Iyer, Truong Pham, Anay MajeeMutual Information Submodular Maximization
Dimensionality and Measurement Precision in HLE's Multiple-Choice Subset
Jul 29, 2026Mayank Sharma, Savira Nadela, Tyler MattesonHumanity Precision
Aggregate in the Advantage, Not the Ratio: A Canonical-Form Analysis of Cooperative Multi-Agent Policy Optimization
Jul 20, 2026Zijian Zhao, Sen LiMulti-Agent Reinforcement Learning Team Formation
Teach it to stop, not just to click
Jul 19, 2026Barada Sahu, Shivesh PandeyReliability Agentic AI Systems
Accelerating A/B-Tests with Counterfactual Estimation: Reducing Variance through Policy Overlap
Jul 16, 2026Olivier JeunenVariance Reduction Variance
Where Does the Noise Come From? A Variance-Components Decomposition of Non-Determinism in LLM Brand Answers
Jul 14, 2026Dmitrij ŻatuchinLarge Language Model Reliability Brand Pairs
Diversify Diffusion with Temperature Sampling and Variance-Corrective Time Shifting
Jul 12, 2026Peizhuo Li, Emre Aksan, Alexandru-Eugen Ichim +2Diffusion Sampling Diffusion Models
CAFE: A Compound-AI Factorial Evaluation Framework
Jul 11, 2026Fabian Lukassen, Christoph Weisser, Thomas Kneib +1Artificial Intelligence Evaluation Multi-Hop Question Answering Benchmarks
Reliability and Identifiability in Persona-Trained Monte Carlo: Variance Decomposition, Stability Bounds, and the Identifiability of Heterogeneous News Reaction
Jul 6, 2026Salavat IshbulatovMonte Carlo Estimators
Language Models Represent and Transform Concepts with Shared Geometry
Jul 5, 2026Zhimin Hu, Lanhao Niu, Sashank VarmaNeural Representations Protein Language Model
Trajectory Variance: An Unsupervised Measure of Developmental Vocal Plasticity in Birdsong
Jul 3, 2026Kanghwi LeeVocalizations Developmental Trajectories
A More Accurate Algorithm Comparison through A/B Testing using Offline Evaluation Methods
Jul 2, 2026Koki Konishi, Masataka Ushiku, Yuta SaitoOnline Correlates
GRPO, Dr. GRPO, and DAPO Are Three Operations on One Number: The Group-Standard-Deviation Identity
Jun 30, 2026Yong Yi Bay, Kathleen A. YearickVariance Protein Language Model
An Integrated Machine Learning and Hierarchical Variance Decomposition Pipeline for Student Performance Prediction and Metacognitive Calibration on Multi-Signal Telemetry
Jun 27, 2026Gurdeep Singh VirdeePredictive Performance Metacognition
Variance Reduction for Stochastic Gradient Generalized Non-reversible Langevin Monte Carlo Algorithms
Jun 27, 2026Bingye Ni, Xiaoyu Wang, Yingli Wang +1Langevin Dynamics Variance Reduction
Analysis of Parameter Settings for the Bat Algorithm Using Variance Evolution
Jun 26, 2026Xin-She Yang, Mehmet KaramanogluEvolutionary Algorithms Variance
Generalized nonparametric regression in reproducing kernel Hilbert spaces: Consistency and rates of convergence
Jun 22, 2026Ioannis KalogridisKernel Hilbert Spaces Exponential Family
Escaping the Variance Trap: Jacobian-Free Dynamics for Root-Finding Bilevel Optimization
Jun 21, 2026Zhiyu Li, Xi Xuan, Davide CarboneBilevel Optimization Stochastic Approximation
On the Variance of Temporal Difference Learning and its Reduction Using Control Variates
Jun 18, 2026Hsiao-Ru Pan, Bernhard SchölkopfTemporal Difference Variance Reduction
Ensuring Trustworthy Online A/B Testing: Addressing Five Key Questions on CUPED
Jun 17, 2026Yu Zhang, Bokui Wan, Yongli Qin +2Heterogeneous Treatment Effects Estimators
Bounded Difference Concentration for Infinitely Exchangeable Sequences with Applications to AI Benchmark Uncertainty
Jun 16, 2026Fangyuan Lin, Spencer Frei, Victor H. de la PenaConcentration Inequalities Artificial Intelligence Benchmarks
Uncertainty Quantification of Engineering Structures by Polynomial Chaos Expansion and Multivariate Active Learning
Jun 15, 2026Qitian Lu, Jafar Jafari-Asl, Panagiotis Spyridis +1Surrogate Modeling Uncertainty Quantification
Demystifying Variance in Circuit Discovery of LLMs
Jun 15, 2026Frank Zhengqing Wu, Francesco Tonin, Volkan CevherMechanistic Interpretability Circuits
Variance Reduction for Non-Log-Concave Sampling with Applications to Inverse Problems
Jun 15, 2026M. Berk Sahin, Ahmet Ege Tanriverdi, Behzad Sharif +1Variance Reduction Posterior Sampling
Learning the generating functional for variance reduction in lattice QCD
Jun 14, 2026Ryan Abbott, Yang Fu, Daniel C. Hackett +3Effective Field Theory Variance Reduction
Semantic DLM+: Improving Diffusion Language Models through Bias-variance Trade-off in Transition Kernel Design
Jun 13, 2026Keyue Jiang, Yuxiang Wang, Yanan Zhao +7Diffusion Language Models Transitions
