Step-by-step implementation of the classic Müller-Brown potential in PyTorch, with performance comparisons between analytical and automatic differentiation approaches for molecular dynamics and machine learning applications.
A PyTorch testbed for the Muller-Brown potential: analytical and autograd force kernels, and a BAOAB Langevin sampler validated against the canonical distribution.
ICML 2025 methodological paper introducing SPHNet, which uses adaptive network sparsification to overcome the computational bottleneck of tensor products in SE(3)-equivariant networks, achieving up to 7x speedup and 75% memory reduction on DFT Hamiltonian prediction tasks.
A NeurIPS 2021 method paper introducing Noise Contrastive Priors to address the VAE ‘prior hole’ problem, where standard Gaussian priors assign high density to regions of latent space that don’t correspond to realistic data, using energy-based models trained with contrastive learning to match the aggregate posterior.
A ground-up PyTorch Word2Vec. Tensorizing the Huffman tree turns pointer-chasing Hierarchical Softmax into dense GPU ops compatible with torch.compile.
A complete guide to implementing modern Variational Autoencoders in PyTorch. Includes a copy-pasteable implementation, explanation of KL annealing to fix posterior collapse, and a deep dive into stable standard deviation parameterizations.
Learn to align molecular structures and point clouds using the Kabsch algorithm, with differentiable implementations for modern ML frameworks.
A PyTorch implementation enforcing Lyapunov stability on RNN controllers, solving a semidefinite program inside the training loop to certify safety.
We develop EigenNoise, a zero-data initialization method for word vectors that synthesizes representations from Zipf’s Law alone, demonstrating competitive performance to GloVe after fine-tuning without requiring any pre-training corpus.
Key dimensions that have helped me understand multi-arm bandit problems: action space, problem structure, external information, reward mechanism, and learner feedback.
Discover how NEAT and HyperNEAT changed neuroevolution by automatically designing neural network architectures and scaling them through geometric patterns.
A fork of Dennis Wilson’s CGP.jl adding the Atari reinforcement-learning experiment layer: experiment variants, fitness functions, and hyperparameter tuning.