New algorithms estimate unknown training examples to improve ML model generalization.
problem Distribution shift between training and testing data leads to poor generalization.
method Combining species-estimation techniques with data-driven methods.
result Correcting the training set with unknown examples improves model robustness.
Neural network residuals isolate and locate unknown faults.
problem Locating unknown faults in industrial systems.
method Neural network-based residuals combining physical insights and machine learning.
result Neural network residuals can isolate and locate unknown faults.
Generative ODE model learns unknown variables in medical systems.
problem Estimating unknown variables in complex medical systems.
method Variational autoencoder incorporating known ODE functions.
result Modeling known-unknowns improves system parameter discovery and extrapolation.
Method learns model for unknown stochastic system from data.
problem Modeling unknown stochastic dynamical systems.
method Autoencoder approach using deep neural networks (DNNs).
result Decoder serves as a predictive model for unknown stochastic systems.
Method preserves Hamiltonian structure for unknown systems from noisy data.
problem Reconstructing unknown Hamiltonian systems from trajectory data.
method Directly approximates the unknown Hamiltonian, enforcing conservation.
result Structure-preserving property demonstrated and effective in numerical examples.
New method for predicting neuron activity with unknown stimuli.
problem Statistical inference of neuron activity with missing data and unknown sources.
method Maximum likelihood estimation with fixed-point iteration.
result Model increases system likelihood and reveals neural connections.
New algorithm learns safe policies in unknown environments.
problem Learning safe policies in unknown, potentially unsafe environments.
method C-UCRL: Upper Confidence Reinforcement Learning for constrained MDPs.
result Achieves sub-linear regret while satisfying constraints.
Iterative method learns unknown constraints for MPC control.
problem Learning to satisfy unknown polyhedral state constraints in iterative MPC.
method Collects and improves estimates of unknown constraints using collected data, designs an MPC controller to satisfy the estimated constraints.
result Robust and probabilistic guarantees of constraint satisfaction as a function of task iterations.
BaCaDI discovers causal structures from unknown interventions.
problem Inferring causal structures from unknown interventions with limited data.
method Bayesian framework with gradient-based variational inference.
result BaCaDI outperforms related methods in identifying causal structures and intervention targets.
Study robust learning without knowing perturbation sets, using interactions with attackers.
problem Learning robust predictors against unknown adversarial perturbations.
method Examined different interaction models with adversarial attackers, derived bounds on sample complexity and interactions.
result Upper bounds on sample complexity and lower bounds on interactions in various models.
New algorithm for truncated linear regression without knowing the survival set.
problem Estimating the unknown regressor in truncated linear regression with an unknown survival set.
method Sub-Gaussian feature vectors and novel subroutine for learning unions of intervals.
result First algorithm with poly(d/ε) runtime for truncated linear regression with unknown survival set.
Study resource allocation strategies in sequential decisions with unknown rewards.
problem Sequential resource allocation with unknown rewards.
method Design combinatorial multi-armed bandit algorithms for discrete or continuous budgets.
result Prove algorithms achieve logarithmic cumulative regret under semi-bandit feedback.
RTSCV detects unknown unknowns to improve model performance.
problem Model deficiency due to incomplete training data.
method Random Test Sampling and Cross-Validation (RTSCV) framework.
result Reduces performance gap by up to 41%.
DUE framework models unknown equations from data using deep learning.
problem Unknown equations in complex systems.
method Data-driven modeling using deep learning techniques.
result Framework capable of learning various types of unknown equations.
Small Nijenhuis tensor found on compact manifolds.
problem Finding compact manifolds with small Nijenhuis tensor.
method Provided explicit examples of manifolds with small Nijenhuis tensor.
result Examples of manifolds with small Nijenhuis tensor in various dimensions.
Study methods to recover unknown processes in PDEs from data.
problem Identifying unknown processes in time-dependent PDEs using observational data.
method Theoretical analysis and numerical approaches including Galerkin and collocation algorithms.
result The Galerkin algorithm is more suitable for practical situations with noisy data.
Generalized ResNet learns unknown dynamical systems using neural networks.
problem Learning unknown dynamical systems with deep neural networks.
method A generalized ResNet framework using discrepancy as model correction.
result Generalized ResNet produces more accurate predictions than standard ResNet.
