Improves model accuracy for neural nets in stochastic dynamics with partial prior knowledge.
problem Stability and accuracy in neural nets modeling stochastic dynamics with many parameters.
method Three steps: probabilistic weights, partial knowledge incorporation, and PAC-Bayesian training.
result Improved model fit with partial and noisy prior knowledge.
Arriving at the complete probabilistic knowledge of a domain, i.e., learning how all variables interact, is indeed a demanding task. In reality, settings often arise for which an individual merely possesses partial knowledge of the domain, and yet, is expected to give adequate answers to a variety of posed queries. Tha…
New method learns from non-uniform data and partial physical knowledge.
problem Identifying dynamical systems from non-uniformly sampled data.
method Physics-informed neural networks integrating numerical integration methods.
result Learning unknown kinetic rates and estimating parameters from non-uniform data.
RID framework quantifies and regularizes task-relevant knowledge in distillation.
problem Distilling irrelevant information can hinder student model performance.
method Partial Information Decomposition to quantify and regularize task-relevant knowledge.
result RID framework leads to more resilient distillation under nuisance teachers.
Reinforcement learning would enjoy better success on real-world problems if domain knowledge could be imparted to the algorithm by the modelers. Most problems have both hidden state and unknown dynamics. Partially observable Markov decision processes (POMDPs) allow for the modeling of both. Unfortunately, they do not p…
New method learns frequency-dependent partial correlations.
problem Learning dependencies across distinct frequency bands.
method Formulate and solve two nonconvex learning problems.
result Proposed methods outperform existing state of the art.
Novel framework for learning infinitesimal generator of stochastic processes.
problem Challenges in learning infinitesimal generator due to unbounded nature and state space dimensionality.
method Introduces a novel framework based on energy functional, integrates physical priors, and uses reduced-rank estimator in RKHS.
result Learning bounds independent of state space dimension and non-spurious spectral estimation.
Reconstructing a planar domain from its Dirichlet-to-Neumann data
problem Reconstructing a planar domain from its Dirichlet-to-Neumann data
method Using the Hilbert transform of the boundary curve
result Reconstructing a simply connected planar domain from the DN data
Enhancing spectral embedding for low-dimensional embeddings in rare disease cohorts
problem Representing clinical concepts and patients in electronic health records
method Spectral-based unsupervised learning with flexible knowledge transfer
result Outperforms competing approaches in challenging scenarios
Proposes SPCA to incorporate structural constraints in model identification.
problem Model identification with partial structural knowledge.
method Structural Principal Component Analysis (SPCA) that leverages structural information.
result Demonstrates improved model estimates using synthetic and industrial data.
KG-A2C agent learns natural language IF games by reasoning and constraining action spaces.
problem Challenges of natural language understanding, partial observability, and combinatorially large action spaces in IF games.
method Builds a dynamic knowledge graph while exploring, constraining actions using templates.
result Outperforms current IF agents across various games with larger action spaces.
Cluster-DAGs improve causal discovery with prior knowledge.
problem Finding cause-effect relationships from high-dimensional data.
method Cluster-DAGs as prior knowledge framework, modified constraint-based algorithms Cluster-PC and Cluster-FCI.
result Cluster-PC and Cluster-FCI outperform baselines without prior knowledge.
Many interesting real world domains involve reinforcement learning (RL) in partially observable environments. Efficient learning in such domains is important, but existing sample complexity bounds for partially observable RL are at least exponential in the episode length. We give, to our knowledge, the first partially …
Recent work in learning ontologies (hierarchical and partially-ordered structures) has leveraged the intrinsic geometry of spaces of learned representations to make predictions that automatically obey complex structural constraints. We explore two extensions of one such model, the order-embedding model for hierarchical…
Centuries of development in natural sciences and mathematical modeling provide valuable domain expert knowledge that has yet to be explored for the development of machine learning models. When modeling complex physical systems, both domain knowledge and data provide necessary information about the system. In this paper…
Oracle-efficient algorithm for offline RL with partial data coverage.
problem Offline reinforcement learning with partial data coverage and constraints.
method PDOCRL, a primal-dual algorithm with decomposed linear-programming formulation.
result Near-optimal, near-feasible policy with \(\widetilde{\mathcal O}(ε^{-2})\) sample guarantee.
