Related papers: Functional mixture-of-experts for classification
Mixture of experts is a prediction aggregation method in machine learning that aggregates the predictions of specialized experts. This method often outperforms Bayesian methods despite the Bayesian having stronger inductive guarantees. We…
Mixtures of Experts (MoEs) have gained prominence in (self-)supervised learning due to their enhanced inference efficiency, adaptability to distributed training, and modularity. Previous research has illustrated that MoEs can significantly…
Artificial intelligence (AI) has achieved astonishing successes in many domains, especially with the recent breakthroughs in the development of foundational large models. These large models, leveraging their extensive training data, provide…
Mixture of Experts (MoE) is a popular framework for modeling heterogeneity in data for regression, classification and clustering. For continuous data which we consider here in the context of regression and cluster analysis, MoE usually use…
Human perception generalizes well across different domains, but most vision models struggle beyond their training data. This gap motivates multi-dataset learning, where a single model is trained on diverse datasets to improve robustness…
We define a generalized likelihood function based on uncertainty measures and show that maximizing such a likelihood function for different measures induces different types of classifiers. In the probabilistic framework, we obtain…
In this paper, we present the practical problems and the lessons learned at short-video services from Kuaishou. In industry, a widely-used multi-task framework is the Mixture-of-Experts (MoE) paradigm, which always introduces some shared…
Mixtures of experts probabilistically divide the input space into regions, where the assumptions of each expert, or conditional model, need only hold locally. Combined with Gaussian process (GP) experts, this results in a powerful and…
Deep mixture-of-experts models have attracted a lot of attention for survival analysis problems, particularly for their ability to cluster similar patients together. In practice, grouping often comes at the expense of key metrics such as…
We propose a new method for the Maximum Likelihood Estimator (MLE) of nonlinear mixed effects models when the variance matrix of Gaussian random effects has a prescribed pattern of zeros (PPZ). The method consists in coupling the recently…
Large language models (LLMs) increasingly adopt Mixture-of-Experts (MoE) architectures to scale model capacity while reducing computation. Fine-tuning these MoE-based LLMs often requires access to distributed and privacy-sensitive data,…
Randomized neural networks (NNs) are an interesting alternative to conventional NNs that are more used for data modeling. The random vector functional-link (RVFL) network is an established and theoretically well-grounded randomized learning…
Automated scoring of written constructed responses typically relies on separate models per task, straining computational resources, storage, and maintenance in real-world education settings. We propose UniMoE-Guided, a knowledge-distilled…
The Mixture of Experts (MoE) selects a few feed-forward networks (FFNs) per token, achieving an effective trade-off between computational cost and performance. In conventional MoE, each expert is treated as entirely independent, and experts…
Variable selection is fundamental to high-dimensional statistical modeling. Many variable selection techniques may be implemented by maximum penalized likelihood using various penalty functions. Optimizing the penalized likelihood function…
Estimators derived from a divergence criterion such as $\varphi-$divergences are generally more robust than the maximum likelihood ones. We are interested in particular in the so-called MD$\varphi$DE, an estimator built using a dual…
Mixture-of-Experts (MoE) architectures have emerged as a cornerstone of modern AI systems. In particular, MoEs route inputs dynamically to specialized experts whose outputs are aggregated through weighted summation. Despite their widespread…
Machine learning (ML) models are increasingly being used in application domains that often involve working together with human experts. In this context, it can be advantageous to defer certain instances to a single human expert when they…
Vulnerability to adversarial attacks is a well-known deficiency of deep neural networks. Larger networks are generally more robust, and ensembling is one method to increase adversarial robustness: each model's weaknesses are compensated by…
The rapidly expanding artificial intelligence (AI) industry has produced diverse yet powerful prediction tools, each with its own network architecture, training strategy, data-processing pipeline, and domain-specific strengths. These tools…