Optimization of Gene Set Annotations Using Robust Trace-Norm Multitask Learning
نویسندگان
چکیده
منابع مشابه
Excess risk bounds for multitask learning with trace norm regularization
Trace norm regularization is a popular method of multitask learning. We give excess risk bounds with explicit dependence on the number of tasks, the number of examples per task and properties of the data distribution. The bounds are independent of the dimension of the input space, which may be infinite as in the case of reproducing kernel Hilbert spaces. A byproduct of the proof are bounds on t...
متن کاملFeature Learning for Multitask Learning Using l2,1 Norm Minimization
We look at solving the task of Multitask Feature Learning by way of feature selection. We find that formulating it as an l2,1 norm minimization problem helps with both sparsity and uniformity, which are required for Multitask Feature Learning. Two approaches are explored, one which formulates an equivalent convex optimization problem and iteratively solves it, and another which formulates two e...
متن کاملDistral: Robust multitask reinforcement learning
Most deep reinforcement learning algorithms are data inefficient in complex and rich environments, limiting their applicability to many scenarios. One direction for improving data efficiency is multitask learning with shared neural network parameters, where efficiency may be improved through transfer across related tasks. In practice, however, this is not usually observed, because gradients fro...
متن کاملMultitask learning in connectionist robust ASR using recurrent neural networks
The use of prior knowledge in machine learning techniques has been proved to give better generalisation performance for unseen data. However, this idea has not been investigated so far for robust ASR. Training several related tasks simultaneously is also called multitask learning (MTL): the extra tasks effectively incorporate prior knowledge. In this work we present an application of MTL in rob...
متن کاملLow-rank optimization with trace norm penalty
The paper addresses the problem of low-rank trace norm minimization. We propose an algorithm that alternates between fixed-rank optimization and rank-one updates. The fixed-rank optimization is characterized by an efficient factorization that makes the trace norm differentiable in the search space and the computation of duality gap numerically tractable. The search space is nonlinear but is equ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: IEEE/ACM Transactions on Computational Biology and Bioinformatics
سال: 2018
ISSN: 1545-5963,1557-9964,2374-0043
DOI: 10.1109/tcbb.2017.2690427