English
Related papers

Related papers: Pre-Train Your Loss: Easy Bayesian Transfer Learni…

200 papers

Bayesian meta-learning enables robust and fast adaptation to new tasks with uncertainty assessment. The key idea behind Bayesian meta-learning is empirical Bayes inference of hierarchical model. In this work, we extend this framework to…

Machine Learning · Computer Science 2020-11-19 Yayi Zou , Xiaoqi Lu

Many real-world applications require making multiple predictions from the same text. Fine-tuning a large pre-trained language model for each downstream task causes computational burdens in the inference time due to several times of forward…

Computation and Language · Computer Science 2023-10-17 Kuan-Hao Huang , Liang Tan , Rui Hou , Sinong Wang , Amjad Almahairi , Ruty Rinott

Deep learning-based image reconstruction approaches have demonstrated impressive empirical performance in many imaging modalities. These approaches usually require a large amount of high-quality paired training data, which is often not…

Image and Video Processing · Electrical Eng. & Systems 2022-09-21 Riccardo Barbano , Zeljko Kereta , Andreas Hauptmann , Simon R. Arridge , Bangti Jin

Machine unlearning algorithms are increasingly important as legal concerns arise around the provenance of training data, but verifying the success of unlearning is often difficult. Provable guarantees for unlearning are often limited to…

Machine Learning · Computer Science 2025-04-22 Stanley Wei , Sadhika Malladi , Sanjeev Arora , Amartya Sanyal

Large, pre-trained models are problematic to use in resource constrained applications. Fortunately, task-aware structured pruning methods offer a solution. These approaches reduce model size by dropping structural units like layers and…

Computation and Language · Computer Science 2023-11-14 Lucio Dery , David Grangier , Awni Hannun

Bayesian models provide recursive inference naturally because they can formally reconcile new data and existing scientific information. However, popular use of Bayesian methods often avoids priors that are based on exact posterior…

Methodology · Statistics 2019-04-29 Mevin B. Hooten , Devin S. Johnson , Brian M. Brost

Deep learning has shown its human-level performance in various applications. However, current deep learning models are characterised by catastrophic forgetting of old knowledge when learning new classes. This poses a challenge particularly…

Machine Learning · Computer Science 2022-04-29 Yang Yang , Zhiying Cui , Junjie Xu , Changhong Zhong , Wei-Shi Zheng , Ruixuan Wang

This paper addresses Bayesian inference related to partial differential equations (PDEs), particularly nonparametric regression constrained by PDEs. To effectively encode prior information, we propose a novel framework that learns a…

Statistics Theory · Mathematics 2026-02-09 Junxiong Jia , Deyu Meng , Zongben Xu , Fang Yao

Human beings can leverage knowledge from relative tasks to improve learning on a primary task. Similarly, multi-task learning methods suggest using auxiliary tasks to enhance a neural network's performance on a specific primary task.…

Computer Vision and Pattern Recognition · Computer Science 2024-12-30 Yuanze Li , Chun-Mei Feng , Qilong Wang , Guanglei Yang , Wangmeng Zuo

Transfer learning methods endeavor to leverage relevant knowledge from existing source pre-trained models or datasets to solve downstream target tasks. With the increase in the scale and quantity of available pre-trained models nowadays, it…

Machine Learning · Computer Science 2024-02-26 Yuhe Ding , Bo Jiang , Aijing Yu , Aihua Zheng , Jian Liang

Exploration and adaptation to new tasks in a transfer learning setup is a central challenge in reinforcement learning. In this work, we build on the idea of modeling a distribution over policies in a Bayesian deep reinforcement learning…

Machine Learning · Computer Science 2019-06-11 Disha Shrivastava , Eeshan Gunesh Dhekane , Riashat Islam

Discovering a unique causal structure is difficult due to both inherent identifiability issues, and the consequences of finite data. As such, uncertainty over causal structures, such as those obtained from a Bayesian posterior, are often…

Machine Learning · Computer Science 2025-03-06 Anish Dhir , Matthew Ashman , James Requeima , Mark van der Wilk

Bayesian deep learning counts on the quality of posterior distribution estimation. However, the posterior of deep neural networks is highly multi-modal in nature, with local modes exhibiting varying generalization performance. Given a…

Machine Learning · Computer Science 2024-03-27 Bolian Li , Ruqi Zhang

In open-ended continuous environments, robots need to learn multiple parameterised control tasks in hierarchical reinforcement learning. We hypothesise that the most complex tasks can be learned more easily by transferring knowledge from…

Artificial Intelligence · Computer Science 2021-02-22 Nicolas Duminy , Sao Mai Nguyen , Junshuai Zhu , Dominique Duhaut , Jerome Kerdreux

Humans can learn new concepts from a small number of examples by drawing on their inductive biases. These inductive biases have previously been captured by using Bayesian models defined over symbolic hypothesis spaces. Is it possible to…

Machine Learning · Computer Science 2024-02-13 Ioana Marinescu , R. Thomas McCoy , Thomas L. Griffiths

Transductive learning is a supervised machine learning task in which, unlike in traditional inductive learning, the unlabelled data that require labelling are a finite set and are available at training time. Similarly to inductive learning…

Machine Learning · Computer Science 2025-07-31 Lorenzo Volpi , Alejandro Moreo , Fabrizio Sebastiani

In this work, we aim to establish a Bayesian adaptive learning framework by focusing on estimating latent variables in deep neural network (DNN) models. Latent variables indeed encode both transferable distributional information and…

Audio and Speech Processing · Electrical Eng. & Systems 2024-01-26 Hu Hu , Sabato Marco Siniscalchi , Chin-Hui Lee

Transfer learning is a powerful paradigm for leveraging knowledge from source domains to enhance learning in a target domain. However, traditional transfer learning approaches often focus on scalar or multivariate data within Euclidean…

Machine Learning · Computer Science 2025-10-24 Kaicheng Zhang , Sinian Zhang , Doudou Zhou , Yidong Zhou

In Generalised Bayesian Inference (GBI), the learning rate and hyperparameters of the loss must be estimated. These inference-hyperparameters can't be estimated jointly with the other parameters, from the data, by giving them a prior.…

Methodology · Statistics 2026-05-18 Jeong Eun Lee , Sitong Liu , Geoff K. Nicholls

Loss function learning is a new meta-learning paradigm that aims to automate the essential task of designing a loss function for a machine learning model. Existing techniques for loss function learning have shown promising results, often…

Machine Learning · Computer Science 2025-10-14 Christian Raymond , Qi Chen , Bing Xue , Mengjie Zhang