The Metric Picks the Winner: Evaluation Choice Flips Model Rankings for Drug-Response Prediction in Unseen Chemistry
Jun 10, 2026Dhruv Agarwal, Riya BishtDrug-Drug Interactions Responses
Crossing the Validation Crisis: Cross-Validation Reduces Benchmarking Variance Surprisingly Well
Jun 10, 2026Célestin Eve, Gaël Varoquaux, Thomas MoreauCross Validation Variance
Effective Reinforcement Learning for Agentic Search by Recycling Zero-Variance Queries During Training
Jun 9, 2026João Coelho, João Magalhães, Bruno Martins +1Agentic Search Multi-Hop Question Answering Benchmarks
The Unsampled Truth: Quantifying Prompt Artifacts in LM Psychometrics
Jun 2, 2026Nils Schwager, Christoph Hau, Simon Münker +1Psychometrics Psychology
Measuring the Symmetry--Data Exchange Rate
May 31, 2026Ahmed M. AdlyEquivariance Asymmetry
Optimal-Point Variance Reduction For Bayesian Optimization With Regret Guarantee
May 31, 2026Shion TakenoBayesian Optimization Variance Reduction
Resource-Constrained Affect Modelling via Variance Regularisation Pruning
May 26, 2026Kosmas Pinitas, Konstantinos KatsifisAffective Computing Valence-Arousal Estimation
Statistical Inference for Stochastic Gradient Descent Beyond Finite Variance
May 25, 2026Jose Blanchet, Peter Glynn, Wenhao YangStochastic Gradient Descent Confidence Intervals
Boundary Variance Inflation Causes Acquisition Bias in Gaussian Processes
May 25, 2026Maria Bånkestad, Sanna Jarl, Jens SjölundGaussian Process Variance
Pre-Registering the Detectable Effect: A Paired-MDE Budget for 4-bit Quantization Benchmarks, with a Pilot Audit
May 25, 2026Zexin Zhuang, Yanhang Li, Zhichao FanEffect Sizes Budgets
AI Cartography: Mapping the Latent Landscape of AI Benchmark Ecosystems
May 24, 2026Michael Hardy, Anka Reuel, Lijin Zhang +6Artificial Intelligence Benchmarks Leaderboard
OSDTW: Optimal Shared Depth and Task Weighting for Long-Tailed Recognition
May 24, 2026Chang Chu, Qingyue Zhang, Shao-Lun Huang +1Long-Tailed Distribution Loss Function
Variance Reduction for Expectations with Diffusion Teachers
May 20, 2026Jesse Bettencourt, Xindi Wu, Matan Atzmon +2Variance Reduction Variance
New Insight of Variance reduce in Zero-Order Hard-Thresholding: Mitigating Gradient Error and Expansivity Contradictions
May 18, 2026Xinzhe Yuan, William de Vazelhes, Bin Gu +1Variance Reduction Zeroth-Order Optimization
Embedding-perturbed Exploration Preference Optimization for Flow Models
May 15, 2026Sujie Hu, Chubin Chen, Jiashu Zhu +3Repair-Based Group-Relative Policy Optimization Curiosity-Driven Exploration
Position: Zeroth-Order Optimization in Deep Learning Is Underexplored, Not Underpowered
May 15, 2026Sijia Liu, Yicheng Lang, Soumyadeep Pal +6Zeroth-Order Optimization Low-Data Regimes
Beyond Bounded Variance: Variance-Reduced Normalized Methods for Nonconvex Optimization under Blum-Gladyshev Noise
May 14, 2026Antesh Upadhyay, Arda Fazla, Abolfazl HashemiConvex Optimization Nonconvex
Heuristic Pathologies and Further Variance Reduction via Uncertainty Propagation in the AIVAT Family of Techniques
May 14, 2026Juho Kim, Tuomas SandholmVariance Uncertainty Propagation
Beyond Explained Variance: A Cautionary Tale of PCA
May 13, 2026Gionni MarchettiPrincipal Component Analysis Persistent Homology
Reducing Bias and Variance: Generative Semantic Guidance and Bi-Layer Ensemble for Image Clustering
May 13, 2026Feijiang Li, Zhenxiong Li, Jieting Wang +3Clustering Ensemble
Decomposing the Generalization Gap in PROTAC Activity Prediction: Variance Attribution and the Inter-Laboratory Ceiling
May 12, 2026Thor Klamt, Wolfgang Nejdl, Ming TangDrug Design Protein
RDEx-CASK: Cauchy Mutation, Archive, and Stagnation Kick for RDEx-CSOP
May 10, 2026Dikshant, Dikshit Chauhan, Chen Hao +3Cryptographically Authorized Mutation Variance
On Variance Reduction in Learning Mean Flows
May 10, 2026Juanwu Lu, Ziran WangLatentflow Velocity Field
SGD for Variational Inference: Tackling Unbounded Variance via Preconditioning and Dynamic Batching
May 8, 2026Hippolyte Labarrière, Cesare Molinari, Silvia Villa +1Variational Inference Stochastic Gradient Descent
Rethinking Importance Sampling in LLM Policy Optimization: A Cumulative Token Perspective
May 8, 2026Yuheng Zhang, Chenlu Ye, Shuowei Jin +4Policy Optimization Variance
Dr. Post-Training: A Data Regularization Perspective on LLM Post-Training
May 8, 2026Pingbang Hu, Xueshen Liu, Z. Morley Mao +1Efficient Data Selection Large Language Model Post-Training
A Linear-Transformer Hybrid for SNP-Based Genotype-to-Phenotype Prediction in Grapevine
May 7, 2026Yibin Wang, Murukarthick Jayakodi, Silvas Kirubakaran +2Phenotypes Hybrid

