paper-with-me

Papers

Consistent Multitask Learning with Nonlinear Output Relations

2017-05-23 · NeurIPS 2017 12 · Carlo Ciliberto, Alessandro Rudi, Lorenzo Rosasco, Massimiliano Pontil

Key to multitask learning is exploiting relationships between different tasks to improve prediction performance. If the relations are linear, regularization approaches can be used successfully. However, in practice assuming the tasks to be linearly related might be restrictive, and allowing for nonlinear structures is a challenge. In this paper, we tackle this issue by casting the problem within the framework of structured prediction. Our main contribution is a novel algorithm for learning multiple tasks which are related by a system of nonlinear equations that their joint outputs need to satisfy. We show that the algorithm is consistent and can be efficiently implemented. Experimental results show the potential of the proposed method.

📄 PDF Abstract BibTeX arXiv:1705.08118

Code (0)

등록된 구현이 없습니다.

Tasks

PredictionStructured Prediction

Similar Papers 제목 키워드 기반

Efficient Multitask Feature and Relationship Learning

2017-02-14 · Han Zhao, Otilia Stretcu, Alex Smola, Geoff Gordon

We consider a multitask learning problem, in which several predictors are learned jointly. Prior research has shown that learning the relations between tasks, and between the input features, together with the predictor, …

Incorporating Sum Constraints into Multitask Gaussian Processes

2022-02-03 · Philipp Pilar, Carl Jidling, Thomas B. Schön, Niklas Wahlström

Machine learning models can be improved by adapting them to respect existing background knowledge. In this paper we consider multitask Gaussian processes, with background knowledge in the form of constraints that require…

Gaussian Processes

Geometrical determinant of nonlinear synaptic integration in human cortical pyramidal neurons

2024-08-10 · Jaeyoung Yoon

Neurons integrate synaptic inputs and convert them to action potential output at electrically distant locations. The computational power of a neuron is hence enhanced by subcellular compartmentalization and nonlinear syn…

Generalization in multitask deep neural classifiers: a statistical physics approach

2019-10-30 · NeurIPS 2019 12 · Tyler Lee, Anthony Ndirango

A proper understanding of the striking generalization abilities of deep neural networks presents an enduring puzzle. Recently, there has been a growing body of numerically-grounded theoretical work that has contributed i…

Hierarchical Multitask Learning for CTC-based Speech Recognition

2018-07-17 · Kalpesh Krishna, Shubham Toshniwal, Karen Livescu

Previous work has shown that neural encoder-decoder speech recognition can be improved with hierarchical multitask learning, where auxiliary tasks are added at intermediate layers of a deep encoder. We explore the effect…

Decoderspeech-recognitionSpeech Recognition