We prove that if ( M , g ) (M,g) ( M , g ) is a topological 3-ball with a C 4 C^4 C 4 -smooth Riemannian metric g g g , and mean-convex boundary ∂ M \partial M ∂ M then knowledge of least areas circumscribed by simple closed curves γ ⊂ ∂ M γ\subset \partial M γ ⊂ ∂ M uniquely determines the metric g g g , under some additional geometric assumptions. These are that g g g …
KalmanNet uses neural networks to improve state estimation in systems with unknown dynamics.
problem State estimation of systems with non-linear dynamics and partial information.
method KalmanNet integrates a recurrent neural network with the Kalman filter to handle non-linearities and model mismatches.
result KalmanNet outperforms classic filtering methods in systems with both mismatched and accurate domain knowledge.
Improved CI test for heteroskedastic data enhances causal discovery.
problem CI testing assumptions fail in heteroskedastic data.
method Adapted partial correlation CI test for heteroskedastic noise.
result The adapted test outperforms standard CI test in heteroskedastic cases.
Method learns relational features for Gaifman models from knowledge bases.
problem Structure learning for Gaifman models.
method Relational tree distances to learn relational features.
result Empirical evaluation shows superiority over classical rule-learning.
Proposes a method to identify causal relationships using background knowledge.
problem Identifying causal relationships in the presence of background knowledge.
method Learning local structure using all types of causal background knowledge (direct, non-ancestral, ancestral). Criteria for identifying causal relationships based on local structure.
result Effective and efficient method for local structure learning and causal relationship identification.
We infer both microscopic and macroscopic behaviors of a three-dimensional chaotic fluid flow using reservoir computing. In our procedure of the inference, we assume no prior knowledge of a physical process of a fluid flow except that its behavior is complex but deterministic. We present two ways of inference of the co…
Introduces a rule-based Bayesian regression for better uncertainty quantification and expert knowledge integration.
problem Handling regression problems with uncertainty quantification and expert intuition.
method Combines Bayesian inference and rule-based systems for better model performance.
result Improves model performance with better uncertainty quantification and point predictions.
New bounds for PDA using partial optimal transport improve domain alignment.
problem Scarcity of labeled target data with abundant source data.
method Derive theoretical bounds based on partial optimal transport.
result Theoretical bounds support partial Wasserstein distance for domain alignment.
Enhances neural operators with physics knowledge for more accurate simulations.
problem Improving accuracy and generalization of neural operators for physical systems.
method Jointly learns from original PDEs and simplified forms, incorporating fundamental physics.
result Significant improvement in nRMSE across various PDE problems.
The paper develops methods to estimate POMDPs from partial information.
problem Making decisions under partial information about state variables.
method Structural estimation of POMDP primitives using observable history.
result Conditions for model identifiability without state dynamics knowledge.
New method for comparing different mass measures on tree structures using entropy partial transport.
problem Comparing nonnegative measures with different masses on tree structures.
method Entropy Partial Transport (EPT) on extended trees, regularized for fast computation and negative definiteness.
result First closed-form solution for unbalanced OT on tree structures.
b-LOAD extends local causal discovery with prior knowledge, improving causal effect estimation.
problem Local causal discovery struggles in data-scarce settings due to uncertainty and incomplete neighborhoods.
method b-LOAD incorporates prior knowledge directly into local structure learning, using Meek's rules to refine discovery.
result b-LOAD refines the admissible equivalence class and enlarges identifiable causal queries, improving causal effect estimation.
Bayesian approach for solving systems of linear PDEs with boundary conditions.
problem Modeling data efficiently with prior knowledge from systems of linear PDEs.
method Construct multi-output Gaussian process priors using Gröbner bases and pullback parametrizations.
result Gaussian process priors can represent solutions to systems of linear PDEs adhering to boundary conditions.
Since time immemorial, people have been looking for ways to organize scientific knowledge into some systems to facilitate search and discovery of new ideas. The problem was partially solved in the pre-Internet era using library classifications, but nowadays it is nearly impossible to classify all scientific and popular…
Integrates skills and world models for efficient task solving and transfer.
problem Quickly solve new tasks in complex environments using reusable knowledge.
method Leverages partial amortization for fast adaptation and online skill planning.
result Improved sample efficiency in single tasks and transfer between tasks.
Framework uses physics knowledge to improve spatiotemporal prediction with limited data.
problem Challenges in modeling physical systems with limited real-world data.
method Physics-aware meta-learning with auxiliary tasks, incorporating PDE-independent spatial and temporal modules.
result Framework outperforms in spatiotemporal prediction tasks with limited data.
New algorithms solve partial optimal transport problems for applications like PU learning.
problem Optimal transport constraints on equal mass distributions limit applicability.
method Developed exact algorithms for partial Wasserstein and Gromov-Wasserstein problems.
result Partial Wasserstein metrics show effectiveness in positive-unlabeled learning.
