The paper develops new inequalities for Markov chain sums, linking them to mixing time.
problem Establishing concentration inequalities for Markov chain sums.
method Developed novel concentration inequalities for geometrically ergodic Markov chains, linking bounds to mixing time constants.
result Explicit bounds for additive functionals of Markov chains, linked to Rosenthal inequality constants and mixing properties.
The paper provides concentration inequalities for Markov chain variance estimators.
problem Estimating the variance of Markov chains with concentration properties.
method Martingale decomposition method for uniformly geometrically ergodic Markov chains.
result Explicit control of the p-th moment of the OBM estimator difference and dependence on p and mixing time.
The paper extends Hoeffding's inequality for Markov chains using a generalized concentrability condition.
problem Applying Hoeffding's inequality to non-ergodic Markov chains.
method Integrates generalized concentrability condition via IPM to extend traditional hypotheses.
result Demonstrates utility in machine learning applications such as empirical risk minimization and bandits.
New concentration inequality for U-statistics of Markov chains.
problem Proving a concentration inequality for U-statistics of order two in uniformly ergodic Markov chains.
method Inductive analysis using martingale techniques, uniform ergodicity, Nummelin splitting, and Bernstein's inequality.
result Recovery of convergence rate for U-statistics of independent random variables and canonical kernels, with improved results for dependent kernels.
The article examines entropy-information inequalities for continuous-time Markov chains under curvature-dimension conditions.
problem Proving Li-Yau inequalities and modified logarithmic Sobolev inequalities for reversible Markov chains.
method Introducing the C D Υ ( κ , F ) CD_Υ(κ,F) C D Υ ( κ , F ) condition and deriving entropy-information inequalities. result Derives functional inequalities relating entropy to Fisher information.
The paper proves inequalities for Steklov eigenvalues on finite graphs.
problem Eigenvalues of Laplacians for reversible Markov chains and Steklov eigenvalues.
method Generalized Cheeger inequalities, convergence results, and resolvent convergence.
result Sharp estimate for the first non-trivial Steklov eigenvalue.
The paper bounds generalization errors for deep neural networks with Markov datasets.
problem Bounding generalization errors for deep learning with Markov datasets.
method Developed new symmetrization inequalities for Markov chains, using spectral gap of the infinitesimal generator.
result Derived upper bounds on generalization errors for deep neural networks with Markov datasets.
Deviation inequalities for stochastic approximation methods.
problem Establishing bounds on the deviation of stochastic approximation methods.
method Martingale approximation method for separately Lipschitz functions.
result Established various deviation inequalities for stochastic approximation by averaging and minimization.
The paper develops a Hoeffding inequality for Markov chains and applies it to bandit problems.
problem Developing a Hoeffding inequality for Markov chains and applying it to bandit problems.
method Developed a Hoeffding inequality for the partial sums of an irreducible Markov chain on a finite state space.
result Demonstrated the inequality's effectiveness in identifying approximately best Markovian arms and minimizing regret in Markovian bandits.
Improved analysis of UCRL2 with empirical Bernstein inequality reduces exploration-exploitation regret.
problem Exploration-exploitation in communicating Markov Decision Processes.
method Analysis of UCRL2 with Empirical Bernstein inequalities (UCRL2B).
result Regret bound of O ~ ( D Γ S A T ) \widetilde{O}(\sqrt{DΓS A T}) O ( D Γ S A T ) for UCRL2B. The study proves inequalities and curvature properties for Markov chains.
problem Isoperimetric and concentration inequalities for Markov chains.
method Laplacian separation principle for eikonal equation; modified log-Sobolev constant; Ollivier curvature.
result Affirmative answers to open questions and new inequalities.
The study establishes a curvature-dimension condition for discrete Markov chains.
problem Proving modified logarithmic Sobolev inequalities for discrete Markov chains.
method Identifying and proving a curvature-dimension inequality C D Υ ( κ , ∞ ) CD_Υ(κ,\infty) C D Υ ( κ , ∞ ) , and showing its compatibility with diffusive settings. result The C D Υ CD_Υ C D Υ condition preserves curvature bounds under tensorization and leads to Beckner inequalities. Exponential inequalities are main tools in machine learning theory. To prove exponential inequalities for non i.i.d random variables allows to extend many learning techniques to these variables. Indeed, much work has been done both on inequalities and learning theory for time series, in the past 15 years. However, for …
Software estimates inequality in random systems with changing communities.
problem Measuring inequality in systems with dynamic interactions and random attributes.
method Piecewise homogeneous Markov chain for changing points, copula function for multivariate distribution, Monte Carlo algorithm for entropy estimation.
result Estimates Random Theil's Entropy to measure inequality in random systems.