The paper models and predicts co-occurrence counts using Gamma regression.
problem Predicting relevance between items or users from high-dimensional sparse co-occurrence count data.
method Shared parameter alternating zero-inflated Gamma regression models (SA-ZIG) with Fisher scoring and learning rate adjustment.
result SA-ZIG with learning rate adjustment performs satisfactorily in predicting relevance.
DeepONet models system discrepancies with low data.
problem Modeling complex systems with limited data.
method Bi-fidelity modeling using DeepONet for uncertain and partially unknown systems.
result DeepONet effectively models complex systems with parametric uncertainty and partial unknownness.
MAGI-X learns unknown dynamics from data without numerical integration.
problem Difficult to propose ODEs in closed-form for complex systems.
method MAGI-X uses neural networks within a manifold-constrained Gaussian process framework.
result MAGI-X achieves competitive accuracy in fitting and forecasting with reduced computational time.
We give an elementary construction of symplectic connections through reduction. This provides an elegant description of a class of symmetric spaces and gives examples of symplectic connections with Ricci type curvature, which are not locally symmetric; the existence of such symplectic connections was unknown.
We present a novel family of nonparametric omnibus tests of the hypothesis that two unknown but estimable functions are equal in distribution when applied to the observed data structure. We developed these tests, which represent a generalization of the maximum mean discrepancy tests described in Gretton et al. [2006], …
Method learns dynamics of slow variables from stochastic data.
problem Modeling unknown multiscale stochastic systems with limited data.
method Data-driven approach to learn effective dynamics from bursts of observation data.
result Generative model accurately captures effective dynamics of slow variables.
This paper focuses on the stability of the non-arbitrage condition in discrete time market models when some unknown information τ is partially/fully incorporated into the market. Our main conclusions are twofold. On the one hand, for a fixed market S, we prove that the non-arbitrage condition is preserved under a m…
Improved PINNs for solving PDEs with unknown measurement noise.
problem Handling non-Gaussian noise in physics-informed neural networks.
method Jointly train an EBM to learn the correct noise distribution.
result Improved performance in solving PDEs with non-Gaussian noise.
Study identifies components of unknown interventions in a mixture.
problem Identify components of a mixture of unknown interventions on a causal Bayesian Network.
method Construct example showing components not identifiable. Prove identifiability under mild conditions. Develop efficient algorithm for recovery. Analyze performance in simulation.
result Components of a mixture of unknown interventions can be uniquely identified under certain conditions.
A novel GPUM constructs Gaussian Processes for unknown manifolds with probabilistic metrics.
problem High-dimensional data on unknown manifolds with non-Euclidean geometry.
method Bayesian Gaussian Processes latent variable models (BGPLVM), Riemannian geometry, probabilistic metric tensor, Brownian Motion.
result GPUM provides more accurate predictions on unknown manifolds compared to traditional methods.
Adversarial examples fool both computer vision and humans.
problem Vulnerability of machine learning models to adversarial examples.
method Transfer adversarial examples from known models to unknown models and match human visual processing.
result Adversarial examples influence human classifications.
A new WNN framework selects wavelet bases for efficient learning.
problem Challenges in constructing accurate wavelet bases and high computational costs in WNN.
method Introduces a constructive WNN that selects initial bases and trains functions by introducing new bases for predefined accuracy while reducing computational costs.
result Significantly improves computational efficiency through a frequency estimator and wavelet-basis increase mechanism.
Develops inverse extended Kalman filter for predicting adversarial steps.
problem Predicting adversarial Kalman filter estimates from limited information.
method Proposes inverse extended Kalman filter (I-EKF) for non-linear systems with unknown inputs.
result Derives I-EKF with theoretical stability guarantees and consistency proofs.
Develops inverse EKF for non-linear systems with stability guarantees and learning unknown dynamics.
problem Estimating adversary's Kalman-filtered estimates in highly non-linear systems.
method Proposes inverse extended Kalman filter (I-EKF) for second-order, Gaussian sum, and dithered forward models. Uses reproducing kernel Hilbert space for learning unknown dynamics.
result Derives theoretical stability guarantees for inverse second-order EKF.
Estimates system parameters from a single observation using kernel-based score.
problem Estimating parameters of a dynamical system from a high-dimensional signal.
method Kernel-based score to compare temporal dependencies between signal and model.
result Accuracy and efficiency demonstrated on chaotic systems.
