Geometrical complexity of data approximators
There are many methods developed to approximate a cloud of vectors embedded in high-dimensional space by simpler objects: starting from principal points and linear manifolds to self-organizing maps, neural gas, elastic maps, various types of principal curves and principal trees, and so on. For each type of approximators the measure of the approximator complexity was developed too. These measures are necessary to find the balance between accuracy and complexity and to define the optimal approximations of a given type. We propose a measure of complexity (geometrical complexity) which is applicable to approximators of several types and which allows comparing data approximations of different types.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Fitted Q-Iteration via Max-Plus-Linear Approximation
In this study, we consider the application of max-plus-linear approximators for Q-function in offline reinforcement learning of discounted Markov decision processes. In particular, we incorporate these approximators to p…
How low-cost AI universal approximators reshape market efficiency
The efficient market hypothesis (EMH) famously stated that prices fully reflect the information available to traders. This critically depends on the transfer of information into prices through trading strategies. Traders…
Parameterized Convex Universal Approximators for Decision-Making Problems
Parameterized max-affine (PMA) and parameterized log-sum-exp (PLSE) networks are proposed for general decision-making problems. The proposed approximators generalize existing convex approximators, namely, max-affine (MA)…
Decision MakingDeep Narrow Boltzmann Machines are Universal Approximators
We show that deep narrow Boltzmann machines are universal approximators of probability distributions on the activities of their visible units, provided they have sufficiently many hidden layers, each containing the same …
State2vec: Off-Policy Successor Features Approximators
A major challenge in reinforcement learning (RL) is the design of agents that are able to generalize across tasks that share common dynamics. A viable solution is meta-reinforcement learning, which identifies common stru…
Meta Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)