English
Related papers

Related papers: Zeta Distribution and Transfer Learning Problem

200 papers

The application of Genetic Programming to the discovery of empirical laws is often impaired by the huge size of the search space, and consequently by the computer resources needed. In many cases, the extreme demand for memory and CPU is due…

Artificial Intelligence · Computer Science 2016-08-16 Alain Ratle , Michèle Sebag

Transfer learning refers to the transfer of knowledge or information from a relevant source task to a target task. However, most existing works assume both tasks are sampled from a stationary task distribution, thereby leading to the…

Machine Learning · Computer Science 2022-07-06 Jun Wu , Jingrui He

Meta-learning algorithms use past experience to learn to quickly solve new tasks. In the context of reinforcement learning, meta-learning algorithms acquire reinforcement learning procedures to solve new problems more efficiently by…

Machine Learning · Computer Science 2020-05-01 Abhishek Gupta , Benjamin Eysenbach , Chelsea Finn , Sergey Levine

In this paper, we leverage ideas from model-based control to address the sample efficiency problem of reinforcement learning (RL) algorithms. Accelerating learning is an active field of RL highly relevant in the context of time-varying…

Systems and Control · Electrical Eng. & Systems 2023-05-23 Ibrahim Ahmed , Marcos Quinones-Grueiro , Gautam Biswas

Deploying machine learning (ML) models in the wild is challenging as it suffers from distribution shifts, where the model trained on an original domain cannot generalize well to unforeseen diverse transfer domains. To address this…

Cryptography and Security · Computer Science 2023-08-17 Tianshuo Cong , Xinlei He , Yun Shen , Yang Zhang

Transfer learning is an essential technique for many machine learning/AI models of complex structures such as large language models and generative AI. The essence of transfer learning is to leverage knowledge from resolved source tasks for…

Machine Learning · Statistics 2026-05-21 Haoyang Cao , Xin Guo , Wenpin Tang , Guan Wang

Machine learning theory has mostly focused on generalization to samples from the same distribution as the training data. Whereas a better understanding of generalization beyond the training distribution where the observed distribution…

Machine Learning · Statistics 2019-05-29 Matias Vera , Pablo Piantanida , Leonardo Rey Vega

The state of many physical, biological and socio-technical systems evolves by combining smooth local transitions and abrupt resetting events to a set of reference values. The inclusion of the resetting mechanism not only provides the…

Statistical Mechanics · Physics 2022-12-21 Oriol Artime

Learning to read words aloud is a major step towards becoming a reader. Many children struggle with the task because of the inconsistencies of English spelling-sound correspondences. Curricula vary enormously in how these patterns are…

Machine Learning · Computer Science 2020-07-03 Ayon Sen , Christopher R. Cox , Matthew Cooper Borkenhagen , Mark S. Seidenberg , Xiaojin Zhu

Learning systems acquire structured internal representations from data, yet classical information-theoretic results state that deterministic transformations do not increase information. This raises a fundamental question: how can learning…

Machine Learning · Computer Science 2026-01-29 Daisuke Okanohara

Learning-to-learn or meta-learning leverages data-driven inductive bias to increase the efficiency of learning on a novel task. This approach encounters difficulty when transfer is not advantageous, for instance, when tasks are considerably…

Machine Learning · Computer Science 2019-06-20 Ghassen Jerfel , Erin Grant , Thomas L. Griffiths , Katherine Heller

Meta-learning, the notion of learning to learn, enables learning systems to quickly and flexibly solve new tasks. This usually involves defining a set of outer-loop meta-parameters that are then used to update a set of inner-loop…

Machine Learning · Computer Science 2023-03-17 Chris Lu , Sebastian Towers , Jakob Foerster

The no-free-lunch theorems promote a skeptical conclusion that all possible machine learning algorithms equally lack justification. But how could this leave room for a learning theory, that shows that some algorithms are better than others?…

Machine Learning · Computer Science 2022-02-10 Tom F. Sterkenburg , Peter D. Grünwald

We consider a setting where a population of artificial learners is given, and the objective is to optimize aggregate measures of performance, under constraints on training resources. The problem is motivated by the study of peer learning in…

Machine Learning · Computer Science 2023-12-04 Ehsan Beikihassan , Amy K. Hoover , Ioannis Koutis , Ali Parviz , Niloofar Aghaieabiane

Transfer learning is beneficial for survival analysis, especially when the target study has a limited number of events. However, existing transfer learning methods rely on the restrictive assumption that the target and source studies share…

Methodology · Statistics 2026-03-13 Yu Gu , Donglin Zeng , D. Y. Lin

Social goods, such as healthcare, smart city, and information networks, often produce ordered event data in continuous time. The generative processes of these event data can be very complex, requiring flexible models to capture their…

Machine Learning · Computer Science 2020-12-29 Shuang Li , Shuai Xiao , Shixiang Zhu , Nan Du , Yao Xie , Le Song

Transfer learning is a popular paradigm for utilizing existing knowledge from previous learning tasks to improve the performance of new ones. It has enjoyed numerous empirical successes and inspired a growing number of theoretical studies.…

Machine Learning · Computer Science 2023-05-23 Haoyang Cao , Haotian Gu , Xin Guo

The training algorithms for AI systems all introduce far-from-equilibrium dynamical processes, and understanding the irreversibility of these algorithms is a fundamental step towards understanding the learning dynamics of modern AI systems.…

Statistical Mechanics · Physics 2026-05-22 Liu Ziyin , Yuanjie Ren , Adam Levine , Isaac Chuang

We analyze a stochastic approximation algorithm for decision-dependent problems, wherein the data distribution used by the algorithm evolves along the iterate sequence. The primary examples of such problems appear in performative prediction…

Optimization and Control · Mathematics 2024-05-15 Joshua Cutler , Mateo Díaz , Dmitriy Drusvyatskiy

When hyperparameter optimization of a machine learning algorithm is repeated for multiple datasets it is possible to transfer knowledge to an optimization run on a new dataset. We develop a new hyperparameter-free ensemble model for…

Machine Learning · Statistics 2022-10-25 Matthias Feurer , Benjamin Letham , Frank Hutter , Eytan Bakshy
‹ Prev 1 8 9 10 Next ›