arXiv subjects

Maciej Klimek

Publications and source records attributed to Maciej Klimek.

4 recordsLinked to original sources

arXiv2023

Łojasiewicz exponent and pluricomplex Green function on algebraic sets

We study pluricomplex Green functions on algebraic sets. Let $f$ be a proper holomorphic mapping between two algebraic sets. Given a compact set $K$ in the range of $f$, we show how to estimate the pluricomplex Green functions of $K$ and of $f^{-1}(K)$ in terms of each other, the Łojasiewicz exponent of $f$ and the growth exponent of $f$. This result leads to explicit examples of pluricomplex Green functions on algebraic sets. We also present an enhanced version of the Bernstein-Walsh polynomial inequality specific to algebraic sets. This article provides a theoretical framework for future investigations of the rate of polynomial approximation of holomorphic functions on algebraic sets in the style of Bernstein-Walsh-Siciak theorem.

math.CV↗

arXiv2018

Improved GQ-CNN: Deep Learning Model for Planning Robust Grasps

Recent developments in the field of robot grasping have shown great improvements in the grasp success rates when dealing with unknown objects. In this work we improve on one of the most promising approaches, the Grasp Quality Convolutional Neural Network (GQ-CNN) trained on the DexNet 2.0 dataset. We propose a new architecture for the GQ-CNN and describe practical improvements that increase the model validation accuracy from 92.2% to 95.8% and from 85.9% to 88.0% on respectively image-wise and object-wise training and validation splits.

cs.LG↗

arXiv2017

Atari games and Intel processors

The asynchronous nature of the state-of-the-art reinforcement learning algorithms such as the Asynchronous Advantage Actor-Critic algorithm, makes them exceptionally suitable for CPU computations. However, given the fact that deep reinforcement learning often deals with interpreting visual information, a large part of the train and inference time is spent performing convolutions. In this work we present our results on learning strategies in Atari games using a Convolutional Neural Network, the Math Kernel Library and TensorFlow 0.11rc0 machine learning framework. We also analyze effects of asynchronous computations on the convergence of reinforcement learning algorithms.

cs.DC↗

arXiv2015

The least squares method for option pricing revisited

It is shown that the the popular least squares method of option pricing converges even under very general assumptions. This substantially increases the freedom of creating different implementations of the method, with varying levels of computational complexity and flexible approach to regression. It is also argued that in many practical applications even modest non-linear extensions of standard regression may produce satisfactory results. This claim is illustrated with examples.

q-fin.CP↗