Percolation on complex networks has been used to study computer viruses, epidemics, and other casual processes. Here, we present conditions for the existence of a network specific, observation dependent, phase transition in the updated posterior of node states resulting from actively monitoring the network. Since tradi…
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
168,742 papers · 148 categories
Trend · papers per month
48 results for “Markov updating”
Modified Metropolis algorithm ensures convergence for multivariate binary distributions with fixed-order updates.
problem Infeasibility of standard Metropolis algorithm for multivariate binary distributions with fixed-order updates.
method Proposed a modified Metropolis transition operator ensuring irreducibility and convergence.
result Ensures convergence to the limiting distribution in multivariate binary case with fixed-order updates.
The paper simplifies multi-agent RL dynamics in finite-state Markov games using homogenization.
problem Approximating complex multi-agent reinforcement learning dynamics in finite-state Markov games.
method Rescaling learning process by reducing learning rate and increasing update frequency, proving convergence to an ODE.
result The rescaled process converges to an ODE that approximates the agent's learning dynamics.
We consider Markov models of stochastic processes where the next-step conditional distribution is defined by a kernel density estimator (KDE), similar to Markov forecast densities and certain time-series bootstrap schemes. The KDE Markov models (KDE-MMs) we discuss are nonlinear, nonparametric, fully probabilistic repr…
RSO uses random weight perturbations to train deep networks without gradients.
problem Training deep neural networks efficiently and without gradient information.
method RSO is a gradient-free Markov Chain Monte Carlo approach that updates weights based on mini-batch loss reduction.
result RSO achieves high accuracy (99.1% on MNIST) with significantly fewer updates than traditional methods.
Paper proposes a DRL-based controller for networked AP systems that reduces communication frequency.
problem Reduce communication frequency in networked AP systems while maintaining control performance.
method Develops a DRL-based controller that avoids explicit update timing learning, using a semi-Markov decision process (SMDP).
result Improves communication efficiency without sacrificing control performance.
Periodic Q-Learningcs.LG
PQ-learning improves Q-learning by periodically updating target estimates.
problem Improving sample complexity in Q-learning for finding optimal policies.
method Maintains two Q-value estimates, one online and one target, updated periodically.
result PQ-learning achieves better sample complexity for finding epsilon-optimal policies.
Stochastic variational inference for collapsed models has recently been successfully applied to large scale topic modelling. In this paper, we propose a stochastic collapsed variational inference algorithm for hidden Markov models, in a sequential data setting. Given a collapsed hidden Markov Model, we break its long M…
Developed a Particle-Gibbs sampler for Bayesian feature allocation models.
problem Intractable exact inference in Bayesian feature allocation models.
method Particle-Gibbs sampler for feature allocation matrix updates.
result PG sampler improves performance of feature allocation models.
The method of block coordinate gradient descent (BCD) has been a powerful method for large-scale optimization. This paper considers the BCD method that successively updates a series of blocks selected according to a Markov chain. This kind of block selection is neither i.i.d. random nor cyclic. On the other hand, it is…
Gibbs sampling is the de facto Markov chain Monte Carlo method used for inference and learning on large scale graphical models. For complicated factor graphs with lots of factors, the performance of Gibbs sampling can be limited by the computational cost of executing a single update step of the Markov chain. This cost …
New algorithm improves sample efficiency for zero-sum Markov games.
problem Improving sample efficiency for model-free algorithms in zero-sum Markov games.
method Proposes a model-free stage-based Q-learning algorithm using variance reduction techniques.
result Achieves optimal sample complexity for finding ε-optimal Nash Equilibrium.
New algorithm learns efficiently in multi-agent settings.
problem Efficient learning in multi-agent Markov decision processes.
method Cooperative Prioritized Sweeping: model-based reinforcement learning with sample efficiency.
result Outperforms state-of-the-art on SysAdmin and randomized environments.
Decentralized Optimistic Hyperpolicy Mirror Descent: Provably No-Regret Learning in Markov Gamescs.LG
DORIS algorithm achieves no-regret learning in Markov games with adversarial opponents.
problem Decentralized policy learning in Markov games with nonstationary opponents.
method DORIS algorithm using optimistic hyperpolicy mirror descent.
result Achieves -regret in general function approximation.
Improved sample complexity for actor-critic algorithms in MDPs.
problem Achieving optimal policies with limited data in reinforcement learning.
method Single-timescale actor-critic with STORM (STOchastic Recursive Momentum) and a sample buffer.
result Optimal sample complexity of for -optimal policies.
Develops a model for analyzing cryptocurrency returns focusing on extreme values.
problem Analyzing extreme returns in cryptocurrency time series.
method Linear expectile hidden Markov model with time-dependent coefficients.
result The method effectively captures the temporal evolution of extreme returns.
