A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
SchNetPack 2.0 enhances atomistic machine learning with improved neural networks.
The need for advanced materials has led to the development of complex, multi-component alloys or solid-solution alloys. These materials have shown exceptional properties like strength, toughness, ductility, electrical and electronic properties. Current development of such material systems are hindered by expensive expe…
Discovery of atomistic systems with desirable properties is a major challenge in chemistry and material science. Here we introduce a novel, autoregressive, convolutional deep neural network architecture that generates molecular equilibrium structures by sequentially placing atoms in three-dimensional space. The model e…
With the rise of deep neural networks for quantum chemistry applications, there is a pressing need for architectures that, beyond delivering accurate predictions of chemical properties, are readily interpretable by researchers. Here, we describe interpretation techniques for atomistic neural networks on the example of …
Optimizes atomic descriptors to reduce redundancy and improve machine learning models.
Study evaluates uncertainty quantification for atomistic neural networks, revealing complex relationships between error and uncertainty.
One endeavour of modern physical chemistry is to use bottom-up approaches to design materials and drugs with desired properties. Here we introduce an atomistic structure learning algorithm (ASLA) that utilizes a convolutional neural network to build 2D compounds and layered structures atom by atom. The algorithm takes …
Deep Learning has been shown to learn efficient representations for structured data such as image, text or audio. In this chapter, we present neural network architectures that are able to learn efficient representations of molecules and materials. In particular, the continuous-filter convolutional network SchNet accura…
Improved neural network models predict molecular and material properties efficiently.
Novel ML model predicts solvation free energies from atom interactions.
Develops neural networks for reductive Lie groups, enhancing symmetry respect.
We present a novel learning framework that consistently embeds underlying physics while bypassing a significant drawback of most modern, data-driven coarse-grained approaches in the context of molecular dynamics (MD), i.e., the availability of big data. The generation of a sufficiently large training dataset poses a co…
Transfer learning boosts chemically accurate neural network potentials for organic molecules.
ML4Chem is an open-source machine learning library for chemistry and materials science. It provides an extendable platform to develop and deploy machine learning models and pipelines and is targeted to the non-expert and expert users. ML4Chem follows user-experience design and offers the needed tools to go from data pr…
New method uses normalizing flows to improve force fields for coarse-grained molecular dynamics.
Extending spatio-temporal scale limitations of models for complex atomistic systems considered in biochemistry and materials science necessitates the development of enhanced sampling methods. The potential acceleration in exploring the configurational space by enhanced sampling methods depends on the choice of collecti…
We present a hybrid continuum-atomistic scheme which combines molecular dynamics (MD) simulations with on-the-fly machine learning techniques for the accurate and efficient prediction of multiscale fluidic systems. By using a Gaussian process as a surrogate model for the computationally expensive MD simulations, we use…
A framework to compare atomistic descriptors and their transformations.
TACE unifies scalar and tensorial modeling in Cartesian space for accurate, stable, and efficient atomistic predictions.
Machine learning advances chemistry and materials science by enabling large-scale exploration of chemical space based on quantum chemical calculations. While these models supply fast and accurate predictions of atomistic chemical properties, they do not explicitly capture the electronic degrees of freedom of a molecule…
Introduce a thermodynamically informed, temperature-transferable MLCG framework for proteins.
We present atomistic molecular dynamics simulations of two Polyethylene systems where all entanglements are trapped: a perfect network, and a melt with grafted chain ends. We examine microscopically at what level topological constraints can be considered as a collective entanglement effect, as in tube model theories, o…
Machine learning generates coarse-grained force fields for molecular dynamics.
We seek to deepen understanding of the micro-foundations of institutionalization while contributing to a sociological theory of markets by investigating the puzzle of price bubbles in financial markets. We find that such markets, despite textbook conditions of high efficiency -- perfect information, atomistic agents, n…
Graph neural networks fail to distinguish certain 3D atom configurations.
Free energy perturbation (FEP) was proposed by Zwanzig more than six decades ago as a method to estimate free energy differences, and has since inspired a huge body of related methods that use it as an integral building block. Being an importance sampling based estimator, however, FEP suffers from a severe limitation: …
Generative models accelerate molecular dynamics by four orders of magnitude.
Complex spatiotemporal dynamics of physicochemical processes are often modeled at a microscopic level (through e.g. atomistic, agent-based or lattice models) based on first principles. Some of these processes can also be successfully modeled at the macroscopic level using e.g. partial differential equations (PDEs) desc…
EGR refines and assesses protein complex structures.
In this work, we extend the SchNet architecture by using weighted skip connections to assemble the final representation. This enables us to study the relative importance of each interaction block for property prediction. We demonstrate on both the QM9 and MD17 dataset that their relative weighting depends strongly on t…
Unconstrained models learn physical symmetries effectively with simple data augmentation.
Ancient grain boundaries resemble atoms in their formation and properties.
New model predicts molecular wavefunctions and densities with unprecedented accuracy.
The CAPM's market returns are endogenously determined, affecting all assets' expected returns.
Wavelet scattering predicts material properties beyond training data.
Improved CG force-field learning from all-atom data.
CG-BGs combine flow-based models with PMFs to sample large systems efficiently.
Molecular dynamics simulations use statistical mechanics at the atomistic scale to enable both the elucidation of fundamental mechanisms and the engineering of matter for desired tasks. The behavior of molecular systems at the microscale is typically simulated with differential equations parameterized by a Hamiltonian,…
The modeling of atomistic biomolecular simulations using kinetic models such as Markov state models (MSMs) has had many notable algorithmic advances in recent years. The variational principle has opened the door for a nearly fully automated toolkit for selecting models that predict the long-time kinetics from molecular…
Bayesian regression underestimates parameter uncertainties in noisy models.
Often the analysis of time-dependent chemical and biophysical systems produces high-dimensional time-series data for which it can be difficult to interpret which individual features are most salient. While recent work from our group and others has demonstrated the utility of time-lagged co-variate models to study such …
Machine-learning of atomic-scale properties amounts to extracting correlations between structure, composition and the quantity that one wants to predict. Representing the input structure in a way that best reflects such correlations makes it possible to improve the accuracy of the model for a given amount of reference …
Molecular dynamics simulations provide theoretical insight into the microscopic behavior of materials in condensed phase and, as a predictive tool, enable computational design of new compounds. However, because of the large temporal and spatial scales involved in thermodynamic and kinetic phenomena in materials, atomis…
Atomistic or ab-initio molecular dynamics simulations are widely used to predict thermodynamics and kinetics and relate them to molecular structure. A common approach to go beyond the time- and length-scales accessible with such computationally expensive simulations is the definition of coarse-grained molecular models.…
New method designs antimicrobial peptides with high potency and low toxicity.
Graphs of neural networks are represented to preserve symmetry, improving performance across various tasks.
Neural networks can approximate functions uniformly across various measures.
Optimal rates for shallow ReLU networks in nonparametric regression.