arXiv research

A new method for sparse Gaussian process regression using correlated experts.

Bayesian model fuses multiple classifiers with explicit correlation modeling.

Many predictive tasks, such as diagnosing a patient based on their medical chart, are ultimately defined by the decisions of human experts. Unfortunately, encoding experts' knowledge is often time consuming and expensive. We propose a simple way to use fuzzy and informal knowledge from experts to guide discovery of int…

The paper presents a novel approach to multi-output regression using probabilistic circuits.

Paper forecasts corporate default risk using Particle MCMC with expert opinions.

This paper considers the challenge of evaluating a set of classifiers, as done in shared task evaluations like the KDD Cup or NIST TREC, without expert labels. While expert labels provide the traditional cornerstone for evaluating statistical learners, limited or expensive access to experts represents a practical bottl…

A new method for faster prediction in distributed Gaussian processes.

STAR improves equivariant and invariant representation learning by routing projection heads.

Improved CI test for heteroskedastic data enhances causal discovery.

A new CoVaR framework integrates expert views using entropy pooling.

Enhances multimodal generation with Normalizing Flows and correlation analysis.

We present DRLViz, a visual analytics interface to interpret the internal memory of an agent (e.g. a robot) trained using deep reinforcement learning. This memory is composed of large temporal vectors updated when the agent moves in an environment and is not trivial to understand due to the number of dimensions, depend…

Worst-case bounds on the expected shortfall risk given only limited information on the distribution of the random variables has been studied extensively in the literature. In this paper, we develop a new worst-case bound on the expected shortfall when the univariate marginals are known exactly and additional expert inf…

Interpretable surrogates of black-box predictors trained on high-dimensional tabular datasets can struggle to generate comprehensible explanations in the presence of correlated variables. We propose a model-agnostic interpretable surrogate that provides global and local explanations of black-box classifiers to address …

Automatic methods for generating state-of-the-art neural network architectures without human experts have generated significant attention recently. This is because of the potential to remove human experts from the design loop which can reduce costs and decrease time to model deployment. Neural architecture search (NAS)…

ICIL learns policies invariant to multiple environments, improving generalization.

Logistic regression can handle noisy labels effectively when labels are imperfectly assigned by multiple experts.

Gryffin optimizes categorical variables in materials design, leveraging expert knowledge.

Proves EM algorithm guarantees for hierarchical imitation learning.

Multi-expert L2D underfits more severely, requiring new methods.

Since manually labeling training data is slow and expensive, recent industrial and scientific research efforts have turned to weaker or noisier forms of supervision sources. However, existing weak supervision approaches fail to model multi-resolution sources for sequential data, like video, that can assign labels to in…

Model identifies key problems in HIV patients' records.

TENP prunes experts and neurons in Mixture-of-Experts models for efficient deployment.

A method to select important experts for Gaussian processes to balance computational efficiency and uncertainty quantification.

Cash managers make daily decisions based on predicted monetary inflows from debtors and outflows to creditors. Usual assumptions on the statistical properties of daily net cash flow include normality, absence of correlation and stationarity. We provide a comprehensive study based on a real-world cash flow data set from…

We consider the problem of contextual bandits with stochastic experts, which is a variation of the traditional stochastic contextual bandit with experts problem. In our problem setting, we assume access to a class of stochastic experts, where each expert is a conditional distribution over the arms given a context. We p…

This paper presents the development of a hybrid learning system based on Support Vector Machines (SVM), Adaptive Neuro-Fuzzy Inference System (ANFIS) and domain knowledge to solve prediction problem. The proposed two-stage Domain Knowledge based Fuzzy Information System (DKFIS) improves the prediction accuracy attained…

Improved time series forecasting with expert loss integration.

In this paper, we model dependence between operational risks by allowing risk profiles to evolve stochastically in time and to be dependent. This allows for a flexible correlation structure where the dependence between frequencies of different risk categories and between severities of different risk categories as well …

HS-MoE selects sparse experts using adaptive priors and data-adaptive gating.

NAMEx merges experts using Nash bargaining for improved performance.

Expert augmentation improves hybrid model generalization.

New method calibrates Gaussian product experts for better predictions.

Meta-algorithm optimizes nonstochastic bandits with infinitely many experts.

New algorithm reduces expert prediction regret for two experts.

The article improves prediction by aggregating Kalman recursions online.

System uses conformal prediction to help experts make accurate decisions without understanding when to trust it.

Improved regret bounds for bandits with fixed expert advice using information theory.

Automated framework forecasts correlated time series in minutes.

Bayesian models combine experts with a flexible gating mechanism for complex data.

Advice-efficient prediction with expert advice (in analogy to label-efficient prediction) is a variant of prediction with expert advice game, where on each round of the game we are allowed to ask for advice of a limited number $M$ out of $N$ experts. This setting is especially interesting when asking for advice of ever…

The study aims to explore the strength of causal relationship between stock price search interest and real stock market outcomes on worldwide equity market indices. Such a phenomenon could also be mediated by investor behavior and extent of news coverage. The stock-specific internet search trends data and corresponding…

Reinforcement learning mimics expert behavior.

Adaptive Bayesian learning aggregates experts to improve performance.

Unified framework for policy learning using weak supervision.

New method aggregates Gaussian experts by detecting conditional independence violations.

Improved HMoE models using Laplace gating function enhance expert specialization and performance.

Optimal algorithm found for anytime regret with two experts.