Detects anomalies relative to typical observations.
problem Common anomaly detection methods fail for frequent anomalies.
method Relative anomaly detection, considering location relative to typical observations.
result Effective for frequent anomalies, computationally feasible, real-time detection.
A new method estimates target images directly from noisy observations in cryo-EM.
problem Estimating target images from noisy, rotated observations in cryo-EM.
method Estimates rotation-invariant features and then images from these features.
result Effectiveness demonstrated on synthetic cryo-EM datasets.
Study on typical knots and links using grid diagrams, focusing on size, components, and writhe.
problem Understanding the statistical behavior of knots and links, especially their typical properties.
method Modeling knots and links with grid diagrams, examining three invariants: size, components, and writhe, through numerical analysis.
result The size of a random knot is uniformly distributed and linearly dependent on grid size, while the number of components follows a distribution whose mean and variance grow with log_2 of grid size.
The R-function theory of Thomas is used to model neutron inelastic scattering and the fine, intermediate, and gross structure observed in the Dow Jones Industrial Average on a typical trading day.
We study distributions which have both fractal and non-fractal scale regions by introducing a typical scale into a scale invariant system. As one of models in which distributions follow power law in the large scale region and deviate further from the power law in the smaller scale region, we employ 2-dim quantum gravit…
We discuss the statistical properties of index returns in a financial market just after a major market crash. The observed non-stationary behavior of index returns is characterized in terms of the exceedances over a given threshold. This characterization is analogous to the Omori law originally observed in geophysics. …
The paper studies pseudo-Anosov maps from typical Thurston constructions.
problem Estimating the entropy of pseudo-Anosov maps from Thurston's constructions.
method Developed a method to extract information about random walks associated with Thurston's construction.
result Random walks eventually become pseudo-Anosov under certain conditions.
Aggregated variables can mask causal effects, turning unconfounded into confounded relations.
problem Aggregated variables can mask causal effects, leading to paradoxical confounding.
method Analysis of how aggregated variables can change the definition of causality and the feasibility of causal relations.
result Macro causal relations are defined by micro states, not just aggregated variables.
A new reinforcement learning method for medical decisions with limited data.
problem Learning high-performing policies from partially observed data in healthcare.
method Optimization objective that combines policy and generative model quality, suitable for batch off-policy settings.
result Demonstrated improved performance on synthetic and medical decision-making problems.
Efficiently infers coupled hidden Markov models with noisy discrete observations.
problem Intractable inference for coupled continuous-time Markov chains with discrete observations.
method Latent Interacting Particle Systems, look-ahead functions, twisted Sequential Monte Carlo sampling.
result Demonstrated effectiveness on latent SIRS model and wildfire spread dynamics.
In this paper, we study the backward Ricci flow on locally homogeneous 3-manifolds. We describe the long time behavior and show that, typically and after a proper re-scaling, there is convergence to a sub-Riemannian geometry. A similar behavior was observed by the authors in the case of the cross curvature flow.
A method to reduce boundary over-exploration in Bayesian optimization.
problem Over-exploration of the boundary in Bayesian optimization.
method Virtual derivative sign observations at the boundary of the search space.
result Consistently reduces the number of evaluations required to optimize the objective.
This research tackles intervention-centric causal reasoning in learning agents by using meta-learning.
problem Learning agents lack the concept of interventions, making causal learning challenging.
method A meta-reinforcement learning algorithm is used to learn causal relationships from observational data.
result The approach enables agents to learn and manipulate the environment effectively.
New algorithm for partially observable contexts in finance.
problem Decision making based on partially observable, correlated market information.
method EMKF-Bandit algorithm integrating system identification, filtering, and bandit algorithms.
result Sub-linear regret under conditions on filtering.
Overparameterized neural nets have a continuous set of global minima.
problem Understanding the loss landscape of overparameterized neural networks.
method Mathematical analysis of neural network loss functions.
result The set of global minima is a high-dimensional submanifold, not discrete.
AdaBelief optimizes deep learning models with faster convergence and better stability.
problem Combining fast convergence and stability in deep learning models.
method Adapts stepsize based on the belief in observed gradients using exponential moving average (EMA) of noisy gradients.
result AdaBelief outperforms other methods in image classification and GAN training, achieving comparable accuracy to SGD on ImageNet.