Sep 8, 2026 · math.OCJ/K move · Enter open · S save

Oracle Complexity of Stochastic Fixed-Point Equations with Nonexpansive Maps

Jelena Diakonikolas, Cristóbal Guzmán, David Martínez-Rubio

We study the oracle complexity of computing a point with small fixed-point residual

\|T(x)-x\| \leq ε

, for a general norm

\|\cdot\|

and a self-map

T

of a compact convex set. We study this problem in the setting where

T

is nonexpansive with respect to the same norm

\|\cdot\|

and accessed via an unbiased stochastic oracle with bounded variance

σ^2

. We provide an algorithm that solves such instances for any norm with a weak Rademacher type

q > 1

, with high probability. The algorithm is based on a recursive anchoring technique. For type-

2

spaces, such as

\ell_p

-spaces for

p \in [2, \infty]

, our algorithm attains stochastic oracle complexity

\tilde O(σ^2 ε^{-3} + ε^{-1})

. We further prove a near-matching lower bound (i.e., matching up to poly-log factors) for such

\ell_{\infty}

-norm instances in high dimensions. Our lower bound holds against any randomized algorithm that succeeds with constant probability. It further extends to settings with ``sparse'' noise, where variance measured with respect to any

\ell_p

norm is of the same order, ruling out the possibility of improving oracle complexity as a function of

\varepsilon

by measuring variance in a non-matching

\ell_p

norm.

Fixed-Point Iteration Optimal Sample Complexity Spectral Norm Stochastic Contraction Convex Sets Variance

Open paper Ask about it PDF