Analyzes generalization error in distributed linear regression.
problem Understanding generalization performance in distributed learning.
method Analytical characterization of generalization error in linear regression with distributed learning.
result Generalization error increases dramatically when nodes estimate close to the number of observations.
Paper presents a method to reduce prediction variance of DNNs for unknown systems.
problem Uncertainty in DNN predictions due to high variance.
method Ensemble averaging of multiple DNN models trained independently.
result Reduction in variance of DNN predictions, improving reliability.
New algorithm solves composite optimization problems with unknown expectations.
problem Solving composite optimization problems with unknown statistical expectations.
method Proposes a new stochastic primal-dual algorithm for composite optimization problems with unknown statistical expectations.
result Converges to a saddle point of the Lagrangian function.
Unknown constraints arise in many types of expensive black-box optimization problems. Several methods have been proposed recently for performing Bayesian optimization with constraints, based on the expected improvement (EI) heuristic. However, EI can lead to pathologies when used with constraints. For example, in the c…
Bayesian model learns multiscale interactions in complex systems.
problem Understanding dynamic interplay between processes at different time scales.
method Bayesian learning framework with Particle Gibbs with Ancestor Sampling (PGAS) algorithm.
result Demonstrated the effectiveness of the proposed approach through simulations.
We use surgery along 2-tori embedded in a union of two copies of a product of punctured 2-tori to produce a new collection of homotopy 4-spheres (4-manifolds homotopy equivalent to S4 and hence homeomorphic to S4 but possibly not diffeomorphic to S4). It is still unknown if these new examples are in fact exoti…
We study pool-based active learning with abstention feedbacks, where a labeler can abstain from labeling a queried example with some unknown abstention rate. This is an important problem with many useful applications. We take a Bayesian approach to the problem and develop two new greedy algorithms that learn both the c…
Develops a data-driven fault diagnosis framework for time-series data.
problem Fault diagnosis of dynamic systems using imbalanced and unknown fault classes.
method Kullback-Leibler divergence, data-driven fault classification, open-set classification.
result Framework handles imbalanced datasets, class overlapping, and unknown faults.
Deep neural networks with memory learn reduced equations from partial data.
problem Constructing governing equations for unknown dynamical systems from limited data.
method Formulate a discrete approximation of memory integrals, use deep neural networks to incorporate history terms.
result Deep neural networks can learn reduced equations with memory from partial data.
Recent work on Bayesian optimization has shown its effectiveness in global optimization of difficult black-box objective functions. Many real-world optimization problems of interest also have constraints which are unknown a priori. In this paper, we study Bayesian optimization for constrained problems in the general ca…
We recall the theory of linear discrete Riemann surfaces and show how to use it in order to interpret a surface embedded in R^3 as a discrete Riemann surface and compute its basis of holomorphic forms on it. We present numerical examples, recovering known results to test the numerics and giving the yet unknown period m…
Factor analysis is broadly used as a powerful unsupervised machine learning tool for reconstruction of hidden features in recorded mixtures of signals. In the case of a linear approximation, the mixtures can be decomposed by a variety of model-free Blind Source Separation (BSS) algorithms. Most of the available BSS alg…
Inverse optimal control, also known as inverse reinforcement learning, is the problem of recovering an unknown reward function in a Markov decision process from expert demonstrations of the optimal policy. We introduce a probabilistic inverse optimal control algorithm that scales gracefully with task dimensionality, an…
Proposes a learned Bayesian Cramér-Rao bound for unknown measurement models.
problem Computing the Bayesian Cramér-Rao bound requires full knowledge of priors and measurement distributions.
method Introduces a Physics-encoded score neural network to learn priors and measurements.
result Demonstrates improved sample complexity and interpretability through domain knowledge incorporation.
New convergence guarantees for learning with unknown nuisance parameters.
problem Learning problems with unknown nuisance parameters.
method Stochastic gradient optimization with Neyman orthogonality and approximately orthogonalized updates.
result Stochastic gradient algorithms can converge under conditions of nuisance parameters.
In this paper we formulate the nonnegative matrix factorisation (NMF) problem as a maximum likelihood estimation problem for hidden Markov models and propose online expectation-maximisation (EM) algorithms to estimate the NMF and the other unknown static parameters. We also propose a sequential Monte Carlo approximatio…