The paper develops a computational method for efficient online filtering of diffusion processes.
problem Online filtering of discretely observed nonlinear diffusion processes.
method The approach involves Doob's h-transforms approximated by solving backward Kolmogorov equations using nonlinear Feynman-Kac formulas and neural networks. result The proposed method can be orders of magnitude more efficient than state-of-the-art particle filters.
Extends symmetry and rigidity to surfaces with soap film-like singularities.
problem Symmetry and rigidity of minimal surfaces with singularities.
method Method of moving planes applied to surfaces with Plateau-like singularities.
result Extends classical results to surfaces with singularities.
IRL approach for studying consumer demand from observed behavior.
problem Confusing observational noise with consumer heterogeneity.
method Developed a Maximum Entropy IRL model for low-dimensional convex optimization.
result Observational noise can be mistaken for consumer heterogeneity.
DVRL learns a generative model for partially observable environments.
problem Learning in partially observable environments with unknown models.
method Introduces a deep variational approach to learn a generative model and perform inference.
result DVRL outperforms previous methods in partially observable environments.
Improved RL for TBGs by pruning irrelevant tokens and bootstrapping.
problem RL methods fail to generalize in TBGs with small data.
method CREST for irrelevant token removal, bootstrapped Q-learning.
result Improved generalization in unseen TextWorld games.
Paper develops consistent estimation of propensity scores for rare exposures.
problem Estimation of propensity score functions for rare exposures in oversampled cohorts.
method Flexible computational implementation using source population probability of exposure and observation weighting.
result Low empirical bias and variance for consistent propensity score function estimators.
Sig-PCA integrates model outputs and observations to correct model biases.
problem Improving model accuracy and reliability by correcting biases and numerical approximations.
method Sig-PCA framework that combines summary statistics from model outputs with localized observations via a neural network.
result Corrects model outputs to align closely with observational data, preserving essential statistical information.
Agents learning to act autonomously in real-world domains must acquire a model of the dynamics of the domain in which they operate. Learning domain dynamics can be challenging, especially where an agent only has partial access to the world state, and/or noisy external sensors. Even in standard STRIPS domains, existing …
New algorithm learns policies from expert observations alone, efficiently.
problem Imitation Learning from expert observations in large-scale MDPs.
method Forward Adversarial Imitation Learning (FAIL) algorithm, minimizing IP metric between expert and learner observation distributions.
result First provably efficient algorithm in ILFO setting, learning near-optimal policies with polynomial sample complexity.
Subsampling methods have been recently proposed to speed up least squares estimation in large scale settings. However, these algorithms are typically not robust to outliers or corruptions in the observed covariates. The concept of influence that was developed for regression diagnostics can be used to detect such corrup…
Researchers have studied the first passage time of financial time series and observed that the smallest time interval needed for a stock index to move a given distance is typically shorter for negative than for positive price movements. The same is not observed for the index constituents, the individual stocks. We use …
We investigate the Heston model with stochastic volatility and exponential tails as a model for the typical price fluctuations of the Brazilian São Paulo Stock Exchange Index (IBOVESPA). Raw prices are first corrected for inflation and a period spanning 15 years characterized by memoryless returns is chosen for the ana…
Extend CPS to non-exchangeable settings with observation-specific permutation weights
problem Calibrated predictive bands under distributional shifts
method Encoding distributional shifts through observation-specific permutation weights
result Shift-aware predictive systems remain valid
CODE learns ODE dynamics from sparse data, outperforming neural and kernel methods.
problem Learning ODE dynamics from sparse and noisy data.
method CODE uses Polynomial Chaos Expansion (aPCE) for the ODE's RHS, enabling global orthonormal polynomial representation.
result CODE exhibits remarkable extrapolation capabilities even under novel initial conditions and measurement noise.
`Distribution regression' refers to the situation where a response Y depends on a covariate P where P is a probability distribution. The model is Y=f(P) + mu where f is an unknown regression function and mu is a random error. Typically, we do not observe P directly, but rather, we observe a sample from P. In this paper…
Conjugate gradient methods improve efficiency for high-dimensional GLMMs.
problem Efficiency bottleneck in computing high-dimensional GLMM precision matrices.
method Combining spectral analysis and random graph theory with conjugate gradient methods.
result CG-based methods achieve linear scaling in cost with model parameters and observations.
