arXiv research

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

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

In this paper, we propose a hierarchical feature-aware tracking framework for efficient visual tracking. Recent years, ensembled trackers which combine multiple component trackers have achieved impressive performance. In ensembled trackers, the decision of results is usually a post-event process, i.e., tracking result …

LMoE uses LLMs to improve stock trading by selecting experts based on textual and price data.

EBBS integrates expert assessments into MIO best-subsets problem.

Generalized algorithm for translation and scale-invariant prediction.

A new mechanism reduces expert belief regret in online forecasting.

New algorithm minimizes expert selection regret in partial bandit feedback.

Interactive IL algorithm queries noisy expert for feedback, reducing sample size.

Unified framework for SGMoE resolves estimation and selection issues.

New algorithms reduce label collection for online prediction with expert advice.

Active learning method for ABC statistics selection reduces expert work and improves posterior estimates.

VMoER improves uncertainty quantification in MoE layers for scalable foundation models.

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

Competency questions help experts select best clustering for energy data.

DSelect-k improves MoE models for multi-task learning with better performance and smoother training.

A fuzzy expert system selects stocks for BSE using AI techniques.

This paper tackles model selection for MoE models in high-dimensional data.

Paper proposes interpretable RL policies from a mixture of experts.

New model handles complex non-linear relationships with hidden graph structures.

Expert system predicts credit card charge-offs using macroeconomic indicators.

Investigates least squares estimation in deterministic MoE models.

We explore the problem of learning under selective labels in the context of algorithm-assisted decision making. Selective labels is a pervasive selection bias problem that arises when historical decision making blinds us to the true outcome for certain instances. Examples of this are common in many applications, rangin…

Societies often rely on human experts to take a wide variety of decisions affecting their members, from jail-or-release decisions taken by judges and stop-and-frisk decisions taken by police officers to accept-or-reject decisions taken by academics. In this context, each decision is taken by an expert who is typically …

The goal of task transfer in reinforcement learning is migrating the action policy of an agent to the target task from the source task. Given their successes on robotic action planning, current methods mostly rely on two requirements: exactly-relevant expert demonstrations or the explicitly-coded cost function on targe…

In real-world scenarios, data tends to exhibit a long-tailed distribution, which increases the difficulty of training deep networks. In this paper, we propose a novel self-paced knowledge distillation framework, termed Learning From Multiple Experts (LFME). Our method is inspired by the observation that networks traine…

Unified framework for expert selection with bandit and lower-bound feedback.

Paper proposes a novel method to accurately determine the number of experts in Gaussian-gated Gaussian MoE models.

Mixtures-of-Experts (MoE) are conditional mixture models that have shown their performance in modeling heterogeneity in data in many statistical learning approaches for prediction, including regression and classification, as well as for clustering. Their estimation in high-dimensional problems is still however challeng…

Higher granularity in MoE models boosts expressivity exponentially.

Adaptive Bayesian learning aggregates experts to improve performance.

A new approach for learning from expert demonstrations using multiple perspectives.

In life sciences, the experts generally use empirical knowledge to recode variables, choose interactions and perform selection by classical approach. The aim of this work is to perform automatic learning algorithm for variables selection which can lead to know if experts can be help in they decision or simply replaced …

We improve MoE models for classification with rigorous guarantees and practical methods.

In this paper, we derive a novel probabilistic model of boosting as a Product of Experts. We re-derive the boosting algorithm as a greedy incremental model selection procedure which ensures that addition of new experts to the ensemble does not decrease the likelihood of the data. These learning rules lead to a generic …

In this paper we introduce a model of lifelong learning, based on a Network of Experts. New tasks / experts are learned and added to the model sequentially, building on what was learned before. To ensure scalability of this process,data from previous tasks cannot be stored and hence is not available when learning a new…

Budgeted deferral framework reduces expert query costs in machine learning.

The paper shows how expert knowledge can improve treatment effect estimation.

Sepsis is the leading cause of mortality in the ICU. It is challenging to manage because individual patients respond differently to treatment. Thus, tailoring treatment to the individual patient is essential for the best outcomes. In this paper, we take steps toward this goal by applying a mixture-of-experts framework …

A new method for learning to defer decisions with expert advice improves over standard methods.

Improved transfer learning with expert models, reducing compute and speeding up performance.

LEARN-SAM improves RL from sub-optimal demonstrations by localizing expert policies and selectively using demonstrations.

In this work we describe a novel deep reinforcement learning architecture that allows multiple actions to be selected at every time-step in an efficient manner. Multi-action policies allow complex behaviours to be learnt that would otherwise be hard to achieve when using single action selection techniques. We use both …

Solving sequential decision prediction problems, including those in imitation learning settings, requires mitigating the problem of covariate shift. The standard approach, DAgger, relies on capturing expert behaviour in all states that the agent reaches. In real-world settings, querying an expert is costly. We propose …

L2D-CD learns to defer expert recommendations in causal discovery.

This study analyzes communication constraints in MoE architectures using information theory.

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

Unified framework for deferring queries to top-k experts, improving accuracy-cost trade-offs.