Study restricts causal graphs with expert knowledge.
problem Restricting causal graphs to include expert orientation knowledge.
method Prove properties, present new orientation rules, develop algorithms.
result Shows how to uniquely represent restricted essential ancestral graphs.
Deep network compression has been achieved notable progress via knowledge distillation, where a teacher-student learning manner is adopted by using predetermined loss. Recently, more focuses have been transferred to employ the adversarial training to minimize the discrepancy between distributions of output from two net…
End-to-end dialogue model learns from joint embeddings and user intent.
problem Challenges in reasoning and incorporating state-full knowledge in goal-oriented dialogues.
method Proposes an RNN-based end-to-end encoder-decoder architecture trained with joint embeddings and multi-task learning.
result Improves task-oriented dialogue system performance as shown by BLEU score evaluation.
The Knowledge Base (KB) used for real-world applications, such as booking a movie or restaurant reservation, keeps changing over time. End-to-end neural networks trained for these task-oriented dialogs are expected to be immune to any changes in the KB. However, existing approaches breakdown when asked to handle such c…
AOI algorithm improved predictive maintenance accuracy.
problem Improving predictive maintenance accuracy in industrial assets.
method Extended AOI algorithm with LSTM for anomaly detection and RUL calculation.
result Methodology accurately detected anomalies and calculated RUL with high precision.
We outline the current state of knowledge regarding geometric inequalities of systolic type, and prove new results, including systolic freedom in dimension 4. Namely, every compact, orientable, smooth 4-manifold X admits metrics of arbitrarily small volume such that every orientable, immersed surface of smaller than un…
Proposes using equivariant generative models for compressed sensing with unknown orientations.
problem Recovering signals with unknown orientations from underdetermined systems of linear measurements.
method Equivariant variational autoencoder as a generative prior for compressed sensing.
result Signals with unknown orientations can be recovered using iterative gradient descent on the latent space of equivariant models.
Designs a framework to transfer causal models between similar environments.
problem Transferability of causal models between different but similar environments.
method Object-oriented representations and continuous optimization for structure learning.
result Demonstrates advantages in gridworld settings using reinforcement learning.
Method recovers particle orientations from cryo-EM projections.
problem Unknown orientations in cryo-EM images.
method Two-step process: estimating distances and recovering orientations.
result Accurate orientation recovery from noisy projections.
A new method for embedding temporal relationships in graphs.
problem Limited performance of existing time-aware graph embedding methods.
method Integrates temporal smoothness and task-oriented negative sampling.
result Improves performance in various tasks, especially entity/relationship/temporal scoping prediction.
Solves TOD systems' query annotation problem without explicit annotations.
problem Training TOD systems without explicit KB query annotation.
method Reinforcement learning (RL) and pipelined approach for query prediction and system training.
result Improved RL agent with modifications for TOD tasks.
In this paper we provide a systematic treatment of Willmore surfaces with orientation reversing symmetries and illustrate the theory by (old and new) examples. We apply our theory to isotropic Willmore two-spheres in S4 and derive a necessary condition for such ( possibly branched) isotropic surfaces to descend to (…
Paper classifies solutions to oriented associativity equations on flat F-manifolds.
problem Classifying quasi-homogeneous formal power series solutions.
method Introducing monodromy local moduli and solving Riemann-Hilbert-Birkhoff problem.
result Formal germs of flat F-manifolds are convergent if not strictly doubly resonant.
Machine learning constructs problem-based medical records from electronic health records.
problem Difficulty in finding relevant medical information for clinical questions.
method Knowledge base completion using machine learning on electronic health records.
result Automatic construction of problem-based groupings of medications, procedures, and lab tests.
Task-oriented dialog presents a difficult challenge encompassing multiple problems including multi-turn language understanding and generation, knowledge retrieval and reasoning, and action prediction. Modern dialog systems typically begin by converting conversation history to a symbolic object referred to as belief sta…
The article proves properties of Seifert links and their cyclic branched covers.
problem Properties of Seifert links and their cyclic branched covers.
method Left-orderability, co-oriented taut foliations, and L-space properties. result Proves the ADE link conjecture for Seifert links. This paper compares deep learning and knowledge-based methods for pedestrian trajectory prediction.
problem Predicting pedestrian trajectories in crowded scenes is challenging due to external factors.
method Comprehensive comparison of deep learning and knowledge-based models.
result Deep learning models outperform knowledge-based models in local trajectory prediction.
