arXiv research

XIMP improves molecular property prediction by integrating multiple graph representations.

Enhances BO with expert preferences about abstract properties.

Constellation learns group-level visual relationships for abstract reasoning.

Survey on algebraic fibers of group extensions and their finiteness properties.

A distinctive property of human and animal intelligence is the ability to form abstractions by neglecting irrelevant information which allows to separate structure from noise. From an information theoretic point of view abstractions are desirable because they allow for very efficient information processing. In artifici…

Unified framework for causal models at different levels of abstraction.

The paper focuses on various properties and applications of the homotopy operator, which occurs in the Poincaré lemma. In the first part, an abstract operator calculus is constructed, where the exterior derivative is an abstract derivative and the homotopy operator plays the role of an abstract integral. This operator …

In this paper, we develop a framework to obtain graph abstractions for decision-making by an agent where the abstractions emerge as a function of the agent's limited computational resources. We discuss the connection of the proposed approach with information-theoretic signal compression, and formulate a novel optimizat…

Slot Attention extracts object-centric representations from images.

Abstracts a theorem for non-smooth maps in infinite dimensions.

Abstract properties of hypersurface data analyzed in spherical symmetry.

The constructions of the virtual Euler (or moduli) cycles and their properties are explained and developed systematically in the general abstract settings.

Resolving abstract anaphora is an important, but difficult task for text understanding. Yet, with recent advances in representation learning this task becomes a more tangible aim. A central property of abstract anaphora is that it establishes a relation between the anaphor embedded in the anaphoric sentence and its (ty…

The paper introduces a method to learn Markov state abstractions for reinforcement learning.

It is known that finitely generated FI-modules over a field of characteristic 0 are Noetherian. We generalize this result to the abstract setting of an infinite EI category satisfying certain combinatorial conditions.

Artificial Neural Networks (ANNs) have demonstrated remarkable utility in various challenging machine learning applications. While formally verified properties of their behaviors are highly desired, they have proven notoriously difficult to derive and enforce. Existing approaches typically formulate this problem as a p…

O-minimal geometry generalizes both semialgebraic and subanalytic geometries, and has been very successful in solving special cases of some problems in arithmetic geometry, such as André-Oort conjecture. Among the many tools developed in an o-minimal setting are cohomology theories for abstract-definable continuous man…

Abstract: Survey on quadratic Hessian equations, their properties, and open problems.

The paper explores higher property T in lattices and its connections to geometric phenomena.

Abstract machinery finds obstructions to uniform positive scalar curvature.

We give an up-to-date perspective with a general overview of the theory of causal properties, the derived causal structures, their classification and applications, and the definition and construction of causal boundaries and of causal symmetries, mostly for Lorentzian manifolds but also in more abstract settings.

The paper develops a framework for abstracting causal models using category theory.

Abstraction is a fundamental part when learning behavioral models of systems. Usually the process of abstraction is manually defined by domain experts. This paper presents a method to perform automatic abstraction for network protocols. In particular a weakly supervised clustering algorithm is used to build an abstract…

simpcomp is an extension (a so called package) to GAP, the well known system for computational discrete algebra. The package enables the user to compute numerous properties of (abstract) simplicial complexes, provides functions to construct new complexes from existing ones and an extensive library of triangulations of …

As companies increase their efforts in retaining customers, being able to predict accurately ahead of time, whether a customer will churn in the foreseeable future is an extremely powerful tool for any marketing team. The paper describes in depth the application of Deep Learning in the problem of churn prediction. Usin…

The notion of chckerboard colorability for virtual links and abstract links is introduced. We study the Jones polynomials of virtual links and abstruct links. It is proved that a certain property of the Jones polynomials of classical links is valid for virtual links which admit checkerboard colorings.

SPEDER extracts state-action abstraction from dynamics for reinforcement learning.

The paper aims to mathematically define and learn abstractions from data.

Abstract MDPs enable strategic exploration and fast reward transfer in complex environments.

We are interested in global properties of systems of left-invariant differential operators on compact Lie groups: regularity properties, properties on the closedness of the range and finite dimensionality of their cohomology spaces, when acting on various function spaces e.g. smooth, analytic and Gevrey. Extending the …

This note focuses on some properties and uses of filtered deformations in the context of D=11 supergravity. We define the concept of abstract symbol and give a strong version of the Reconstruction Theorem, namely a bijective correspondence from the space of highly supersymmetric supergravity backgrounds to the space of…

The abstract discusses p-harmonic forms and their geometric properties, proving new theorems about Lp-cohomology.

Abstract: Characterizes special Kähler manifolds with specific properties.

The abstract discusses extensions of Jacobi groups and their orbit space properties.

The paper characterizes biconservative surfaces in hyperbolic 4-space.

New approach to abstract neural network representations using renormalization group.

Study investigates how simple speech sounds can form abstract categories.

Abstract Neural Networks (ANNs) improve DNN verification efficiency.

Algorithm finds latent structure in value functions for improved reinforcement learning.

In this paper we discuss algebraic, combinatorial and topological properties of singular virtual braids. On the algebraic side we state the relations between classical and virtual singular objects, in addition we discuss a Birman-like conjecture for the virtual case. On the topological and combinatorial side, we prove …

Abstraction plays a key role in concept learning and knowledge discovery; this paper is concerned with computational abstraction. In particular, we study the nature of abstraction through a group-theoretic approach, formalizing it as symmetry-driven---as opposed to data-driven---hierarchical clustering. Thus, the resul…

A collection of the accepted abstracts for the Machine Learning for Health (ML4H) workshop at NeurIPS 2019. This index is not complete, as some accepted abstracts chose to opt-out of inclusion.

In this paper it was developed a modification of the known multiagent model Minority Game, designed to simulate the behavior of traders in financial markets and the resulting price dynamics on the abstract resource. The model was implemented in the form of software. The modified version of Minority Game was investigate…

The paper proposes a principle for dynamically adjusting the granularity of reinforcement learning abstractions.

We present PubMed 200k RCT, a new dataset based on PubMed for sequential sentence classification. The dataset consists of approximately 200,000 abstracts of randomized controlled trials, totaling 2.3 million sentences. Each sentence of each abstract is labeled with their role in the abstract using one of the following …

TASID learns policies in high-dimensional settings with abstract simulator knowledge.

We prove a definable version of the Whitney embedding theorem for abstract-definable $\mathcal{C}^p$ manifolds with $1\leq p<\infty$, namely: every abstract-definable $\mathcal{C}^p$ manifold is abstract-definable $C^p$ embedded into $R^N$, for some positive integer $N$. As a consequence, we show that every abstract-de…

This paper simplifies OPE in large state spaces using state abstractions.