Learning data discretization via convex optimization
نویسندگان
چکیده
منابع مشابه
Sparse Reinforcement Learning via Convex Optimization
We propose two new algorithms for the sparse reinforcement learning problem based on different formulations. The first algorithm is an off-line method based on the alternating direction method of multipliers for solving a constrained formulation that explicitly controls the projected Bellman residual. The second algorithm is an online stochastic approximation algorithm that employs the regulari...
متن کاملLearning Maximal Margin Markov Networks via Tractable Convex Optimization
Learning of Markov networks constitutes a challenging optimization problem. Even the predictive step of a general Markov network involves solving an NP-complete max-sum problem. By using the discriminative approach, learning of the Markov networks from noisy examples can be transformed to a convex quadratic program with intractably large number of linear constraints. The intractable quadratic p...
متن کاملMultitask learning meets tensor factorization: task imputation via convex optimization
We study a multitask learning problem in which each task is parametrized by a weight vector and indexed by a pair of indices, which can be e.g, (consumer, time). The weight vectors can be collected into a tensor and the (multilinear-)rank of the tensor controls the amount of sharing of information among tasks. Two types of convex relaxations have recently been proposed for the tensor multilinea...
متن کاملModel reduction via convex optimization
Roughly speaking, an “optimization problem” is the task of finding an element x = xo of a given set X for which the value Φ(x) of a given function Φ : X 7→ R is minimal. Alternatively, the objective could be to find an element xγ ∈ X such that Φ(xγh) < γ, where γ ∈ R is a given threshold, or to give evidence to non-existence of such xγ does not exist. Among the most familiar optimization proble...
متن کاملCapacity Control via Convex Optimization
Capacity control is a very important problem in civil infrastructure operation, but no general model exists for it. In this project we • Formulate the real-time capacity control problem of a single facility • Perform dynamic programming to search for the optimal solution • Implement piecewise linear regression to update the objective function, and SCP to update the policy • Extend the model to ...
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: Machine Learning
سال: 2017
ISSN: 0885-6125,1573-0565
DOI: 10.1007/s10994-017-5654-4