English
Related papers

Related papers: On Bayesian Softmax-Gated Mixture-of-Experts Model…

200 papers

In this work, we propose a method that combines two popular research areas by injecting linguistic structures into pre-trained language models in the parameter-efficient fine-tuning (PEFT) setting. In our approach, parallel adapter modules…

Computation and Language · Computer Science 2023-10-26 Raymond Li , Gabriel Murray , Giuseppe Carenini

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…

Computer Vision and Pattern Recognition · Computer Science 2017-04-20 Rahaf Aljundi , Punarjay Chakravarty , Tinne Tuytelaars

Bayesian model comparison (BMC) offers a principled probabilistic approach to study and rank competing models. In standard BMC, we construct a discrete probability distribution over the set of possible models, conditional on the observed…

Machine Learning · Statistics 2023-02-22 Marvin Schmitt , Stefan T. Radev , Paul-Christian Bürkner

We consider the problem of sampling from a product-of-experts-type model that encompasses many standard prior and posterior distributions commonly found in Bayesian imaging. We show that this model can be easily lifted into a novel latent…

Image and Video Processing · Electrical Eng. & Systems 2026-04-16 Muhamed Kuric , Martin Zach , Andreas Habring , Michael Unser , Thomas Pock

Linear Mode Connectivity (LMC) is a notable phenomenon in the loss landscapes of neural networks, wherein independently trained models have been observed to be connected--up to permutation symmetries--by linear paths in parameter space…

Machine Learning · Computer Science 2025-10-28 Viet-Hoang Tran , Van Hoan Trinh , Khanh Vinh Bui , Tan M. Nguyen

Numerous models for supervised and reinforcement learning benefit from combinations of discrete and continuous model components. End-to-end learnable discrete-continuous models are compositional, tend to generalize better, and are more…

Machine Learning · Computer Science 2023-07-27 David Friede , Mathias Niepert

Bayesian inference on structured models typically relies on the ability to infer posterior distributions of underlying hidden variables. However, inference in implicit models or complex posterior distributions is hard. A popular tool for…

Machine Learning · Statistics 2016-12-16 Theofanis Karaletsos

As for other latent-variable problems, exact Bayesian analysis is typically not practicable for mixture problems and approximate methods have been developed. Variational Bayes tends to produce approximate posterior distributions for…

Statistics Theory · Mathematics 2026-02-24 Nils Lid Hjort , Mike Titterington

Most of applied statistics involves regression analysis of data. This paper presents a stand-alone and menu-driven software package, Bayesian Regression: Nonparametric and Parametric Models. Currently, this package gives the user a choice…

Computation · Statistics 2015-07-15 George Karabatsos

When random effects are correlated with sample design variables, the usual approach of employing individual survey weights (constructed to be inversely proportional to the unit survey inclusion probabilities) to form a pseudo-likelihood no…

Methodology · Statistics 2021-08-26 Terrance D. Savitsky , Matthew R. Williams

In this paper, we aim to build a robust question answering system that can adapt to out-of-domain datasets. A single network may overfit to the superficial correlation in the training distribution, but with a meaningful number of expert…

Computation and Language · Computer Science 2022-04-21 Yu Qing Zhou , Xixuan Julie Liu , Yuanzhe Dong

We introduce Mixture-of-Gaussians with Uncertainty-based Gating (MoGU), a novel Mixture-of-Experts (MoE) framework designed for regression tasks. MoGU replaces standard learned gating with an intrinsic routing paradigm where expert-specific…

Machine Learning · Computer Science 2026-02-04 Gilad Aviv , Jacob Goldberger , Yoli Shavit

We study Bayesian estimation of finite mixture models in a general setup where the number of components is unknown and allowed to grow with the sample size. An assumption on growing number of components is a natural one as the degree of…

Statistics Theory · Mathematics 2022-03-18 Ilsang Ohn , Lizhen Lin

In this paper we compare and contrast the behavior of the posterior predictive distribution to the risk of the maximum a posteriori estimator for the random features regression model in the overparameterized regime. We will focus on the…

Machine Learning · Statistics 2023-10-30 Youngsoo Baek , Samuel I. Berchuck , Sayan Mukherjee

This paper deals with Bayesian inference of a mixture of Gaussian distributions. A novel formulation of the mixture model is introduced, which includes the prior constraint that each Gaussian component is always assigned a minimal number of…

Methodology · Statistics 2014-05-21 Colin J. Stoneking

Many methods have been proposed to quantify the predictive uncertainty associated with the outputs of deep neural networks. Among them, ensemble methods often lead to state-of-the-art results, though they require modifications to the…

Machine Learning · Computer Science 2021-05-11 Zhiyun Lu , Eugene Ie , Fei Sha

The sparse Mixture-of-Experts (MoE) model is powerful for large-scale pre-training and has achieved promising results due to its model capacity. However, with trillions of parameters, MoE is hard to be deployed on cloud or mobile…

Machine Learning · Computer Science 2022-06-03 Tianyu Chen , Shaohan Huang , Yuan Xie , Binxing Jiao , Daxin Jiang , Haoyi Zhou , Jianxin Li , Furu Wei

Functional mixed models are widely useful for regression analysis with dependent functional data, including longitudinal functional data with scalar predictors. However, existing algorithms for Bayesian inference with these models only…

Methodology · Statistics 2023-06-14 Thomas Y. Sun , Daniel R. Kowal

Scientific experiments are usually expensive due to complex experimental preparation and processing. Experimental design is therefore involved with the task of finding the optimal experimental input that results in the desirable output by…

Machine Learning · Statistics 2020-02-27 Cheng Li , Sunil Gupta , Santu Rana , Vu Nguyen , Antonio Robles-Kelly , Svetha Venkatesh

Bayesian Dark Knowledge is a method for compressing the posterior predictive distribution of a neural network model into a more compact form. Specifically, the method attempts to compress a Monte Carlo approximation to the parameter…

Machine Learning · Computer Science 2019-06-11 Meet P. Vadera , Benjamin M. Marlin