New sampling method guarantees approximate first-order stationary points for non-convex functions.
problem Sampling from non-log-concave densities with non-convex potential functions.
method Averaged Langevin Monte Carlo with complexity analysis.
result Langevin Monte Carlo outputs a sample with ε-relative Fisher information after O(L²d²/ε²) iterations.
New methods reduce constraint violations to certainty in stochastic optimization.
problem Finding a point with certain constraint satisfaction and near-stationarity.
method Single-loop variance-reduced stochastic first-order methods with truncated momentum schemes.
result Achieves strong convergence guarantees for ε-stochastic stationary points with certain constraint satisfaction. Volatility, fitting with first order Landau expansion, stationarity, and causality of the Taiwan stock market (TAIEX) are investigated based on daily records. Instead of consensuses that consider stock market index change as a random time series we propose the market change as a dual time series consists of the index a…
Method solves complex optimization problems with high probability bounds.
problem Nonlinear equality constrained stochastic optimization problems.
method Step-search sequential quadratic programming method.
result High-probability bound on iteration complexity for first-order stationarity.
Paper proposes an algorithm to solve complex minimax problems efficiently.
problem Stochastic nonconvex-concave minimax problems in various fields.
method Accelerated first-order regularized momentum descent ascent algorithm (FORMDA).
result Achieves best-known complexity bound of ildeO(ε−6.5) for single-loop algorithms. Second-order guarantees for federated learning algorithms.
problem Non-convex optimization in federated learning with saddle-points as bottlenecks.
method Drawing on recent results on second-order optimality in centralized and decentralized settings, establish second-order guarantees for federated learning algorithms.
result Established second-order guarantees for federated learning algorithms.
Paper develops a TR-SSQP method for noisy optimization with heavy-tailed noise.
problem Optimization problems with stochastic objectives and heavy-tailed noise.
method Trust-Region Stochastic Sequential Quadratic Programming (TR-SSQP) method.
result Achieves high-probability first-order and second-order stationarity bounds for heavy-tailed noise.
The paper sets lower bounds for sampling non-log-concave distributions using Fisher information.
problem Understanding the complexity of sampling non-log-concave distributions.
method Proves two lower bounds using Fisher information in the context of sampling.
result Lower bounds on the complexity of sampling non-log-concave distributions, ruling out high-accuracy algorithms.
Muon optimizes Transformer training with heavy-tailed data, achieving optimal sample complexity.
problem Theoretical understanding of non-Euclidean optimisation methods for heavy-tailed data in training Transformers.
method Addressing the gap in theoretical understanding, we show Muon achieves optimal sample complexity under heavy-tailed noise.
result Muon finds an ε-stationary point in nuclear norm with optimal sample complexity, absorbing heavy-tailed noise without dimension dependence.
We consider discriminative dictionary learning in a distributed online setting, where a network of agents aims to learn a common set of dictionary elements of a feature space and model parameters while sequentially receiving observations. We formulate this problem as a distributed stochastic program with a non-convex o…
New algorithm provably converges to second-order stationary points in NMF.
problem Understanding convergence to local minima in NMF.
method Multiplicative weight update dynamics, concurrent updates, and simplex reduction.
result Provable convergence to second-order stationary points.
New methods solve sparse estimation robustly, even with outliers.
problem Sparse estimation in high-dimensional data with outliers.
method Non-convex optimization formulations for robust sparse mean estimation and PCA.
result Any approximate stationary point yields near-optimal solutions.
Adaptive algorithm AMSGrad converges for weakly convex constrained optimization problems.
problem Solving constrained stochastic optimization problems with weakly convex objectives.
method Analysis of AMSGrad algorithm for a specific class of problems.
result AMSGrad achieves a convergence rate of ildeO(t−1/4) for the norm of the gradient of the Moreau envelope. TSFMs embed non-stationary time series data, revealing specific types of changes.
problem Understanding non-stationarity in TSFMs' embedding spaces.
method Examined mean shifts, variance changes, linear trends, and persistence in TSFMs.
result Different TSFMs exhibit distinct failure modes in detecting non-stationarity.
Deep RL agents suffer from transient non-stationarity, which ITER mitigates.
problem Transient non-stationarity in deep RL agents affects generalization.
method Iterated Relearning (ITER) transfers knowledge between networks to reduce non-stationarity.
result ITER improves deep RL agents' performance on generalization benchmarks.
TimeBridge addresses non-stationarity in long-term time series forecasting.
problem Non-stationarity in multivariate time series leads to spurious regressions and obscures long-term relationships.
method TimeBridge segments series into patches, applying Integrated Attention for short-term non-stationarity and Cointegrated Attention for long-term cointegration.
result TimeBridge achieves state-of-the-art performance in both short-term and long-term forecasting.