The paper studies how quickly samples from Langevin dynamics become independent.
problem Understanding the dependence between samples along Langevin dynamics and related algorithms.
method Measures dependence via Φ Φ Φ -mutual information and proves strong data processing inequalities. result The Φ Φ Φ -mutual information between samples decreases exponentially to zero. The paper analyzes convergence rates of Langevin dynamics and Proximal Sampler using Φ Φ Φ -divergence.
problem Analyzing convergence rates of Langevin dynamics and Proximal Sampler.
method Extending mixing time analyses to Φ Φ Φ -divergence, using strong data processing inequalities. result Convergence of Φ Φ Φ -divergence to 0 exponentially fast along Unadjusted Langevin Algorithm and Proximal Sampler. Estimates covariance matrices using Markov chain Monte Carlo with improved sample complexity.
problem Complexity of covariance matrix estimation for Gibbs distributions.
method Uses Markov chain Monte Carlo with conditions on the chain's spectral gap and Poincaré inequality.
result Achieves similar sample complexity as i.i.d. samples with better query complexity.
Study improves generalization bounds for equivariant networks on Markov data.
problem Challenges in integrating equivariance with Markov dependencies in neural networks.
method Applied McDiarmid's inequality and computed covering number using group theory.
result Derived upper bound on Rademacher complexity for equivariant neural networks on Markov datasets.
Intertwining curvature bounds for graphs and quantum Markov semigroups verified.
problem Intertwining curvature bounds for graphs and quantum Markov semigroups.
method Introducing and verifying curvature bounds in various examples.
result Improved entropic curvature bounds for depolarizing semigroups and qubits.
We prove a global Li-Yau inequality for a general Markov semigroup under a curvature-dimension condition. This inequality is stronger than all classical Li-Yau type inequalities known to us. On a Riemannian manifold, it is equivalent to a new parabolic Harnack inequality, both in negative and positive curvature, giving…
New method detects changes in high-dimensional Markov processes without explicit likelihood evaluation.
problem Quickest change detection in Markov processes with unknown transition kernels.
method Learn conditional score from sample pairs, develop score-based CUSUM procedure.
result Exponential lower bounds on mean time to false alarm and asymptotic upper bounds on detection delay.
New insights into stochastic methods for solving variational inequalities.
problem Understanding convergence behaviors of stochastic algorithms in variational inequalities.
method Re-casting SEG/SGDA as Markov Chains to analyze their probabilistic structures.
result The average iterate is asymptotically normal with a unique invariant distribution for various VIPs.
New entropy flow method extends generalization bounds for all Markov algorithms.
problem Understanding generalization error for Markov algorithms.
method Unified framework using continuous-time approximation and modified logarithmic Sobolev inequalities.
result Established new connections between generalization error and ergodic properties of Markov processes.
New transport method simplifies cutoff phenomenon for Markov processes.
problem Understanding the cutoff phenomenon for Markov processes.
method A new W-TV transport inequality combined with a parabolic regularization estimate.
result Recovery and extension of previous results on cutoff phenomena.
The paper advances U-statistics in dependent settings, improving spectral estimation and goodness-of-fit tests.
problem Non-asymptotic analysis of U-statistics in dependent Markov chain settings.
method Proved new concentration and exponential inequalities for U-statistics, applied to spectral estimation, online algorithms, and goodness-of-fit tests.
result Established new results for spectral estimation, online algorithms, and goodness-of-fit tests in Markov chain settings.
Novel bounds improve TD learning consistency in RL.
problem Analyzing Temporal Difference learning's performance.
method High-dimensional concentration inequalities and Berry-Esseen bounds for Markov chain induced martingales.
result Sharp high-probability consistency guarantee for TD learning, matching asymptotic variance up to logarithmic factors.
New approach to concentration inequalities for unbounded state space dynamical systems.
problem Concentration inequalities for unbounded state space dynamical systems.
method Functional analytic framework, transport-entropy inequality.
result Exponential concentration inequalities for sampling from stationary distribution.
Uniform TD(0) bound derived for function approximation with Markov noise.
problem Uniform concentration bound for TD(0) with function approximation.
method Contractive stochastic approximation, martingale and Markov noises, Poisson equation, relaxed concentration inequalities.
result Uniform all-time concentration bound for TD(0) with linear function approximation.
MER algorithm speeds up VI solving with Markovian data.
problem Solving stochastic variational inequalities with Markovian data.
method MER algorithm using multi-scale sampling from a Markovian buffer.
result Achieves faster convergence without knowing Markov chain mixing time.
New COS method formula improves option pricing accuracy.
problem Determining the optimal truncation range for COS method.
method Derive new formula using Markov's inequality to ensure convergence.
result New formula leads to more accurate option pricing.
