Auto-Encoding Variational Bayes (VAE Paper Summary)
Summary of Kingma & Welling's foundational VAE paper introducing the reparameterization trick and variational …...
Optimization
Importance Weighted Autoencoders (IWAE Paper Summary)
Summary of Burda, Grosse & Salakhutdinov's ICLR 2016 paper introducing Importance Weighted Autoencoders for tighter …...
Importance Weighted Autoencoders: Beyond the Standard VAE
Learn the crucial difference between multi-sample VAEs and Importance Weighted Autoencoders (IWAEs). Explore how …
How to Fold Graciously: The Levinthal Paradox
A perspective paper defining the Grand Challenge of protein folding: distinguishing kinetic pathways from thermodynamic …...
Müller-Brown Potential
The Müller-Brown potential: a classic two-dimensional analytical benchmark for testing optimization algorithms, reaction …...
High-Performance Müller-Brown Potential: A PyTorch Testbed for Machine Learning and Molecular Dynamics
High-performance, GPU-accelerated PyTorch framework for the Müller-Brown potential, featuring JIT compilation, …...
Implementing the Müller-Brown Potential in PyTorch
Guide to implementing the Müller-Brown potential in PyTorch, comparing analytical vs automatic differentiation with …
Müller-Brown Basin MA: Langevin Dynamics Simulation
Langevin dynamics simulation showing particle motion in the deep reactant minimum (Basin MA) of the Müller-Brown …
Müller-Brown Basin MB: Langevin Dynamics Simulation
Langevin dynamics simulation showing particle motion in the product minimum (Basin MB) of the Müller-Brown potential …
Müller-Brown Transition: Langevin Dynamics Simulation
Extended Langevin dynamics simulation showing particle transitions between different basins of the Müller-Brown …
A Contrastive Learning Approach for Training Variational Autoencoder Priors
Aneja et al.'s NeurIPS 2021 paper introducing Noise Contrastive Priors (NCPs) to address VAE's 'prior hole' problem with …...
Vectorizing the Tree: High-Performance Word2Vec in Pure PyTorch
A production-grade implementation of Hierarchical Softmax and Negative Sampling, featuring vectorized tree traversals, …...