To get good performance for two-dimensional site percolation developping a supervised, scale-shared neural architecture, it is key that the learned latent representation exhibits critical fluctuations and scale-dependent flows consistent with the renormalization-group structure of percolation.
Abstract
Machine learning offers a possible route to data-driven real-space renormalization when the relevant observables are nonlocal and difficult to prescribe explicitly. We explore this idea for two-dimensional site percolation developping a supervised, scale-shared neural architecture. The model recursively applies the same learned coarse-graining rule across scales, producing a latent field from which the crossing probability is predicted, while a corresponding fine-graining decoder reconstructs the largest-cluster mask. Trained only on small lattices, the model extrapolates to substantially larger systems, recovers the spanning cluster with high fidelity, and produces observables obeying the expected finite-size scaling near the critical point. We observe that to get such performance it is key that the learned latent representation exhibits critical fluctuations and scale-dependent flows consistent with the renormalization-group structure of percolation.
Despite their remarkable success in modeling complex data, generative models face a fundamental tradeoff. Global approaches can capture full structural coherence but suffer from high computational costs, while local models are efficient but often fail to reproduce long-range correlations and global coherence. The renor...
Simulating strongly correlated fermions remains a long-standing challenge due to the exponential complexity of the Hilbert space and the intricate sign structure of many-body wavefunctions. We introduce a variational framework centered on a neural network backflow transformation that combines deep learning with variati...
Tian-Shu Huang, Xiao-Wei Ou, V. Ozoliņš· 0 citations
We study the dynamics of Stochastic Gradient Descent (SGD), which is known to steer deep neural networks toward invariant sets that correspond to simpler subnetworks. How this steering unfolds over time remains poorly understood. We answer this by modeling the stochastic gradient flow (SGF) as a percolation process, in...
Sai Niranjan Ramachandran, Suvrit Sra· 0 citations
We introduce a renormalization-group (RG) guided machine-learning algorithm for lattice field generation based on approximate inversion of an RG transformation. A ``perfect blocking''construction supplies equilibrated long-distance modes, while a conditional normalizing flow reconstructs short-distance details and brie...
A. Hasenfratz, E. T. Neil, L. Parato et al.· 1 citation
This work develops a generative counterpart to the theory of benign overfitting and algorithmic regularization for overparameterized neural networks in the supervised lazy-training regime by studying denoising score matching in a vector-valued reproducing kernel Hilbert space with an inner-product kernel.
Hugo Latourelle-Vigeant, Sinho Chewi, Aram-Alexandre Pooladian et al.· 1 citation· ⚡1
Renormalization group (RG) is a core concept in physics from statistical mechanics to quantum field theory, yet its schemes differ widely between field theory and many-body physics. We formulate the Wilsonian RG as a quantum channel, whose Kraus representation yields pure conditional trajectories for pure inputs and re...
Takato Mori, Teruaki Nagasawa· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