This paper compares stationarity in Bitcoin and S&P500 price indices.
problem Comparing stationarity in cryptocurrency and traditional stock market indices.
method Wide sense stationarity defined; Wiener-Khinchin Theorem applied; stationarity achieved through detrending and normalization of price returns.
result S&P500 price return achieves stationarity for 28 years with specific normalization windows, while Bitcoin's stationarity varies by segment and volatility.
New method tackles bilevel optimization with polyhedral constraints.
problem Challenges in bilevel optimization with active-set changes and expensive Hessian inversions.
method Logarithmic barrier smoothing and proxy-gradient algorithm for differentiable approximation.
result Stationarity rates of O(K−2/3) in deterministic setting and O(K−2/5) under stochastic noise. AdaGrad outperforms SGD in non-convex optimization problems by a factor of d.
problem Finding near-stationary points in stochastic non-convex optimization.
method Refined assumptions on smoothness and gradient noise variance, l1-norm stationarity measure. result AdaGrad achieves a convergence rate favorable over SGD in certain non-convex settings.
Develops anytime-valid stopping rules for SGD based on observed trajectory.
problem Stopping stochastic gradient descent (SGD) based on observed trajectory.
method Develops anytime-valid confidence sequences for stochastic gradient methods.
result Statistically valid, time-uniform stopping rules for SGD across convex and nonconvex settings.
The paper explores various stationarity concepts in non-smooth optimization.
problem Understanding stationarity in non-smooth optimization problems.
method Introduction and discussion of different stationarity concepts for non-convex non-smooth functions.
result Clarification of the relationship among different stationarity concepts and their relevance in iterative methods.
Improved stock return prediction model handles noise and non-stationarity.
problem Predicting stock returns with robustness to noise and non-stationarity.
method Extended AROW algorithm to handle synchronous mini-batch updates and applied it to stock return prediction.
result The new model outperforms classical approaches in backtesting on S\&P500 stocks.
This paper considers regression tasks involving high-dimensional multivariate processes whose structure is dependent on some {known} graph topology. We put forth a new definition of time-vertex wide-sense stationarity, or joint stationarity for short, that goes beyond product graphs. Joint stationarity helps by reducin…
Lower bounds found for nonconvex-strongly-concave min-max optimization problems.
problem Finding stationary points in nonconvex-strongly-concave min-max optimization.
method Provided lower bounds for first-order oracle complexity.
result Lower bounds of Ω(√κε⁻²) for deterministic oracles and Ω(√κε⁻² + κ¹/₃ε⁻⁴) for stochastic oracles.
Master algorithm fails to detect non-stationarity in practical settings.
problem Non-Stationary Reinforcement Learning without prior knowledge.
method Master algorithm tested under various conditions, including piecewise stationary multi-armed bandits.
result Master's non-stationarity detection is ineffective for practical horizons, leading to performance similar to random restarting.
New algorithm solves non-convex, non-differentiable min-max games.
problem Limited theoretical understanding of non-smooth min-max games.
method Proximal gradient descent-ascent algorithm for convex-strongly convex games.
result Algorithm converges to ε-Nash equilibrium with polynomial gradient evaluations.
Generative Adversarial Networks (GANs) are one of the most practical methods for learning data distributions. A popular GAN formulation is based on the use of Wasserstein distance as a metric between probability distributions. Unfortunately, minimizing the Wasserstein distance between the data distribution and the gene…
Study classifies stock price data into stationary and non-stationary periods for mechanical trading.
problem Classifying stock price fluctuations into stationary and non-stationary periods for trading.
method Stationarity analysis using KM2O-Langevin theory and trend-based indicators for stationary periods, oscillator-based indicators for non-stationary periods. result Back testing confirms the strategy is a safe trading strategy with small maximum drawdown.
Study large deviation in stationarized fully lifted blirp interpolation.
problem Understanding atypical solutions in random optimization problems.
method Large deviation theory applied to fully lifted blirp interpolation.
result Elegant relations uncovered for fundamental interpolating parameters.
New solver SR2 tackles deep neural network training with nonsmooth regularization.
problem Training deep neural networks with nonsmooth regularization to achieve sparsity and efficiency.
method Combines adaptive quadratic regularization with proximal stochastic gradient principles.
result Established worst-case iteration complexity of O(ε^−2) for SR2.
Study non-stationary bandits with resource constraints.
problem Maximize reward in a non-stationary environment with resource constraints.
method Propose new non-stationarity measure and use primal-dual analysis.
result Upper and lower bounds for non-stationary BwK problem.
