English
Related papers

Related papers: Functional Ensemble Distillation

200 papers

Stock trend forecasting has become a popular research direction that attracts widespread attention in the financial field. Though deep learning methods have achieved promising results, there are still many limitations, for example, how to…

Machine Learning · Computer Science 2020-12-14 Hongshun Tang , Lijun Wu , Weiqing Liu , Jiang Bian

Training a diverse ensemble of models has several practical applications such as providing candidates for model selection with better out-of-distribution (OOD) generalization, and enabling the detection of OOD samples via Bayesian…

Machine Learning · Computer Science 2024-09-26 Alexander Rubinstein , Luca Scimeca , Damien Teney , Seong Joon Oh

Bayesian neural networks (BNNs) provide a formalism to quantify and calibrate uncertainty in deep learning. Current inference approaches for BNNs often resort to few-sample estimation for scalability, which can harm predictive performance,…

Machine Learning · Computer Science 2024-02-14 Zhe Zeng , Guy Van den Broeck

This study presents a novel approach to enhance the cost-to-quality ratio of image generation with diffusion models. We hypothesize that differences between distilled (e.g. FLUX.1-schnell) and baseline (e.g. FLUX.1-dev) models are…

Computer Vision and Pattern Recognition · Computer Science 2025-05-12 Jakub Wasala , Bartlomiej Wrzalski , Kornelia Noculak , Yuliia Tarasenko , Oliwer Krupa , Jan Kocon , Grzegorz Chodak

Clustered Federated Learning (CFL) addresses the challenges posed by non-IID data by training multiple group- or cluster-specific expert models. However, existing methods often overlook the shared information across clusters, which…

Machine Learning · Computer Science 2025-06-26 Zeqi Leng , Chunxu Zhang , Guodong Long , Riting Xia , Bo Yang

Diffusion models achieve strong generation quality, diversity, and distribution coverage, but their performance often comes with expensive inference. In this work, we propose Stochastic Transition-Map Distillation (STMD), a teacher-free…

Machine Learning · Computer Science 2026-05-11 George Rapakoulias , Peter Garud , Lingjiong Zhu , Panagiotis Tsiotras

Identifying predictive factors for an outcome of interest via a multivariable analysis is often difficult when the data set is small. Combining data from different medical centers into a single (larger) database would alleviate this…

Applications · Statistics 2024-03-12 Marianne A. Jonker , Hassan Pazira , Anthony CC Coolen

To accelerate diffusion model inference, numerical solvers perform poorly at extremely small steps, while distillation techniques often introduce complexity and instability. This work presents an intermediate strategy, balancing performance…

Machine Learning · Computer Science 2025-12-16 Wenze Liu , Xiangyu Yue

Decomposing prediction uncertainty into aleatoric (irreducible) and epistemic (reducible) components is critical for the reliable deployment of machine learning systems. While the mutual information between the response variable and model…

Machine Learning · Statistics 2026-02-10 Anchit Jain , Stephen Bates

We present Causal Posterior Estimation (CPE), a novel method for Bayesian inference in simulator models, i.e., models where the evaluation of the likelihood function is intractable or too computationally expensive, but where one can…

Machine Learning · Computer Science 2025-05-28 Simon Dirmeier , Antonietta Mira

In this work we aim to obtain computationally-efficient uncertainty estimates with deep networks. For this, we propose a modified knowledge distillation procedure that achieves state-of-the-art uncertainty estimates both for in and…

Machine Learning · Computer Science 2019-06-14 Erik Englesson , Hossein Azizpour

This paper investigates the feasibility of federated representation learning under the constraints of communication cost and privacy protection. Existing works either conduct annotation-guided local training which requires frequent…

Machine Learning · Computer Science 2022-01-19 Haizhou Shi , Youcai Zhang , Zijin Shen , Siliang Tang , Yaqian Li , Yandong Guo , Yueting Zhuang

By distributing the training process, local approximation reduces the cost of the standard Gaussian Process. An ensemble technique combines local predictions from Gaussian experts trained on different partitions of the data. Ensemble…

Machine Learning · Computer Science 2024-01-09 Hamed Jalali , Gjergji Kasneci

Federated learning (FL) enables multiple clients to collaboratively train a global model while keeping local data decentralized. Data heterogeneity (non-IID) across clients has imposed significant challenges to FL, which makes local models…

Machine Learning · Computer Science 2025-04-22 Yuting He , Yiqiang Chen , XiaoDong Yang , Hanchao Yu , Yi-Hua Huang , Yang Gu

Distributed learning frameworks often rely on exchanging model parameters across workers, instead of revealing their raw data. A prime example is federated learning that exchanges the gradients or weights of each neural network model. Under…

Machine Learning · Computer Science 2020-11-05 Hyowoon Seo , Jihong Park , Seungeun Oh , Mehdi Bennis , Seong-Lyun Kim

Federated Learning (FL) is a machine learning paradigm where many local nodes collaboratively train a central model while keeping the training data decentralized. This is particularly relevant for clinical applications since patient data…

Distillation is the task of replacing a complicated machine learning model with a simpler model that approximates the original [BCNM06,HVD15]. Despite many practical applications, basic questions about the extent to which models can be…

Machine Learning · Computer Science 2024-05-07 Enric Boix-Adsera

Many statistical models can be simulated forwards but have intractable likelihoods. Approximate Bayesian Computation (ABC) methods are used to infer properties of these models from data. Traditionally these methods approximate the posterior…

Machine Learning · Statistics 2018-04-03 George Papamakarios , Iain Murray

Large Language Models (LLMs) often exhibit misalignment between the quality of their generated responses and the confidence estimates they assign to them. Bayesian treatments, such as marginalizing over a reliable weight posterior or over…

The poor cross-architecture generalization of dataset distillation greatly weakens its practical significance. This paper attempts to mitigate this issue through an empirical study, which suggests that the synthetic datasets undergo an…

Machine Learning · Computer Science 2024-06-27 Lirui Zhao , Yuxin Zhang , Fei Chao , Rongrong Ji