New algorithm proves RL from partial obs is feasible.
problem Difficulty in learning from partial observability.
method Optimism combined with MLE for weakly revealing POMDPs.
result Simple algorithm guarantees polynomial sample efficiency.
The paper analyzes extreme risk measures with limited distributional information.
problem Investigating risk measures under partial knowledge of distribution moments and shape.
method Employing probability inequalities and modified Schwarz inequality to derive bounds on distortion risk measures.
result Unified framework for calculating best- and worst-case scenarios of distortion risk measures.
A tutorial on optimizing complex functions with partial knowledge.
problem Optimizing functions with limited or partial information.
method Grey-box Bayesian optimization, blending black-box and white-box approaches.
result Improves optimization performance by leveraging internal information.
Extracts geometric information from point-clouds for multiclass classification.
problem Multiclass Classification with labeled point-clouds.
method Stochastic partial orderings and label embedding trees.
result Computes multiscale geometries for explainable prediction and error-free labeling.
Transformer learns to infer partial MDPs for efficient in-context adaptation and exploration.
problem Efficiently adapt and explore in-context without gradient-based updates.
method Uses a transformer to learn inference from training tasks, considering hypothesis space of partial models.
result Adaptation speed and exploration-exploitation balance approach those of an exact posterior sampling oracle.
Identifies causal effects in partially directed acyclic graphs with observed variables.
problem Identifying conditional causal effects in graphs with background knowledge and observed variables.
method Three results: identification formula, do calculus generalization, and algorithm completeness.
result Complete algorithm for identifying conditional effects in MPDAGs.
ParKCa combines multiple causal inference methods to infer new causes from known and unknown factors.
problem Causal inference from observational data when randomized experiments are not feasible.
method ParKCa uses a stacking approach to combine results from multiple causal inference methods.
result ParKCa infers more causes than existing methods in real-world and simulated datasets.
Paper tackles robust knowledge transfer in parallel RL tasks.
problem Transfer knowledge from low-tier to high-tier tasks in parallel RL without shared dynamics or reward functions.
method Identifies Optimal Value Dominance condition and proposes online learning algorithms for both tasks.
result Achieves constant regret on partial states and near-optimal regret when tasks are dissimilar.
The paper develops algorithms for competitive RL in partially observable MGs.
problem Challenges in reinforcement learning with function approximation and partial observability.
method Proposes posterior sampling methods for self-play and adversarial learning in zero-sum MGs.
result Developed algorithms achieve low regret bounds scaling sublinearly with GEC and episode number.
We derive upper bounds on the complexity of ReLU neural networks approximating the solution maps of parametric partial differential equations. In particular, without any knowledge of its concrete shape, we use the inherent low-dimensionality of the solution manifold to obtain approximation rates which are significantly…
This paper introduces glocal explanations for expected goal models in soccer.
problem Limited interpretability of expected goal models trained with black-box methods.
method Proposes glocal explanations using aggregated SHAP values and partial dependence profiles.
result Extracts knowledge from expected goal models for teams and players, enhancing performance analysis.
Paper characterizes and represents pairwise causal background knowledge for improved causal inference.
problem Improving causal inference by handling pairwise causal constraints.
method Graphical characterization, direct causal clause (DCC), unified representation, MPDAG, polynomial-time algorithms.
result Pairwise causal background knowledge uniquely decomposes into MPDAG and DCCs, improving causal effect identification.
Optimistic Q-learning reduces sample complexity for systems with known dynamics.
problem Sample efficiency in reinforcement learning with partial dynamics knowledge.
method Optimistic Q-learning algorithm for systems with additive disturbance model.
result Achieves i l d e O ( e x t P o l y ( H ) T ) ilde{\mathcal{O}}( ext{Poly}(H)\sqrt{T}) i l d e O ( e x t P o l y ( H ) T ) regret under perfect knowledge of dynamics. This work improves knowledge distillation by transferring full kernel matrices efficiently.
problem Efficiently transferring full pairwise similarity matrices for model compression in deep learning.
method The authors propose a method to transfer the full similarity matrix effectively using the Nyström method, decomposing it into partial matrices.
result The difference between the full kernel matrices of teacher and student can be well bounded by partial matrices, improving optimization efficiency.
Derives Black-Scholes model without stochastic calculus or PDEs.
problem Deriving the Black-Scholes model without advanced math.
method Continuum limit of Binomial tree approach.
result Derives Black-Scholes model and exchange-option generalization.