Generative diffusion and flow models are constructed to remain exactly on the Lorentz-invariant massless N-particle phase space manifold during sampling for particle physics applications.
Trajectory of mini-batch momentum: Batch size saturation and convergence in high dimensions
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
verdicts
UNVERDICTED 4representative citing papers
SGD on neural network weights induces a BBP phase transition that detaches signal eigenvalues from the random bulk, yielding an analytically solvable phase diagram for trainability in a linear teacher-student model.
Ridge regression in high dimensions exhibits power-law scalings because covariance fluctuations renormalize the ridge parameter, allowing closed-form error expressions and bias-variance decompositions for random feature models via free probability.
DNNs succeed by capturing high-order correlation structures in datasets, similar to mesoscale methods in physics.
citing papers explorer
-
Generative models on phase space
Generative diffusion and flow models are constructed to remain exactly on the Lorentz-invariant massless N-particle phase space manifold during sampling for particle physics applications.
-
Spectral phase transitions and trainability in neural network learning dynamics
SGD on neural network weights induces a BBP phase transition that detaches signal eigenvalues from the random bulk, yielding an analytically solvable phase diagram for trainability in a linear teacher-student model.
-
Scaling and renormalization in high-dimensional regression
Ridge regression in high dimensions exhibits power-law scalings because covariance fluctuations renormalize the ridge parameter, allowing closed-form error expressions and bias-variance decompositions for random feature models via free probability.
-
DNNs, Dataset Statistics, and Correlation Functions
DNNs succeed by capturing high-order correlation structures in datasets, similar to mesoscale methods in physics.