A foundational 1931 paper that derives exact recursive formulas for counting alkane structural isomers, correcting historical errors and establishing the first systematic enumeration up to C₄₀.
Explore two fundamental approaches to generating exponentially distributed random numbers: the modern inverse transform method using logarithms and von Neumann’s ingenious 1951 comparison-based algorithm that avoids transcendental functions entirely.
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 2-5x speedup while maintaining accuracy on DFT Hamiltonian prediction tasks.
Torrie and Valleau’s 1977 methodological breakthrough introducing importance sampling with non-physical distributions to overcome the sampling gap problem in Monte Carlo free-energy calculations, particularly for rare events and phase transitions.
A ground-up PyTorch implementation of Word2Vec treating it as a systems engineering challenge, with “tensorized tree” architecture converting pointer-chasing Hierarchical Softmax into dense GPU operations, infinite streaming datasets with Zipfian subsampling, and torch.compile compatibility for production-grade efficiency.
Weiler et al.’s NeurIPS 2018 paper introducing 3D Steerable CNNs that achieve SE(3) equivariance through group representation theory and spherical harmonic convolution kernels, eliminating the need for rotational data augmentation and improving data efficiency for scientific applications with rotational symmetry like molecular and protein structures.
Learn to align molecular structures and point clouds using the Kabsch algorithm, with differentiable implementations for modern ML frameworks.
A PyTorch implementation enforcing strict Lyapunov stability guarantees on recurrent neural network controllers through Integral Quadratic Constraints, bridging 1990s robust control theory with modern deep reinforcement learning by solving semidefinite programs inside the gradient descent loop to provide mathematical certificates of safety.
We provide the first analytical solution to Word2Vec’s softmax skip-gram objective, introducing the Independent Frequencies Model and deriving a low-cost, training-free method for measuring semantic bias directly from corpus statistics.
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.
Understand the pattern recognition behind Netflix recommendations, email spam filters, and game-playing AI through three core machine learning approaches.