no code implementations • 3 Oct 2023 • Victor Chardès, Suryanarayana Maddu, Michael J. Shelley
Inferring dynamical models from low-resolution temporal data continues to be a significant challenge in biophysics, especially within transcriptomics, where separating molecular programs from noise remains an important open problem.
no code implementations • 27 Jul 2023 • Dominik Sturm, Suryanarayana Maddu, Ivo F. Sbalzarini
We use a combination of unsupervised clustering and sparsity-promoting inference algorithms to learn locally dominant force balances that explain macroscopic pattern formation in self-organized active particle systems.
no code implementations • 21 Jan 2022 • Suryanarayana Maddu, Quentin Vagne, Ivo F. Sbalzarini
We present a principled data-driven strategy for learning deterministic hydrodynamic models directly from stochastic non-equilibrium active particle trajectories.
no code implementations • 7 Dec 2021 • Joel Jonsson, Bevan L. Cheeseman, Suryanarayana Maddu, Krzysztof Gonciarz, Ivo F. Sbalzarini
Here, we provide the algorithmic building blocks required to efficiently and natively process APR images using a wide range of algorithms that can be formulated in terms of discrete convolutions.
no code implementations • 2 Jul 2021 • Suryanarayana Maddu, Dominik Sturm, Christian L. Müller, Ivo F. Sbalzarini
We characterize and remedy a failure mode that may arise from multi-scale dynamics with scale imbalances during training of deep neural networks, such as Physics Informed Neural Networks (PINNs).
no code implementations • 15 Jan 2021 • Suryanarayana Maddu, Dominik Sturm, Bevan L. Cheeseman, Christian L. Müller, Ivo F. Sbalzarini
Often, this requires high-resolution or adaptive discretization grids to capture relevant spatio-temporal features in the PDE solution, e. g., in applications like turbulence, combustion, and shock propagation.
no code implementations • 11 Dec 2020 • Suryanarayana Maddu, Bevan L. Cheeseman, Christian L. Müller, Ivo F. Sbalzarini
We propose a statistical learning framework based on group-sparse regression that can be used to 1) enforce conservation laws, 2) ensure model equivalence, and 3) guarantee symmetries when learning or inferring differential-equation models from measurement data.
1 code implementation • 17 Jul 2019 • Suryanarayana Maddu, Bevan L. Cheeseman, Ivo F. Sbalzarini, Christian L. Müller
We show that in particular the combination of stability selection with the iterative hard-thresholding algorithm from compressed sensing provides a fast, parameter-free, and robust computational framework for PDE inference that outperforms previous algorithmic approaches with respect to recovery accuracy, amount of data required, and robustness to noise.