Large Deviations Theory

Follow this topic Ask about this topic

Recent momentum

-100%

0 papers in the last 28 days · 0.0% of indexed attention

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

29 papers

Latest in Large Deviations Theory

Open your feed →

Online Inference for Quantile Temporal Difference Learning in Distributional Reinforcement Learning
Aug 13, 2026Zijie Cheng, Yang Peng, Zhihua ZhangDistributional Reinforcement Learning Temporal Difference
Self-Normalized Inference for Constant-Stepsize Temporal-Difference Learning under Markovian Sampling
Aug 11, 2026Min Zeng, Yichen Zhang, Xiaofeng ShaoTemporal Difference Large Deviations Theory
Multiplicity of Stable Attractors in Disordered Neural Models
Jul 24, 2026Raffaele Marino, Roberto Livi, Antonio PolitiAttractors Neural Ordinary Differential Equations
Lipschitzian SLLNs for random functions
Jul 22, 2026Lai Tian, Johannes O. RoysetLipschitz Constant Large Deviations Theory
Free energy landscape of Dense Associative Memory
Jul 21, 2026Sumedha, Abhishek SinghAssociative Memory Hopfield Networks
Riesz-Kernel Stein Variational Gradient Descent: Renormalized Entropy and Long-Time Particle Limits
Jul 16, 2026Trevor Teolis, Maarten V. de HoopLangevin Dynamics Large Deviations Theory
Asymptotical Analysis of the $(1+(λ,λ))$ GA Escape Time from Local Optima on Jump FunctionsAsymptotical Analysis of the (1+(λ,λ)) GA Escape Time from Local Optima on Jump Functions
Jul 15, 2026Anton V. Eremeev, Valentin A. TopchiiGenetic Algorithms Asymptotics
Variance Reduction for Stochastic Gradient Generalized Non-reversible Langevin Monte Carlo Algorithms
Jun 27, 2026Bingye Ni, Xiaoyu Wang, Yingli Wang +1Langevin Dynamics Variance Reduction
Scaling limit of the Random Language Model
Jun 26, 2026Eric De GiuliContext-Free Grammars Scaling Laws
Central limit theorem for the averaged Adam optimizer
Jun 19, 2026Steffen Dereich, Arnulf JentzenStochastic Approximation Large Deviations Theory
On the Variance of Temporal Difference Learning and its Reduction Using Control Variates
Jun 18, 2026Hsiao-Ru Pan, Bernhard SchölkopfTemporal Difference Variance Reduction
Boltzmann MapReduce: A Partition-Function Reduce for Forkable Sandboxes
Jun 17, 2026Yossi EliazBoltzmann Distributions Large Deviations Theory
Uncertainty Estimation and Generalization Bounds for Modern Deep Learning
Jun 11, 2026Luis A. OrtegaBayesian Neural Networks Uncertainty-Aware Teachers
How Deep Are Deep GPs, Really? A Sharp Threshold and a Non-Gaussian Limit for Compositional GPs
Jun 6, 2026Mark Kozdoba, Shie MannorGaussian Process Bayesian Neural Networks
How abundant are good interpolators?
Jun 4, 2026August Y. Chen, Ahmed El AlaouiEmpirical Risk Minimization Interpolation
Quantifying Uncertainty In Wide Two-Layer Neural Networks: On The Law Of The Limiting Fluctuation Process
Jun 4, 2026Arnaud Descours, Arnaud Guillin, Geoffrey Lacour +3Two-Layer Neural Networks Fluctuation-Dissipation Theorem
An Asymptotic Theory of Chain-of-Thought in In-Context Learning
Jun 2, 2026Kaito Takanami, Cengiz PehlevanIn-Context Learning Chain-Of-Thought
Large-scale Uncertainty Quantification for Latent Variable Models Using Subsampling Markov Chain Monte Carlo
May 29, 2026Xiaoyu Wang, Jonathan H. HugginsVariational Inference Gibbs Measures
Kernel Renormalization in Bayesian Deep Neural Networks: the Equivalent Wishart Ansatz in the Proportional Regime
May 28, 2026Paolo Baglioni, Christian Keup, Vincenzo Zimbardo +4Bayesian Neural Networks Deep Neural Network
Optimal Data Acquisition for Reinforcement Learning: A Large Deviations Perspective
May 27, 2026Mingjie Hu, Jian-Qiang Hu, Enlu ZhouData Collection Lagrangian Relaxation
Optimal Non-Asymptotic Edgeworth Expansions for Multivariate Neural Network Outputs
May 22, 2026Lucia CelliLarge Deviations Theory Neural-Network Approximation
On Gaussian approximation for entropy-regularized Q-learning with function approximation
May 17, 2026Artemy Rubtsov, Rahul Singh, Eric Moulines +2Q-Learning Large Deviations Theory
Central Limit Theorem for Two-Time-Scale Approximate Distributionally Robust RL
May 8, 2026Shengbo Wang, Zexi ZhangDistributional Reinforcement Learning Model-Free Reinforcement Learning
Universality in Deep Neural Networks: An approach via the Lindeberg exchange principle
May 4, 2026Filippo Giovagnini, Sotirios Kotitsas, Marco RomitoDeep Neural Network Large Deviations Theory
A Semi-Supervised Kernel Two-Sample Test
May 3, 2026Gyumin Lee, Shubhanshu Shekhar, Ilmun KimTwo-Sample Testing Covariate Shift
Phase Transitions in the Fluctuations of Functionals of Random Neural Networks
Apr 21, 2026Simmaco Di Lillo, Leonardo Maini, Domenico MarinucciLarge Deviations Theory Fluctuation-Dissipation Theorem
Global universal approximation with Brownian signatures
Dec 18, 2025Mihriban Ceylan, David J. PrömelStochastic Differential Equations Large Deviations Theory
Quenched large deviations for Monte Carlo integration with Coulomb gases
Aug 2, 2025Martin Rouault, Rémi Bardenet, Mylène MaïdaGibbs Measures Monte Carlo
Nonasymptotic CLT and Error Bounds for Linear Two-Time-Scale Stochastic Approximation
Feb 14, 2025Seo Taek Kong, Sihan Zeng, Thinh T. Doan +1Stochastic Approximation Large Deviations Theory

Aug 13, 2026 · stat.MLJ/K move · Enter open · S save

Online Inference for Quantile Temporal Difference Learning in Distributional Reinforcement Learning

Zijie Cheng, Yang Peng, Zhihua Zhang

School of Mathematical Sciences, Peking University · Yau Mathematical Sciences Center, Tsinghua University

In this paper, we study how to perform statistical inference for quantile temporal difference learning (QTD) in distributional reinforcement learning. Assuming access to a generative model, we first establish functional central limit theorems for both synchronous and asynchronous QTD, which show that the averaged iterates of QTD converge weakly to a rescaled Brownian motion. We next provide online inference methods. Based on random scaling, the inference procedure constructs an asymptotically pivotal statistic for inference by using the information along the whole QTD path. Meanwhile, the proposed statistic can be computed online without storing the entire trajectory of QTD iterates. This substantially reduces the memory requirement and enables efficient statistical inference in distributional reinforcement learning.

Distributional Reinforcement Learning Temporal Difference Distributional Learning Large Deviations Theory

Open paper Ask about it PDF