FairDTD improves fairness in GNNs by distilling dual teacher knowledge, balancing utility and bias.
problem Bias in GNN predictions due to sensitive attributes.
method Dual-Teacher Distillation with a causal graph model, feature and structure teachers, and graph-level distillation.
result Achieves optimal fairness while preserving high model utility.
In this paper we propose a novel index to quantify and measure the flow of information on macro and micro scales. We discuss the implications of this index for knowledge management fields and also as intellectual capital that can thus be utilized by entrepreneurs. We explore different function and human oriented metric…
Robot learns multiple tasks hierarchically by transferring knowledge.
problem Learning multiple complex tasks in open-ended environments.
method Task-oriented procedures, goal-babbling, imitation learning, active learning, intrinsic motivation.
result Robots can learn complex tasks more efficiently by transferring knowledge from simpler ones.
A new method improves EEG classification across subjects efficiently.
problem Challenges in adapting and retaining knowledge for EEG classifiers across different subjects.
method Meta UPdate Strategy (MUPS-EEG) for continuous EEG classification.
result Outperforms current state-of-the-art methods in adapting to new subjects and retaining knowledge of learned subjects.
New concepts of barriers and black regions defined for Lorentzian manifolds.
problem Understanding causal world-lines and horizons in Lorentzian manifolds.
method Proving properties of null hypersurfaces and their causal world-lines.
result Null hypersurfaces are semi-permeable, leading to new concepts of barriers and black regions.
We integrate camera pose correlations into deep models using Gaussian processes.
problem Lack of inter-frame reasoning in deep neural networks.
method Derive a principled framework combining camera pose information with deep models using a novel view kernel.
result Soft-prior knowledge aids pose-related vision tasks like novel view synthesis.
The crosscap number of a knot is an invariant describing the non-orientable surface of smallest genus that the knot bounds. Unlike knot genus (its orientable counterpart), crosscap numbers are difficult to compute and no general algorithm is known. We present three methods for computing crosscap number that offer varyi…
The study optimizes sampling in complex systems with probabilistic response distributions.
problem Calibrating and optimizing complex systems with probabilistic response distributions.
method Non-parametric Bayesian approach to modeling spatial fields of probability distributions, introducing adaptive sampling strategies.
result Adaptive sampling strategies improve system evaluations by guiding focus towards key features.
In this paper, we propose a new perspective for quantizing a signal and more specifically the channel state information (CSI). The proposed point of view is fully relevant for a receiver which has to send a quantized version of the channel state to the transmitter. Roughly, the key idea is that the receiver sends the r…
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.
Let M be a compact oriented d-dimensional smooth manifold. Chas and Sullivan have defined a structure of Batalin-Vilkovisky algebra on H∗(LM). Extending work of Cohen, Jones and Yan, we compute this Batalin-Vilkovisky algebra structure when M is a sphere Sd, d≥1. In particular, we show that $…
In this paper, we propose a deep reinforcement learning (DRL) solution to the grasping problem using 2.5D images as the only source of information. In particular, we developed a simulated environment where a robot equipped with a vacuum gripper has the aim of reaching blocks with planar surfaces. These blocks can have …
Proof of Thurston's earthquake theorem using Anti-de Sitter geometry.
problem Proving Thurston's earthquake theorem for orientation-preserving homeomorphisms.
method Using the bi-invariant geometry of Anti-de Sitter three-space.
result Provided a proof of Thurston's earthquake theorem.
New split rules improve subpopulation targeting in policy-making.
problem Improving binary classification for subpopulation targeting in policy-making.
method MDFS, PFS, wEFS for maximizing distance and penalizing final splits.
result Proposed methods target more vulnerable subpopulations than classic CART/KD-CART.
Cryo-electron microscopy (cryo-EM) is a powerful technique for determining the structure of proteins and other macromolecular complexes at near-atomic resolution. In single particle cryo-EM, the central problem is to reconstruct the three-dimensional structure of a macromolecule from 104−7 noisy and randomly orien…
Method analyzes hyperparameters using HSIC for better neural network performance.
problem Complex hyperparameter spaces in deep learning.
method Goal-oriented sensitivity analysis using HSIC.
result Robust analysis index quantifies hyperparameters' impact.
