Search Results for author:
Found 10 papers, 9 papers with code
Predicting Properties of Periodic Systems from Cluster Data: A Case Study of Liquid Water
The accuracy of the training data limits the accuracy of bulk properties from machine-learned potentials.
Uncertainty-biased molecular dynamics for learning uniformly accurate interatomic potentials
Existing biased and unbiased MD simulations, however, are prone to miss either rare events or extrapolative regions -- areas of the configurational space where unreliable predictions are made.
Mind the spikes: Benign overfitting of kernels and neural networks in fixed dimension
In this paper, we show that the smoothness of the estimators, and not the dimension, is the key: benign overfitting is possible if and only if the estimator's derivatives are large enough.
Convergence Rates for Non-Log-Concave Sampling and Log-Partition Estimation
Specifically, for $m$-times differentiable functions in $d$ dimensions, the optimal rate for algorithms with $n$ function evaluations is known to be $O(n^{-m/d})$, where the constant can potentially depend on $m, d$ and the function to be optimized.
Transfer learning for chemically accurate interatomic neural network potentials
This work studies the capability of transfer learning, in particular discriminative fine-tuning, for efficiently generating chemically accurate interatomic neural network potentials on organic molecules from the MD17 and ANI data sets.
A Framework and Benchmark for Deep Batch Active Learning for Regression
We provide open-source code that includes efficient implementations of all kernels, kernel transformations, and selection methods, and can be used for reproducing our results.
Fast and Sample-Efficient Interatomic Neural Network Potentials for Molecules and Materials Based on Gaussian Moments
Artificial neural networks (NNs) are one of the most frequently used machine learning approaches to construct interatomic potentials and enable efficient large-scale atomistic simulations with almost ab initio accuracy.
On the Universality of the Double Descent Peak in Ridgeless Regression
We prove a non-asymptotic distribution-independent lower bound for the expected mean squared generalization error caused by label noise in ridgeless linear regression.
Training Two-Layer ReLU Networks with Gradient Descent is Inconsistent
We prove that two-layer (Leaky)ReLU networks initialized by e. g. the widely used method proposed by He et al. (2015) and trained using gradient descent on a least-squares loss are not universally consistent.
Efficient Neighbor-Finding on Space-Filling Curves
In this thesis, we show how neighbors on many regular grids ordered by space-filling curves can be found in an average-case time complexity of $O(1)$.
Computational Geometry Data Structures and Algorithms Performance
