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.
Estimates stationary mass and frequency from non-i.i.d. data.
Estimates missing mass in Markovian sequences with linear runtime and near-optimal risk.
Faster convergence of kernel mean embeddings using variance information.
Study online learning in RKHS with dependent processes, focusing on \(β\)- and \(φ\)-mixing.
Study on gradient descent in Hilbert spaces with Markov chains, focusing on mixing coefficients.
We show how to control the generalization error of time series models wherein past values of the outcome are used to predict future values. The results are based on a generalization of standard i.i.d. concentration inequalities to dependent data without the mixing assumptions common in the time series setting. Our proo…
We study a special case of the problem of statistical learning without the i.i.d. assumption. Specifically, we suppose a learning method is presented with a sequence of data points, and required to make a prediction (e.g., a classification) for each one, and can then observe the loss incurred by this prediction. We go …
Two algorithms learn Gaussian graphical models from Glauber dynamics trajectories, achieving optimal performance.
The literature on statistical learning for time series assumes the asymptotic independence or ``mixing' of the data-generating process. These mixing assumptions are never tested, nor are there methods for estimating mixing rates from data. We give an estimator for the -mixing rate based on a single stationary sample…
Paper analyzes distributed learning with non-i.i.d. samples.
This paper investigates the supervised learning problem with observations drawn from certain general stationary stochastic processes. Here by \emph{general}, we mean that many stationary stochastic processes can be included. We show that when the stochastic processes satisfy a generalized Bernstein-type inequality, a u…
Develops large-sample theory for non-stationary source separation.
Strong stability of ergodic iterations proven without ergodic driving sequence.
The paper studies convergence of kernel autocovariance operators for stationary processes.
This paper resolves the Langevin Algorithm's mixing time for log-concave distributions.
Learned factor graphs improve inference from time sequences using neural networks.
The study explores splitting conditions for mixed braid group sequences.
Memory-based models can learn to approximate Bayes-optimal predictors for non-stationary data.
Differentiable segmented models for non-stationary data.
Study optimal transport for stationary processes, estimating joinings and costs.
We prove a bubble tree convergence theorem for a sequence of closed Hamiltonian Stationary Lagrangian surfaces with bounded areas and Willmore energies in a complete K{ä}hler surface. We also prove two strong compactness theorems on the space of Hamiltonian stationary Lagrangian tori in and $\mathbb{CP}^2…
New bound for neural nets on non-iid data.
New method adapts to unknown mixing time in stochastic optimization.
Given a heterogeneous time-series sample, the objective is to find points in time (called change points) where the probability distribution generating the data has changed. The data are assumed to have been generated by arbitrary unknown stationary ergodic distributions. No modelling, independence or mixing assumptions…
Efficiently samples multimodal distributions using data-based initialization.
We study statistical inference and distributionally robust solution methods for stochastic optimization problems, focusing on confidence intervals for optimal values and solutions that achieve exact coverage asymptotically. We develop a generalized empirical likelihood framework---based on distributional uncertainty se…
Kernel-based tests detect dependencies in multivariate time series, including stationary and non-stationary data.
For stationary harmonic maps between Riemannian manifolds, we provide a necessary and sufficient condition for the uniform interior and boundary gradient estimates in terms of the total energy of maps. We also show that if analytic target manifolds do not carry any harmonic S^2, then the singular sets of stationary map…
Paper analyzes Nyström regularization for time series forecasting with sequential sub-sampling.
Models for sequential data such as the recurrent neural network (RNN) often implicitly model a sequence as having a fixed time interval between observations and do not account for group-level effects when multiple sequences are observed. We propose a model for grouped sequential data based on the RNN that accounts for …
Gaussian processes (GPs) are commonplace in spatial statistics. Although many non-stationary models have been developed, there is arguably a lack of flexibility compared to equipping each location with its own parameters. However, the latter suffers from intractable computation and can lead to overfitting. Taking the i…
The continuous observation of the financial markets has identified some stylized facts which challenge the conventional assumptions, promoting the born of new approaches. On the one hand, the long-range dependence has been faced replacing the traditional Gauss-Wiener process (Brownian motion), characterized by stationa…
Inference in general Ising models is difficult, due to high treewidth making tree-based algorithms intractable. Moreover, when interactions are strong, Gibbs sampling may take exponential time to converge to the stationary distribution. We present an algorithm to project Ising model parameters onto a parameter set that…
Bayesian nonparametric method segments multi-sequence time series data.
Process Monitoring involves tracking a system's behaviors, evaluating the current state of the system, and discovering interesting events that require immediate actions. In this paper, we consider monitoring temporal system state sequences to help detect the changes of dynamic systems, check the divergence of the syste…
Markov chain Monte Carlo (MCMC) algorithms are simple and extremely powerful techniques to sample from almost arbitrary distributions. The flaw in practice is that it can take a large and/or unknown amount of time to converge to the stationary distribution. This paper gives sufficient conditions to guarantee that univa…
We build a sequence of empirical measures on the space D(R_+,R^d) of R^d-valued càdlàg functions on R_+ in order to approximate the law of a stationary R^d-valued Markov and Feller process (X_t). We obtain some general results of convergence of this sequence. Then, we apply them to Brownian diffusions and solutions to …
Pac-Bayes bounds are among the most accurate generalization bounds for classifiers learned from independently and identically distributed (IID) data, and it is particularly so for margin classifiers: there have been recent contributions showing how practical these bounds can be either to perform model selection (Ambrol…
This study improves estimation of locally stationary functional time series using NW method.
Study LASSO for high-dimensional VAR models with weakly dependent innovations.
Study nonparametric estimator for Markov chain transition matrices in offline setting.
A new algorithm for restless bandits handles long-range dependencies.
The paper analyzes convergence rates of Langevin dynamics and Proximal Sampler using -divergence.
New definition resolves ambiguity in non-stationary bandit classification.
Optimal switching regret for all segmentations in online convex optimisation.
We provide a measure based topology for certain unions of C2 rectifiable submanifolds of mixed dimensions in Rn. In this topology lower dimensional sets remain in the limit as measures when higher dimensional sets collapse down to them. For example a decreasing sequence of spheres may have a limit consisting of just a …
Paper describes links of mixed polynomials with specific properties.
Markov chain Monte Carlo (MCMC) algorithms are ubiquitous in probability theory in general and in machine learning in particular. A Markov chain is devised so that its stationary distribution is some probability distribution of interest. Then one samples from the given distribution by running the Markov chain for a "lo…