This paper is concerned with an optimal stock selling rule under a Markov chain model. The objective is to find an optimal stopping time to sell the stock so as to maximize an expected return. Solutions to the associated variational inequalities are obtained. Closed-form solutions are given in terms of a set of thresho…
Bayesian network models with latent variables are widely used in statistics and machine learning. In this paper we provide a complete algebraic characterization of Bayesian network models with latent variables when the observed variables are discrete and no assumption is made about the state-space of the latent variabl…
New strategy identifies best Markovian arm with fixed confidence.
problem Identifying the best arm in Markovian bandit models with fixed confidence.
method Analyzed the Track-and-Stop strategy and derived a concentration inequality for Markov chains.
result The Track-and-Stop strategy is at most a factor of four apart from the lower bound for asymptotic performance.
Study non-negative curvature Markov chains, proving entropy contraction.
problem Prove entropy contraction for Markov chains with non-negative curvature.
method Prove 1-step contraction in Wasserstein distance implies 1-step contraction in relative entropy.
result Prove MLSI with constant equal to minimal rate increment for mean-field zero-range process.
Develops robust MDPs for unknown disturbances with performance guarantees.
problem Unknown disturbance distribution in MDPs.
method Empirical distribution, sublevel set of distance function, weak convergence, concentration inequality.
result Robust optimal value function converges to true optimal value function with increasing sample sizes.
New measures generalize existing ones, linking information and risk.
problem Linking information measures and risk in statistical decision problems.
method Introducing new families of divergence measures and deriving an information processing equality.
result Extension of variational φ φ φ -divergence representation to multiple distributions. This paper sets a lower bound for sample complexity in inverse reinforcement learning.
problem Finding a reward function that generates a desired optimal policy in MDPs.
method Information-theoretic lower bound using geometric construction and Fano's inequality.
result An O ( n log n ) O(n \log n) O ( n log n ) sample complexity lower bound for IRL problems. Introducing inequality constraints in Gaussian process (GP) models can lead to more realistic uncertainties in learning a great variety of real-world problems. We consider the finite-dimensional Gaussian approach from Maatouk and Bay (2017) which can satisfy inequality conditions everywhere (either boundedness, monoton…
New bound improves on weighted majority vote risk estimation.
problem Improving risk estimation for weighted majority vote.
method Novel Chebyshev-Cantelli inequality and PAC-Bayes-Bennett inequality.
result New bounds improve on existing methods.
Paper tackles high-order inference in structured prediction tasks.
problem Maximizing a score function on the space of labels in high-order Markov random fields.
method Generative model approach with two-stage convex optimization algorithm.
result Success in general high-order inference problems driven by hyperedge expansion properties.
Efficiently samples multimodal distributions using data-based initialization.
problem Sampling multimodal distributions with limited samples.
method Data-based initialization for Markov chains with spectral gap.
result Efficiently generates samples close to stationary distribution.
A new algorithm speeds up elliptical slice sampling for truncated multivariate normals.
problem Efficiently sampling from truncated multivariate normal distributions with linear constraints.
method Adapting elliptical slice sampling to linearly truncated multivariate normals, with an algorithm for ellipse-polytope intersection in O(m log m) time.
result The algorithm enhances numerical stability, speeds up running time, and is easy to parallelize.
Unified approach for first-order methods with Markovian noise in stochastic optimization and variational inequalities.
problem Stochastic optimization problems with Markovian noise.
method Unified theoretical analysis of first-order gradient methods using randomized batching and multilevel Monte Carlo.
result Optimal (linear) dependence on the mixing time of the noise sequence, eliminating previous limiting assumptions.
Study on financial systems using perturbed unimodal maps with heteroscedastic noise.
problem Analyzing systemic risk in financial systems using mathematical models.
method Investigation of one-dimensional unimodal maps perturbed by heteroscedastic noise, proving stability, convergence, and Lyapunov exponent continuity.
result Continuous dependence of average Lyapunov exponent on Markov chain parameters, and Gumbel's law for extreme values.
Study optimal adaptive allocation for multi-armed bandits with Markovian rewards.
problem Optimal adaptive allocation for multi-armed bandits with Markovian rewards.
method Round-robin Kullback-Leibler upper confidence bounds for optimal adaptive allocation.
result Logarithmic dependence of regret on time horizon, asymptotically optimal.
ST-BCP narrows the coverage gap in BCP by transforming nonconformity scores.
problem The looseness in BCP's coverage guarantee due to Markov's inequality.
method Introduces a data-dependent transformation of nonconformity scores.
result Reduces the average coverage gap from 4.20% to 1.12% on benchmarks.
In the paper, we construct conservative Markov processes corresponding to the martingale solutions to the stochastic heat equation on R + \mathbb{R}^+ R + or R \mathbb{R} R with values in a general Riemannian maifold, which is only assumed to be complete and stochastic complete. This work is an extension of the previous paper …
New method improves RL in continuous spaces with kernel smoothing.
problem Sample efficiency and structural assumptions in classical RL.
method Kernel smoothing model-based approach with Bernstein-style exploration bonus.
result Achieves improved regret bound in finite-horizon settings.