English
Related papers

Related papers: The Unreasonable Effectiveness Of Early Discarding…

200 papers

An important challenge in multi-objective reinforcement learning is obtaining a Pareto front of policies to attain optimal performance under different preferences. We introduce Iterated Pareto Referent Optimisation (IPRO), which decomposes…

Machine Learning · Computer Science 2025-02-07 Willem Röpke , Mathieu Reymond , Patrick Mannion , Diederik M. Roijers , Ann Nowé , Roxana Rădulescu

Learning to defer uncertain predictions to costly experts offers a powerful strategy for improving the accuracy and efficiency of machine learning systems. However, standard training procedures for deferral algorithms typically require…

Machine Learning · Computer Science 2025-10-31 Giulia DeSalvo , Clara Mohri , Mehryar Mohri , Yutao Zhong

Early-exiting dynamic neural networks (EDNN), as one type of dynamic neural networks, has been widely studied recently. A typical EDNN has multiple prediction heads at different layers of the network backbone. During inference, the model…

Machine Learning · Computer Science 2022-12-01 Haichao Yu , Haoxiang Li , Gang Hua , Gao Huang , Humphrey Shi

Preference optimization (PO) is indispensable for large language models (LLMs), with methods such as direct preference optimization (DPO) and proximal policy optimization (PPO) achieving great success. A common belief is that DPO is…

Machine Learning · Computer Science 2026-05-18 Yue Wang , Qizhou Wang , Zizhuo Zhang , Gang Niu , Bo Han , Masashi Sugiyama

The alignment of large language models with human values presents a critical challenge, particularly when balancing conflicting objectives like helpfulness and harmlessness. Existing approaches, such as Reinforcement Learning from Human…

Computation and Language · Computer Science 2025-03-04 Yuxuan Liu

Deep Learning is becoming increasingly relevant in Embedded and Internet-of-things applications. However, deploying models on embedded devices poses a challenge due to their resource limitations. This can impact the model's inference…

Machine Learning · Computer Science 2024-03-14 Max Sponner , Lorenzo Servadei , Bernd Waschneck , Robert Wille , Akash Kumar

A number of popular transfer learning methods rely on grid search to select regularization hyperparameters that control over-fitting. This grid search requirement has several key disadvantages: the search is computationally expensive,…

Machine Learning · Computer Science 2025-01-28 Ethan Harvey , Mikhail Petrov , Michael C. Hughes

In continual learning (CL) -- where a learner trains on a stream of data -- standard hyperparameter optimisation (HPO) cannot be applied, as a learner does not have access to all of the data at the same time. This has prompted the…

Machine Learning · Computer Science 2025-03-17 Thomas L. Lee , Sigrid Passano Hellan , Linus Ericsson , Elliot J. Crowley , Amos Storkey

Deep learning architectures with a huge number of parameters are often compressed using pruning techniques to ensure computational efficiency of inference during deployment. Despite multitude of empirical advances, there is a lack of…

Machine Learning · Computer Science 2021-06-14 Rupam Acharyya , Ankani Chattoraj , Boyu Zhang , Shouman Das , Daniel Stefankovic

Predictive coding networks are neural models that perform inference through an iterative energy minimization process, whose operations are local in space and time. While effective in shallow architectures, they suffer significant…

Machine Learning · Computer Science 2025-10-13 Chang Qi , Matteo Forasassi , Thomas Lukasiewicz , Tommaso Salvatori

Optimization is an important module of modern machine learning applications. Tremendous efforts have been made to accelerate optimization algorithms. A common formulation is achieving a lower loss at a given time. This enables a…

Machine Learning · Computer Science 2025-05-29 Zhonglin Xie , Yiman Fong , Haoran Yuan , Zaiwen Wen

Online learning is the cornerstone of applications like recommendation and advertising systems, where models continuously adapt to shifting data distributions. Model training for such systems is remarkably expensive, a cost that multiplies…

Machine Learning · Computer Science 2025-12-02 Berivan Isik , Matthew Fahrbach , Dima Kuzmin , Nicolas Mayoraz , Emil Praun , Steffen Rendle , Raghavendra Vasudeva

Hyperparameter optimization (HPO) is increasingly used to automatically tune the predictive performance (e.g., accuracy) of machine learning models. However, in a plethora of real-world applications, accuracy is only one of the multiple --…

Machine Learning · Statistics 2021-06-25 Robin Schmucker , Michele Donini , Muhammad Bilal Zafar , David Salinas , Cédric Archambeau

The rising growth of deep neural networks (DNNs) and datasets in size motivates the need for efficient solutions for simultaneous model selection and training. Many methods for hyperparameter optimization (HPO) of iterative learners,…

Machine Learning · Computer Science 2023-02-28 Syrine Belakaria , Janardhan Rao Doppa , Nicolo Fusi , Rishit Sheth

The Internet of Things is transforming various fields, with sensors increasingly embedded in wearables, smart buildings, and connected equipment. While deep learning enables valuable insights from IoT data, conventional models are too…

Machine Learning · Computer Science 2026-04-01 Alaa Zniber , Mounir Ghogho , Ouassim Karrakchou , Mehdi Zakroum

Modern machine learning algorithms crucially rely on several design decisions to achieve strong performance, making the problem of Hyperparameter Optimization (HPO) more important than ever. Here, we combine the advantages of the popular…

Machine Learning · Computer Science 2021-10-22 Noor Awad , Neeratyoy Mallik , Frank Hutter

Conventional decision trees have a number of favorable properties, including interpretability, a small computational footprint and the ability to learn from little training data. However, they lack a key quality that has helped fuel the…

Machine Learning · Statistics 2017-12-08 Thomas Hehn , Fred A. Hamprecht

In many real-world deployments of machine learning systems, data arrive piecemeal. These learning scenarios may be passive, where data arrive incrementally due to structural properties of the problem (e.g., daily financial data) or active,…

Machine Learning · Computer Science 2021-01-01 Jordan T. Ash , Ryan P. Adams

Direct Preference Optimization (DPO), which derives reward signals directly from pairwise preference data, has shown its effectiveness on aligning Large Language Models (LLMs) with human preferences. Despite its widespread use across…

Computation and Language · Computer Science 2024-04-09 Duanyu Feng , Bowen Qin , Chen Huang , Zheng Zhang , Wenqiang Lei

Neural networks offer high-accuracy solutions to a range of problems, but are costly to run in production systems because of computational and memory requirements during a forward pass. Given a trained network, we propose a techique called…

Computer Vision and Pattern Recognition · Computer Science 2018-06-18 Michele Pratusevich
‹ Prev 1 4 5 6 7 8 10 Next ›