1 code implementation • 27 Sep 2023 • Jacek Cyranka, Szymon Haponiuk
In order to support the advancement of machine learning methods for predicting time-series data, we present a comprehensive dataset designed explicitly for long-term time-series forecasting.
1 code implementation • 28 Jul 2023 • Jacek Cyranka, Kevin E M Church, Jean-Philippe Lessard
We raise concerns about controllers' robustness in simple reinforcement learning benchmark problems.
no code implementations • 28 Jan 2022 • Bartłomiej Polaczyk, Jacek Cyranka
Second, we provide a technical result (working also for general approximators) relating solutions of the aforementioned differential inclusion to the (discrete) stochastic gradient descent sequences, hence establishing linear convergence towards zero loss for the stochastic gradient descent iterations.
no code implementations • 29 Sep 2021 • Jacek Cyranka, Zuzanna Opała, Jacek Płocharczyk, Mikhail Zanka
We introduce an algorithm for reinforcement learning, in which the actor plans for the next state provided the current state.
no code implementations • 16 Dec 2020 • Sophie Gruenbacher, Ramin Hasani, Mathias Lechner, Jacek Cyranka, Scott A. Smolka, Radu Grosu
We show that Neural ODEs, an emerging class of time-continuous neural networks, can be verified by solving a set of global-optimization problems.
1 code implementation • 14 Dec 2020 • Sophie Gruenbacher, Jacek Cyranka, Mathias Lechner, Md. Ariful Islam, Scott A. Smolka, Radu Grosu
Secondly, it computes the next reachset as the intersection of two balls: one based on the Cartesian metric and the other on the new metric.
2 code implementations • 17 Oct 2019 • Jacek Cyranka, Alexander Georges, David Meyer
We propose a classifier based on applying the Mapper algorithm to data projected onto a latent space.
1 code implementation • 3 Mar 2017 • Jacek Cyranka, Thomas Wanner
We present a computer-assisted proof of heteroclinic connections in the one-dimensional Ohta-Kawasaki model of diblock copolymers.
Analysis of PDEs Computational Engineering, Finance, and Science Dynamical Systems Numerical Analysis 35B40, 35B41, 35K55, 65C20, 35Q99, 15B99, 68U20