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.
The method approximates stationary distributions of Markov models by truncating irrelevant states.
Green functions on stationary varifolds established with inequalities and convergence results.
Study on fake stationary Volterra Heston model for non-stationary processes.
New method stabilizes FQE by reweighting Bellman targets.
A method based on wavelet transform and genetic programming is proposed for characterizing and modeling variations at multiple scales in non-stationary time series. The cyclic variations, extracted by wavelets and smoothened by cubic splines, are well captured by genetic programming in the form of dynamical equations. …
Reinforcement learning mimics expert behavior.
New method improves stability of soft FQI for offline RL.
We consider off-policy policy evaluation when the trajectory data are generated by multiple behavior policies. Recent work has shown the key role played by the state or state-action stationary distribution corrections in the infinite horizon context for off-policy policy evaluation. We propose estimated mixture policy …
Transformers achieve near-optimal dynamic regret in non-stationary reinforcement learning.
We study how resetting affects geometric Brownian motion, showing it becomes stationary but remains non-ergodic.
HHAR-net uses neural networks to recognize human activities at different levels of abstraction.
The article presents methods to select models from behavioral learning data, with applications to contextual bandits.
We utilize a recently developed genetic algorithm, in conjunction with discrete wavelets, for carrying out successful forecasts of the trend in financial time series, that includes the NASDAQ composite index. Discrete wavelets isolate the local, small scale variations in these non-stationary time series, after which th…
The paper studies Möbius energy gradient of helix pairs and finds limiting behavior as coiling ratio increases.
This paper proposes a hierarchical feature extractor for non-stationary streaming time series based on the concept of switching observable Markov chain models. The slow time-scale non-stationary behaviors are considered to be a mixture of quasi-stationary fast time-scale segments that are exhibited by complex dynamical…
Study optimal transport for stationary processes, estimating joinings and costs.
New algorithm tackles non-stationary delayed feedback in recommender systems.
Study on gradient descent in Hilbert spaces with Markov chains, focusing on mixing coefficients.
Method learns evolving policies in healthcare contexts.
New GP kernels avoid mean reversion without losing smoothness.
A defining feature of non-stationary systems is the time dependence of their statistical parameters. Measured time series may exhibit Gaussian statistics on short time horizons, due to the central limit theorem. The sample statistics for long time horizons, however, averages over the time-dependent parameters. To model…
In sustained growth with random dynamics stationary distributions can exist without detailed balance. This suggests thermodynamical behavior in fast growing complex systems. In order to model such phenomena we apply both a discrete and a continuous master equation. The derivation of elementary rates from known stationa…
The method of cointegration in regression analysis is based on an assumption of stationary increments. Stationary increments with fixed time lag are called integration I(d). A class of regression models where cointegration works was identified by Granger and yields the ergodic behavior required for equilibrium expectat…
HA-SME models SGD dynamics with Hessian info for better escaping behaviors.
New findings show Bregman proximal algorithms can get stuck near non-stationary points.
Incremental learning from non-stationary data poses special challenges to the field of machine learning. Although new algorithms have been developed for this, assessment of results and comparison of behaviors are still open problems, mainly because evaluation metrics, adapted from more traditional tasks, can be ineffec…
Unified DICE estimators as regularized Lagrangians for improved off-policy evaluation.
Study on queues with Hawkes arrivals, proving steady-state behavior and developing an efficient algorithm.
We apply a recently developed wavelet based approach to characterize the correlation and scaling properties of non-stationary financial time series. This approach is local in nature and it makes use of wavelets from the Daubechies family for detrending purpose. The built-in variable windows in wavelet transform makes t…
Proposes a new method combining Reservoir Computing and Normalizing Flow for predicting stochastic dynamical systems.
We characterize stationary solutions to McKean-Vlasov equations on the circle.
To understand the structural dynamics of a large-scale social, biological or technological network, it may be useful to discover behavioral roles representing the main connectivity patterns present over time. In this paper, we propose a scalable non-parametric approach to automatically learn the structural dynamics of …
Study an anisotropic capillary flow to solve capillary Orlicz-Minkowski problem.
OML-AD detects anomalies in non-stationary time series data.
The paper improves QD policy ensembles using distribution ratio estimators.
ABS dynamically adjusts batch size based on policy stability, improving RL performance.
We consider the off-policy estimation problem of estimating the expected reward of a target policy using samples collected by a different behavior policy. Importance sampling (IS) has been a key technique to derive (nearly) unbiased estimators, but is known to suffer from an excessively high variance in long-horizon pr…
Paper shows no spurious local minima in a specific matrix factorization problem.
Paper develops sparse learning for heavy-tailed time series with locally stationary dynamics.
Recently, a new viewpoint on the classical c-boundary in Mathematical Relativity has been developed, the relations of this boundary with the conformal one and other classical boundaries have been analyzed, and its computation in some classes of spacetimes, as the standard stationary ones, has been carried out. In the p…
This research creates efficient models for cyclo-stationary systems using generative methods.
Noise balance theory explains SGD's behavior in neural networks.
In many real-world reinforcement learning applications, access to the environment is limited to a fixed dataset, instead of direct (online) interaction with the environment. When using this data for either evaluation or training of a new policy, accurate estimates of discounted stationary distribution ratios -- correct…
Master algorithm fails to detect non-stationarity in practical settings.
The Hull-Strominger system for supersymmetric vacua of the heterotic string allows general unitary Hermitian connections with torsion and not just the Chern unitary connection. Solutions on unimodular Lie groups exploiting this flexibility were found by T. Fei and S.T. Yau. The Anomaly flow is a flow whose stationary p…
We prove that a single-layer neural network trained with the Q-learning algorithm converges in distribution to a random ordinary differential equation as the size of the model and the number of training steps become large. Analysis of the limit differential equation shows that it has a unique stationary solution which …
This paper studies the landscape of empirical risk of deep neural networks by theoretically analyzing its convergence behavior to the population risk as well as its stationary points and properties. For an -layer linear neural network, we prove its empirical risk uniformly converges to its population risk at the rat…
The scaling properties of oil price fluctuations are described as a non-stationary stochastic process realized by a time series of finite length. An original model is used to extract the scaling exponent of the fluctuation functions within a non-stationary process formulation. It is shown that, when returns are measure…