arXiv research

A new framework for adaptive behavior using reusable value profiles.

CompILE learns reusable segments from demonstrations for hierarchical task execution.

MCP learns reusable skills for complex tasks by combining simple ones.

The paper proposes reusable network components by making them compatible across tasks.

MSPM uses modular agents to manage financial portfolios efficiently.

This work explores how incorporating prior knowledge into reinforcement learning can lead to faster learning and transfer.

The paper examines how updates to probabilistic models influence behavior based on evidence.

This paper proposes a generic classification system designed to detect security threats based on the behavior of malware samples. The system relies on statistical features computed from proxy log fields to train detectors using a database of malware samples. The behavior detectors serve as basic reusable building block…

Generative model prices basket options efficiently.

CK simplifies ML model deployment and reproducibility with open APIs and DevOps.

The FAIRnets Ontology makes neural networks findable, accessible, interoperable, and reusable.

This work learns a default policy to speed up RL learning by restricting information it receives.

Integrates skills and world models for efficient task solving and transfer.

Successor Options discovers reusable skills using landmark states.

Probabilistic inference procedures are usually coded painstakingly from scratch, for each target model and each inference algorithm. We reduce this effort by generating inference procedures from models automatically. We make this code generation modular by decomposing inference algorithms into reusable program-to-progr…

We develop a technique for generalising from data in which models are samplers represented as program text. We establish encouraging empirical results that suggest that Markov chain Monte Carlo probabilistic programming inference techniques coupled with higher-order probabilistic programming languages are now sufficien…

New model shows hierarchical proof structure helps theorem provers.

Modular deep learning framework using pairwise labels without backpropagation.

ReSkill reconciles RL skill creation with policy optimization.

New method reduces fine-tuning cost for reused models.

Study allocates resources to strategic agents while balancing cost and incentives.

Paper analyzes CRL generalization under non-i.i.d. settings, providing bounds for practical data reuse.

Auto-encoding is an important task which is typically realized by deep neural networks (DNNs) such as convolutional neural networks (CNN). In this paper, we propose EncoderForest (abbrv. eForest), the first tree ensemble based auto-encoder. We present a procedure for enabling forests to do backward reconstruction by ut…

In many real-world applications, data are often collected in the form of stream, and thus the distribution usually changes in nature, which is referred as concept drift in literature. We propose a novel and effective approach to handle concept drift via model reuse, leveraging previous knowledge by reusing models. Each…

The paper develops a learning framework for diverse legged robots.

Method learns reusable actions from human demonstrations.

Signed compression progress on a sealed audit is goodhart-resistant.

Contextualized ML learns context-dependent effects using deep learning.

A neural network learns relational representations from raw data.

Baconian simplifies MBRL experiments by providing a flexible framework.

Martingale Doppelgänger-Eval benchmarks VLMs on candlestick evidence vs. trend extrapolation

New algorithm corrects bias in LDP-released data for better analysis.

Automated discovery of adaptive attacks improves adversarial defense evaluation.

ModSSC unifies semi-supervised classification for various data types.

Several methods were recently proposed for the task of translating images between domains without prior knowledge in the form of correspondences. The existing methods apply adversarial learning to ensure that the distribution of the mapped source domain is indistinguishable from the target domain, which suffers from kn…

VSML unifies meta learning concepts and enables simple backpropagation.

This paper analyzes and improves active learning techniques for real-world projects.

Framework reconstructs missing spatio-temporal data for extreme value prediction.

New method learns temporal abstractions by defining interest functions.

Inference for GP models with non-Gaussian noises is computationally expensive when dealing with large datasets. Many recent inference methods approximate the posterior distribution with a simpler distribution defined on a small number of inducing points. The inference is accurate only when data points have strong corre…

The recent proliferation of richly structured probabilistic models raises the question of how to automatically determine an appropriate model for a dataset. We investigate this question for a space of matrix decomposition models which can express a variety of widely used models from unsupervised learning. To enable mod…

DeepSwarm uses swarm intelligence to optimize CNN architectures.

cuSLINK clusters data faster on GPUs, saving space and time.

ANN predicts methane heat transfer in rocket engines efficiently.

Deep tabular models outperform GBDT in medical diagnosis tasks.

Framework for lifelong learning of compositional structures.

Proposes Continuous Graph Flow for modeling graph data.

Unified approach for learning state representations from streaming data.