Constrained Markov Decision Process (CMDP) is a natural framework for reinforcement learning tasks with safety constraints, where agents learn a policy that maximizes the long-term reward while satisfying the constraints on the long-term cost. A canonical approach for solving CMDPs is the primal-dual method which updat…
Unbiased Monte Carlo Cluster Updates with Autoregressive Neural Networkscond-mat.stat-mech
New method makes machine learning approximations unbiased and efficient.
problem Efficient sampling of complex probability distributions.
method Uses autoregressive neural networks with cluster updates and physical symmetries.
result Shows unbiased and low-variance approximations for phase transitions.
The paper analyzes Q-learning convergence rates with asynchronous updates.
problem Analyzing convergence rates of asynchronous Q-learning algorithms.
method Derives rates of convergence using high-dimensional central limit theorems.
result Establishes a rate of order up to for hyper-rectangles.
New algorithm improves volatility forecasting using Pairwise Markov Chains.
problem Inability to effectively predict volatility due to feature problem and non-stationarity.
method Introduced a new algorithm for prediction with Pairwise Markov Chains (PMC), extending its capabilities.
result Enhanced performance of volatility forecasting models compared to GARCH(1,1) and feedforward neural models.
New algorithm optimizes MCMC sampling for structural dynamic models.
problem Time-consuming retraining of neural networks in MCMC methods.
method Adaptive meta-learning SGHMC algorithm that optimizes sampling strategy.
result Trained sampler can be applied to various problems without retraining.
RLCFR improves CFR's generalization in imperfect information games.
problem Improving CFR's performance in large-scale, imperfect information games.
method RLCFR integrates CFR with deep reinforcement learning to update strategies dynamically.
result RLCFR significantly enhances CFR's generalization ability in various games.
Updating predictive models introduces bias, leading to miscalibration.
problem Bias introduced when updating predictive models after interventions.
method Proposed a causal framework and partially observed Markov decision process.
result Successive predictive scores may converge to undesirable outcomes.
We consider a distributed estimation method in a setting with heterogeneous streams of correlated data distributed across nodes in a network. In the considered approach, linear models are estimated locally (i.e., with only local data) subject to a network regularization term that penalizes a local model that differs fr…
We present here a general framework and a specific algorithm for predicting the destination, route, or more generally a pattern, of an ongoing journey, building on the recent work of [Y. Lassoued, J. Monteil, Y. Gu, G. Russo, R. Shorten, and M. Mevissen, "Hidden Markov model for route and destination prediction," in IE…
FedSGM tackles constrained federated learning with unified framework.
problem Functional constraints, communication bottlenecks, local updates, and partial client participation in federated learning.
method Unified framework based on switching gradient method, incorporating bi-directional error feedback, and soft switching for stability.
result Achieves convergence rate with high-probability bounds decoupling from sampling noise.
RILA learns HQMMs robustly against adversarial corruption.
problem Robustness of HQMM learning algorithms under adversarial perturbations.
method Adversarially Corrupted HQMM (AC-HQMM) and Robust Iterative Learning Algorithm (RILA).
result RILA outperforms existing algorithms in convergence stability, corruption resilience, and physical validity.
Due to physiological variation, patients diagnosed with the same condition may exhibit divergent, but related, responses to the same treatments. Hidden Parameter Markov Decision Processes (HiP-MDPs) tackle this transfer-learning problem by embedding these tasks into a low-dimensional space. However, the original formul…
Bayesian estimation of GARCH model by hybrid Monte Carlophysics.comp-ph
The hybrid Monte Carlo (HMC) algorithm is used for Bayesian analysis of the generalized autoregressive conditional heteroscedasticity (GARCH) model. The HMC algorithm is one of Markov chain Monte Carlo (MCMC) algorithms and it updates all parameters at once. We demonstrate that how the HMC reproduces the GARCH paramete…
Traditional learning methods for training Markov random fields require doing inference over all variables to compute the likelihood gradient. The iteration complexity for those methods therefore scales with the size of the graphical models. In this paper, we propose \emph{block belief propagation learning} (BBPL), whic…
Novel algorithm for Markov decision processes using rank-one approximation.
problem Solving planning and learning problems of Markov decision processes.
method Policy iteration with rank-one approximation of transition probability matrix.
result The proposed algorithm consistently outperforms first-order algorithms and their accelerated versions.
This paper improves Bayesian decision tree learning using HMC.
problem Bayesian decision tree learning is challenging due to a large parameter space.
method Develops and compares HMC-based algorithms for exploring Bayesian decision tree posteriors.
result HMC-based methods outperform existing methods in predictive accuracy and tree complexity.