Principal Component Analysis (PCA) is the most common nonparametric method for estimating the volatility structure of Gaussian interest rate models. One major difficulty in the estimation of these models is the fact that forward rate curves are not directly observable from the market so that non-trivial observational e…
Spectral method learns hidden state mapping for RL in rich-observation MDPs.
problem Challenges in RL with large state spaces and hidden low-dimensional structure.
method Spectral decomposition method to learn hidden state to observation state mapping.
result Achieves low regret with weak dependence on observed space dimensionality.
New method learns stochastic process representations without exact reconstruction.
problem Learning exact representations of high-dimensional noisy stochastic processes.
method CReSP framework for contrastive learning of stochastic processes.
result Effective for learning representations of various stochastic processes.
New method combines multiple datasets to estimate ATE with valid confidence intervals.
problem Combining multiple observational datasets to estimate ATE with valid confidence intervals.
method Prediction-powered inferences to shrink CIs and provide valid CIs.
result Valid confidence intervals for ATE from multiple datasets.
Combines observational and randomized data to estimate treatment effects.
problem Estimating heterogeneous treatment effects using only observational data is biased.
method Two-step framework: learn shared structure from observational data, then data-specific structures from randomized data.
result Combining observational and randomized data improves treatment effect estimation.
In this paper we develop a tractable structural model with analytical default probabilities depending on some dynamics parameters, and we show how to calibrate the model using a chosen number of Credit Default Swap (CDS) market quotes. We essentially show how to use structural models with a calibration capability that …
The paper develops a method to learn navigation costs from expert demonstrations in partially observable environments.
problem Learning navigation costs from expert demonstrations in partially observable environments.
method Develops a cost function representation composed of a probabilistic occupancy encoder and a cost encoder, optimized by differentiating the error between demonstrated controls and a control policy computed from the cost encoder.
result The method outperforms baseline IRL algorithms in robot navigation tasks, improving both training and test-time efficiency.
We study the relaxation dynamics of a financial market just after the occurrence of a crash by investigating the number of times the absolute value of an index return is exceeding a given threshold value. We show that the empirical observation of a power law evolution of the number of events exceeding the selected thre…
Dynamical-VAE learns causal dynamics from POMDPs using future information.
problem Learning accurate state representations from partial observations in POMDPs.
method Dynamical Variational Auto-Encoder (DVAE) with hindsight framework.
result DVAE uncovers causal graph more effectively than history-based methods.
DiEM trains diffusion models from noisy data using EM.
problem Training diffusion models requires clean data, which is often unavailable.
method DiEM uses expectation-maximization algorithm to train diffusion models from incomplete and noisy observations.
result DiEM leads to proper diffusion models suitable for downstream tasks.
Method learns dynamics from noisy partial observations.
problem Reconstructing stochastic dynamical systems from indirect noisy data.
method Amortized path generation method for nonlinear stochastic filtering.
result Learned conditional path generator quantifies uncertainty.
Online learning of nonstationary functions using Gaussian processes.
problem Real-time estimation of time-dependent functions with Gaussian processes.
method Sequential Monte Carlo algorithm for infinite mixtures of non-stationary GPs.
result Empirical improvement over state-of-the-art methods for online GP estimation.
Hybrid framework merges data and domain knowledge for better spatial interpolation.
problem Spatial interpolation overlooks domain knowledge and limits to spatial coordinates.
method Integrates data-driven features with rule-assisted spatial dependency function mapping.
result Superior performance in two application scenarios, capturing localized features.
A novel sequence-to-sequence model predicts missing sensor data.
problem Missing sensor data in sequences.
method Formulated a novel sequence-to-sequence model using forward and backward RNNs.
result The model produces the lowest errors in 12% more cases than the current state-of-the-art.
New method for tensor completion from specific mode observations.
problem Recovering multiway data tensors from partial observations.
method Tensor train decomposition for fiber-wise observations.
result Deterministic recovery guarantees for specific observation patterns.
The paper examines how timing of observations affects causal discovery methods.
problem The sensitivity of causal discovery methods to mismatched observation timing.
method Empirical and theoretical analysis of classical and recent causal discovery methods.
result Causal discovery methods are sensitive to sampling rate and window length.