Linearly Parameterized Bandits
نویسندگان
چکیده
منابع مشابه
Linearly Parameterized Bandits
We consider bandit problems involving a large (possibly infinite) collection of arms, in which the expected reward of each arm is a linear function of an r-dimensional random vector Z ∈ Rr, where r ≥ 2. The objective is to minimize the cumulative regret and Bayes risk. When the set of arms corresponds to the unit sphere, we prove that the regret and Bayes risk is of order Θ(r √ T ), by establis...
متن کاملA State and Parameter Identification Scheme for Linearly Parameterized Systems
Abstract This paper presents an adaptive algorithm to estimate states and unknown parameters simultaneously for nonlinear time invariant systems which depend affinely on the unknown parameters. The system output signals are filtered and re-parameterized into a regression form from which the least squares error scheme is applied to identify the unknown parameters. The states are then estimated b...
متن کاملReconstruction of linearly parameterized models using the vanishing points from a single image
In this paper, we propose a new method using only three vanishing points to recover the dimensions of object and its pose from a single image with a camera of unknown focal length. Our approach is to compute the dimensions of objects represented by the unit vector of objects from an image. The dimension vector v can be solved by the standard nonlinear optimization techniques with a multistart m...
متن کاملSGD Learns Over-parameterized Networks that Provably Generalize on Linearly Separable Data
Neural networks exhibit good generalization behavior in the over-parameterized regime, where the number of network parameters exceeds the number of observations. Nonetheless, current generalization bounds for neural networks fail to explain this phenomenon. In an attempt to bridge this gap, we study the problem of learning a two-layer over-parameterized neural network, when the data is generate...
متن کاملObservability and Local Observer Construction for Unknown Parameters in Linearly and Nonlinearly Parameterized Systems
Using geometric concepts from observability theory for nonlinear systems, we propose an approach for parameter estimation for linearly and nonlinearly parameterized systems. The proposed approach relies on extending a parameter estimation problem to a state estimation problem by introducing the parameters as auxiliary state variables. Applying tools from geometric nonlinear control theory we es...
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: Mathematics of Operations Research
سال: 2010
ISSN: 0364-765X,1526-5471
DOI: 10.1287/moor.1100.0446