Parametric Task Learning
نویسندگان
چکیده
We introduce an extended formulation of multi-task learning (MTL) called parametric task learning (PTL) that can systematically handle infinitely many tasks parameterized by a continuous parameter. Our key finding is that, for a certain class of PTL problems, the path of the optimal task-wise solutions can be represented as piecewise-linear functions of the continuous task parameter. Based on this fact, we employ a parametric programming technique to obtain the common shared representation across all the continuously parameterized tasks. We show that our PTL formulation is useful in various scenarios such as learning under non-stationarity, cost-sensitive learning, and quantile regression. We demonstrate the advantage of our approach in these scenarios.
منابع مشابه
Comparing Structure Learning Methods for RKHS Embeddings of Protein Structures
Non-parametric graphical models, embedded in reproducing kernel Hilbert spaces, provide a framework to model multi-modal and arbitrary multi-variate distributions, which are essential when modeling complex protein structures. Non-parametric belief propagation requires the structure of the graphical model to be known a priori. Currently there are nonparametric structure learning algorithms avail...
متن کاملDeepCoder: Semi-parametric Variational Autoencoders for Facial Action Unit Intensity Estimation
Variational (deep) parametric auto-encoders (VAE) have shown a great potential for unsupervised extraction of latent representations from large amounts of data. Human face exhibits an inherent hierarchy in facial representations (encoded in facial action units (AUs) and their intensity). This makes VAE a sophisticated method for learning facial features for AU intensity estimation. Yet, most ex...
متن کاملA Formal Analysis of Parametric Design Problem Solving
A formal analysis of the problem of parametric design is given on the basis of the competence-theory approach to problem solving methods. In particular, the ontological commitments and assumptions underlying some problem solving methods as used in the VT task are investigated.
متن کاملNon-parametric Policy Search with Limited Information Loss
Learning complex control policies from non-linear and redundant sensory input is an important challenge for reinforcement learning algorithms. Non-parametric methods that approximate values functions or transition models can address this problem, by adapting to the complexity of the data set. Yet, many current non-parametric approaches rely on unstable greedy maximization of approximate value f...
متن کاملTask-Induced Involvement in L2 Vocabulary Learning: A Case for Listening Comprehension
The study aimed at investigating whether the retention of vocabulary acquired incidentally is dependent upon the amount of task-induced involvement. Immediate and delayed retention of twenty unfamiliar words was examined in three learning tasks( listening comprehension + group discussion, listening comprehension + dictionary checking + summary writing in L1, and listening comprehension + dictio...
متن کامل