We present a construction of a canonical G_2 structure on the unit sphere tangent bundle S_M of any given orientable Riemannian 4-manifold M. Such structure is never geometric or 1-flat, but seems full of other possibilities. We start by the study of the most basic properties of our construction. The structure is co-ca…
Study on oriented disingquandles for distinguishing singular links.
problem Distinguishing singular links of different colors.
method Introduced oriented dichromatic singular links and oriented disingquandles to define invariants.
result Found invariants that can distinguish some singular links.
Given integers g,n≥0 satisfying 2−2g−n<0, let Mg,n be the moduli space of connected, oriented, complete, finite area hyperbolic surfaces of genus g with n cusps. We study the global behavior of the Mirzakhani function B:Mg,n→R≥0 which assigns to $X…
The incorporation of prior knowledge into learning is essential in achieving good performance based on small noisy samples. Such knowledge is often incorporated through the availability of related data arising from domains and tasks similar to the one of current interest. Ideally one would like to allow both the data f…
This paper extends the results from the author's previous paper to consider finite, fiber- and orientation- preserving group actions on closed, orientable Seifert manifolds M that fiber over a non-orientable base space. An orientable base space double cover M~ of M is constructed and then an isomorphism be…
Paper proves achiral Lefschetz fibrations from non-orientable Lefschetz fibrations.
problem Understanding achiral Lefschetz fibrations from non-orientable ones.
method Composition of standard orientation double covering map and non-orientable Lefschetz fibration.
result Specification of a monodromy factorization for the composition.
Analog of Kauffman bracket for non-orientable knots in thickened surface.
problem Defining an invariant for non-orientable knots in a non-orientable surface.
method Proposes an analog of the Kauffman bracket polynomial with modified sign rules.
result Polynomial is an isotopy invariant and independent of classical Kauffman for orientable covers.
Study trisections of non-orientable 4-manifolds with boundary.
problem Understanding trisections in non-orientable 4-manifolds.
method Introduced trisections of non-orientable 4-manifolds with boundary, proved a non-orientable analogue of a theorem, and discussed adaptation of trisection theory.
result Existence of trisection diagrams and Kirby diagrams for closed non-orientable 4-manifolds.
Sym-NCO leverages symmetricities to improve DRL-NCO performance.
problem Improving neural combinatorial optimization methods.
method Sym-NCO is a regularizer-based training scheme that exploits universal symmetricities in CO problems and solutions.
result Sym-NCO significantly improves DRL-NCO performance across various CO tasks.
To any generic curve in an oriented surface there corresponds an oriented chord diagram, and any oriented chord diagram may be realized by a curve in some oriented surface. The genus of an oriented chord diagram is the minimal genus of an oriented surface in which it may be realized. Let g_n denote the expected genus o…
Study curves in non-orientable surfaces with specific intersection properties.
problem Enumerate and understand curves in non-orientable surfaces with intersection constraints.
method Generalized construction of Malestein-Rivin-Theran to non-orientable surfaces.
result Lower bound for maximum number of curves in generic non-orientable surface.
The study establishes conditions for orientability in spaces with lower Ricci curvature bounds.
problem Conditions for orientability in spaces with lower Ricci curvature bounds.
method Equivalent characterizations of orientability using Ricci limit and RCD spaces.
result Four-manifolds with Ricci curvature bounded below and volume non-collapsing are uniformly locally orientable.
Study fiber-preserving, orientation-reversing involutions on Seifert fibered 3-manifolds.
problem Characterize fiber-preserving, orientation-reversing involutions on Seifert fibered 3-manifolds.
method Construct a class of involutions, extend product involutions, and use double covering.
result Any fiber-preserving, orientation-reversing involution factors as a product of an orientation-preserving and a specific class of involutions.
Study shortest non-separating curves on non-orientable surfaces, proving NP-hardness and tractability.
problem Computing shortest non-separating simple closed curves on non-orientable surfaces.
method Developed tools for computing shortest curves, proving NP-hardness and tractability.
result Proved NP-hardness and fixed-parameter tractability for computing shortest orienting curves, and polynomial-time algorithm for non-orienting curves.
This work presents MeKDDaM-SAGA, computer-aided automation software for implementing a novel knowledge discovery and data mining process model that was designed for performing justifiable, traceable and reproducible metabolomics data analysis. The process model focuses on achieving metabolomics analytical objectives an…