Neural population activity often exhibits rich variability and temporal structure. This variability is thought to arise from single-neuron stochasticity, neural dynamics on short time-scales, as well as from modulations of neural firing properties on long time-scales, often referred to as "non-stationarity". To better …
Paper tackles uncertainty prediction for deep sequential regression.
problem Challenges in generating accurate uncertainty estimates for deep recurrent networks.
method Flexible method that generates symmetric and asymmetric uncertainty estimates without stationarity assumptions.
result Outperforms competitive baselines on both drift and non-drift scenarios.
Framework isolates causal effects from time series data, improving accuracy under non-stationarity and autocorrelation.
problem Causal inference in non-stationary, autocorrelated time series data.
method Decomposes time series into trend, seasonal, and residual components; performs component-specific causal analysis.
result Framework more accurately recovers ground-truth causal structure than state-of-the-art baselines, especially under strong non-stationarity and temporal autocorrelation.
Study uses RL to optimize dynamic portfolios, addressing non-stationarity and constraints.
problem Non-stationarity and investment constraints in dynamic portfolio optimization.
method Reinforcement learning with regime change variables and practical constraints integration.
result Enhanced prediction accuracy through incorporation of regime change variables.
This article develops a statistical test for the null hypothesis of strict stationarity of a discrete time stochastic process in the frequency domain. When the null hypothesis is true, the second order cumulant spectrum is zero at all the discrete Fourier frequency pairs in the principal domain. The test uses a window …
Develops RL algorithm for lifelong non-stationary environments.
problem Challenges of reinforcement learning in environments with persistent change.
method Formalizes lifelong non-stationarity, uses latent variable models, and leverages online learning and probabilistic inference.
result Substantial improvement in performance over non-reasoning approaches in lifelong non-stationary environments.
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…
New method for estimating and optimizing MDPs without stationarity.
problem Challenges in offline contextual MDP estimation without stationarity.
method Introduces a new adaptive estimation and cost optimization approach for contextual MDPs.
result First robust, theoretically backed method for offline contextual MDP estimation.
New conditions for ACD model consistency and normality.
problem Random number of durations in ACD model.
method Additional sufficient conditions for consistency and normality of QMLE.
result Finite mean of durations is required for consistency and normality.
This paper explores twisted Lagrangian tori in C^2 and their Hamiltonian stationarity.
problem Understanding the Hamiltonian stationarity of twisted Lagrangian tori in C^2.
method Investigation of differential geometry of twisted tori, including product and Chekanov's exotic tori.
result Only product tori are minimal under Hamiltonian deformations, indicating Chekanov's exotic tori are not area minimal.
Study on fake stationary Volterra Heston model for non-stationary processes.
problem Non-stationary nature of true Volterra equations.
method Weak notion of stationarity (fake stationary regime) for inhomogeneous affine Stochastic Volterra equations.
result Existence of limiting distributions in the long run, which may depend on initial state.
Graph-based methods for signal processing have shown promise for the analysis of data exhibiting irregular structure, such as those found in social, transportation, and sensor networks. Yet, though these systems are often dynamic, state-of-the-art methods for signal processing on graphs ignore the dimension of time, tr…
Proposes a probabilistic framework for stationary topological signals on simplicial complexes.
problem Complex data structures require new models and tools.
method Generalizes stationarity to topological signals on simplicial complexes.
result Defines topological power spectral density (PSD) for stationary signals.
Solves POMDPs with recurrent neural networks and natural policy gradient.
problem Non-stationarity in optimal policies of POMDPs.
method Integrates recurrent neural networks into natural policy gradient and temporal difference learning.
result Non-asymptotic theoretical guarantees for global optimality up to function approximation.
A new QHR model extends HR model with a quadratic variance function.
problem Modeling volatility with greater flexibility and stationarity.
method Introducing a quadratic variance function to the HR model, maintaining Markovian property.
result Stationary distribution of the QHR model is Pearson type IV.
S&P 500 index data sampled at one-minute intervals over the course of 11.5 years (January 1989- May 2000) is analyzed, and in particular the Hurst parameter over segments of stationarity (the time period over which the Hurst parameter is almost constant) is estimated. An asymptotically unbiased and efficient estimator …
EM algorithm converges in KL divergence for exponential families via mirror descent.
problem Lack of understanding of EM's non-asymptotic convergence properties.
method Viewing EM as a mirror descent algorithm, showing convergence rates in KL divergence.
result KL divergence rates for EM in exponential families, invariant to parametrization.