New method reduces forecasting error by up to 67% in various data types.
problem Outliers and model misspecification in online infinite hidden Markov models.
method Batched Robust iHMM (BR-iHMM) with bounded posterior influence function.
result Reduces one-step-ahead forecasting error by up to 67% in various data types.
A new framework predicts hidden Markov model regimes online.
problem Efficiently identify hidden Markov model regimes in streaming data.
method Develops a predictive-first optimisation framework for streaming HMMs, approximating the full posterior predictive distribution.
result The method provides competitive prequential performance compared to Online EM and Sequential Monte Carlo.
Optimistic PPO variant solves linear MDPs with improved regret bound.
problem Understanding theoretical limits of PPO in linear MDPs.
method Proposes an optimistic variant of PPO for episodic adversarial linear MDPs with full-information feedback.
result Establishes a regret bound.
Reinforcement learning improves insurance claims reserving by learning from all claim trajectories.
problem Traditional reserving models learn only from settled claims, missing valuable data from ongoing claims.
method Formulated as a Markov decision process, uses reinforcement learning to update OCL estimates sequentially.
result Soft Actor-Critic implementation achieves competitive claim-level accuracy and strong aggregate performance.
Efficiently implements polar slice sampling for high-dimensional distributions.
problem Sampling from difficult-to-implement distributions in high dimensions.
method Separates directional and radial components for efficient implementation.
result Outperforms related methods in various settings.
New method reduces computational cost for Bayesian inference.
problem High computational cost in Bayesian inference.
method Coreset MCMC, a Markov chain targeting coreset posterior.
result Coreset MCMC provides higher quality posterior approximations and reduced computational cost.
Paper introduces v-CMC linking causality and utility.
problem Linking causality and utility for value theory.
method Developed a new causal independence principle (v-CMC) and proved its equivalence.
result Equivalence of local, global, and decomposition versions of v-CMC.
LSB is a new MCMC method for discrete spaces that reduces target evaluations.
problem Sampling in discrete domains with high efficiency and adaptability.
method Local self-balancing proposals, mutual information objective, self-balancing learning.
result LSB converges with fewer target evaluations compared to existing methods.
New method for optimistic planning in MDPs using regularization.
problem Optimistic planning in infinite-horizon discounted MDPs.
method Regularized dynamic programming for approximate value iteration.
result Achieves near-optimal statistical guarantees in learning policies.
PPO algorithm converges to global optimality in multi-agent reinforcement learning.
problem Designing statistical guarantees for policy optimization methods in multi-agent reinforcement learning.
method Leveraging a multi-agent performance difference lemma, a localized action value function is used as a descent direction for each local policy, leading to a multi-agent PPO algorithm.
result The multi-agent PPO algorithm converges to the globally optimal policy at a sublinear rate under standard regularity conditions.
Federated learning enables training collaborative machine learning models at scale with many participants whilst preserving the privacy of their datasets. Standard federated learning techniques are vulnerable to Byzantine failures, biased local datasets, and poisoning attacks. In this paper we introduce Adaptive Federa…
Expectation-Maximization (EM) is a prominent approach for parameter estimation of hidden (aka latent) variable models. Given the full batch of data, EM forms an upper-bound of the negative log-likelihood of the model at each iteration and updates to the minimizer of this upper-bound. We first provide a "model level" in…
Paper proposes scalable algorithm to estimate intervention targets in linear models.
problem Estimating intervention targets in linear models from observational and interventional data.
method The paper proposes a scalable algorithm that estimates intervention sites from the difference between precision matrices of observational and interventional datasets.
result The algorithm consistently identifies all intervention targets and updates observational Markov equivalence classes to interventional ones.
Convergence of off-policy TD(0) with linear function approximation for reversible Markov chainsstat.ML
Study shows TD(0) with linear approx. converges for reversible Markov chains.
problem TD(0) divergence with off-policy and function approximation.
method Analyzes standard TD(0) with reversible Markov chains, adapting stochastic approximation framework.
result Establishes convergence with probability one for projected Bellman error = 0.
Detects anomalies in multiple processes using hidden Markov models.
problem Detecting an anomalous process among many with hidden states.
method Sequential search strategy using ADHM algorithm.
result ADHM algorithm effectively leverages temporal correlations.
Bayes-CPACE: PAC Optimal Exploration in Continuous Space Bayes-Adaptive Markov Decision Processescs.LG
We present the first PAC optimal algorithm for Bayes-Adaptive Markov Decision Processes (BAMDPs) in continuous state and action spaces, to the best of our knowledge. The BAMDP framework elegantly addresses model uncertainty by incorporating Bayesian belief updates into long-term expected return. However, computing an e…