arXiv research

Unified framework for causal models at different levels of abstraction.

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

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…

Study investigates how simple speech sounds can form abstract categories.

We introduce an algorithm for model-based hierarchical reinforcement learning to acquire self-contained transition and reward models suitable for probabilistic planning at multiple levels of abstraction. We call this framework Planning with Abstract Learned Models (PALM). By representing subtasks symbolically using a n…

New approach to abstract neural network representations using renormalization group.

Deep neural network learns discrete state abstractions for efficient planning.

Generative models use latent abstractions to create images.

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…

Develops models for temporally abstract reasoning and attention.

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

In the past few years, neural abstractive text summarization with sequence-to-sequence (seq2seq) models have gained a lot of popularity. Many interesting techniques have been proposed to improve seq2seq models, making them capable of handling different challenges, such as saliency, fluency and human readability, and ge…

Constellation learns group-level visual relationships for abstract reasoning.

Generates biomedical abstracts from titles, years, and keywords.

Abstract commensurators linked to topological models of solenoids.

In this work, we study abstractive text summarization by exploring different models such as LSTM-encoder-decoder with attention, pointer-generator networks, coverage mechanisms, and transformers. Upon extensive and careful hyperparameter tuning we compare the proposed architectures against each other for the abstractiv…

Attention mechanisms have been boosting the performance of deep learning models on a wide range of applications, ranging from speech understanding to program induction. However, despite experiments from psychology which suggest that attention plays an essential role in visual reasoning, the full potential of attention …

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…

Proposes method to learn state abstractions that generalize across environments.

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

PLOT uses optimal transport to find neural site handles for causal abstraction.

Abstract Morse index theorem applied to various optimization problems.

Enhances BO with expert preferences about abstract properties.

We study the problem of formally verifying the robustness to adversarial examples of support vector machines (SVMs), a major machine learning model for classification and regression tasks. Following a recent stream of works on formal robustness verification of (deep) neural networks, our approach relies on a sound abst…

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

Scalable verifier for recurrent neural networks using polyhedral abstractions.

Abstract Neural Networks (ANNs) improve DNN verification efficiency.

Predicting stochastic cellular dynamics as emerging from the mechanistic models of molecular interactions is a long-standing challenge in systems biology: low-level chemical reaction network (CRN) models give raise to a highly-dimensional continuous-time Markov chain (CTMC) which is computationally demanding and often …

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…

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

NHC learns scalable algorithmic solutions from diverse tasks.

STAR framework reduces OPE variance by distilling complex problems into discrete ARPs.

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.

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

Math theory explains how neural networks learn abstract representations.

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 …

In an abstract Wiener space setting, we constract a rigorous mathematical model of the one-loop approximation of the perturbative Chern-Simons integral, and derive its explicit asymptotic expansion for stochastic Wilson lines.

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…

We present an encoder-powered generative adversarial network (EncGAN) that is able to learn both the multi-manifold structure and the abstract features of data. Unlike the conventional decoder-based GANs, EncGAN uses an encoder to model the manifold structure and invert the encoder to generate data. This unique scheme …

CIB compresses variables causally, preserving key causal interactions.

Biological systems are often modelled at different levels of abstraction depending on the particular aims/resources of a study. Such different models often provide qualitatively concordant predictions over specific parametrisations, but it is generally unclear whether model predictions are quantitatively in agreement, …

We develop a method to learn abstract causal graphs from interventional data.

We consider a class of abstract nonlinear evolution equations in supermanifolds (smf's) modelled over Z_2-graded locally convex spaces. We show uniqueness, local existence, smoothness, and an abstract version of causal propagation of the solutions. If an a-priori estimate prevents the solutions from blowing-up then an …

Abstract discusses different corks.

Tasks like code generation and semantic parsing require mapping unstructured (or partially structured) inputs to well-formed, executable outputs. We introduce abstract syntax networks, a modeling framework for these problems. The outputs are represented as abstract syntax trees (ASTs) and constructed by a decoder with …

Can simple algorithms with a good representation solve challenging reinforcement learning problems? In this work, we answer this question in the affirmative, where we take "simple learning algorithm" to be tabular Q-Learning, the "good representations" to be a learned state abstraction, and "challenging problems" to be…

We present a training system, which can provably defend significantly larger neural networks than previously possible, including ResNet-34 and DenseNet-100. Our approach is based on differentiable abstract interpretation and introduces two novel concepts: (i) abstract layers for fine-tuning the precision and scalabilit…

Modular meta-learning is a new framework that generalizes to unseen datasets by combining a small set of neural modules in different ways. In this work we propose abstract graph networks: using graphs as abstractions of a system's subparts without a fixed assignment of nodes to system subparts, for which we would need …