Proves near-tight concentration for polynomial functions of high-temperature Ising models.
problem Understanding interactions in high-dimensional data like social networks.
method Proves concentration of measure for polynomial functions of the Ising model.
result Polynomial functions of high-temperature Ising models exhibit exponential tails with optimal radius.
The paper studies structure detection in high-temperature ferromagnetic models.
problem Distinguishing between empty models and models with a specific subgraph structure.
method Matching upper and lower bounds for minimax testing, and computational hardness results.
result Arboricity drives the testability of the problem, and there are no polynomial time tests under certain conditions.
Algorithm learns Sherrington-Kirkpatrick model parameters at low temperatures.
problem Learning parameters of random graphical models at low temperatures.
method Multiplicative-weight update algorithm for polynomial time learning.
result Algorithm learns SK model parameters at β ≤ log n β\leq \sqrt{\log n} β ≤ log n . A new method uses modified Boltzmann weights to infer system configurations from observed data.
problem Inference of system configurations from limited observed data.
method Data-driven approach based on re-weighting observed configurations to achieve a flat distribution probability.
result Accurate inference of system configurations with high-temperature re-weighting of observations.
The paper proposes a thermodynamic potential to guide training of generative models, breaking ergodicity to improve functionality.
problem Improving generative model functionality while limiting access to underrepresented patterns.
method Constructing a thermodynamic potential that guides training, leading to multiple minima in the free energy.
result Training a generative model breaks ergodicity, preventing escape into the high-temperature phase.
The Gibbs algorithm's generalization error is bounded, improving with prior volume in low temperatures.
problem Bounding the generalization error of the Gibbs algorithm in low temperature regimes.
method Analyzes the Gibbs algorithm's performance, extending known high-temperature bounds to low-temperature scenarios.
result With high probability, the generalization error decreases with the total prior volume of similar hypotheses.
Paper analyzes Gibbs and Langevin Monte Carlo for interpolation regime, showing generalization from low errors.
problem Analyzing Gibbs and Langevin Monte Carlo in overparameterized interpolation regime.
method Data-dependent bounds and stability under approximation with Langevin Monte Carlo.
result Generalization is signaled by small training errors in noisy regime, with bounds stable under approximation.
Introduces bi-temperature logistic loss for more robust training.
problem Training neural nets with noise robustness.
method Introduces two temperatures into logistic loss and Bregman divergences.
result Training becomes more robust to noise with bi-temperature loss.
Proposes r2SGLD for efficient constrained exploration in non-convex learning.
problem Stagnation in high-temperature chains of reSGLD in distribution tails.
method r2SGLD: replica exchange with reflection steps in a bounded domain.
result Reflection steps enhance mixing rates with quadratic improvement in domain diameter.
LLMs are compared to Markov chains for natural language processing.
problem Theoretical analysis of LLMs' generalization capabilities.
method Equivalence between LLMs and Markov chains, studying multi-step inference.
result Derives generalization bounds for LLMs, capturing their behavior in practice.
Study shows sample complexity for logistic regression with normal covariates.
problem Estimating parameters of logistic regression with normal design.
method Analyzes sample complexity in terms of dimension and inverse temperature.
result Shows two change-points in sample complexity curve based on inverse temperature.
Gradient flow in a potential energy (or Euclidean action) landscape provides a natural set of paths connecting different saddle points. We apply this method to General Relativity, where gradient flow is Ricci flow, and focus on the example of 4-dimensional Euclidean gravity with boundary S^1 x S^2, representing the can…
We describe an adaptation of the simulated annealing algorithm to nonparametric clustering and related probabilistic models. This new algorithm learns nonparametric latent structure over a growing and constantly churning subsample of training data, where the portion of data subsampled can be interpreted as the inverse …
Study non-negative curvature Markov chains, proving entropy contraction.
problem Prove entropy contraction for Markov chains with non-negative curvature.
method Prove 1-step contraction in Wasserstein distance implies 1-step contraction in relative entropy.
result Prove MLSI with constant equal to minimal rate increment for mean-field zero-range process.
Optimal SQ bounds for learning binary product distributions and Ising models.
problem Learning binary product distributions and Ising models robustly.
method Statistical Query (SQ) lower bounds for robust learning.
result Optimal SQ lower bounds match known algorithm error guarantees.
Review of mean-field methods for neural network inference.
problem Understanding neural network learning from a theoretical perspective.
method Mean-field methods, high-temperature expansions, replica method, message passing algorithms.
result Equivalences and complementarities of mean-field methods.
PTSD improves neural samplers by combining diffusion models and PT, enhancing efficiency.
problem Efficiency and correlation issues in neural samplers compared to PT.
method Sequential training of diffusion models across temperatures, combining high-temperature models for approximate lower-temperature samples.
result Significantly improved target evaluation efficiency, outperforming diffusion-based samplers.
Estimates binary labels from dependent data using Markov Random Fields.
problem Statistical estimation from dependent data across spatial, temporal, and social domains.
method Modeling dependencies as Markov Random Fields and providing efficient estimation algorithms.
result Statistically efficient estimation rates for Ising models from a single sample.
We prove a mapping between dual and primal factor graph marginals for efficient estimation.
problem Efficient estimation of marginal densities in factor graphs.
method Local mappings derived from Fourier transforms of local factors, applied to Ising and Potts models.
result Marginal densities can be more accurately estimated in the dual domain.
Study extends deep learning theory to long-range spin systems.
problem Exploring deep learning in long-range spin systems.
method MCMC simulations and RBM training for critical temperature and scaling dimensions.
result RBM flow for long-range models does not converge to correct scaling dimensions.
Statistical physics method analyzes error in learning Ising model couplings.
problem Analyzing error in learning Ising model couplings from independent data.
method Combining replica method and cavity approach for densely connected systems.
result Explicit estimator achieves minimal reconstruction error but requires prior knowledge.
Fine-tuning LLMs on privacy-sensitive data introduces privacy risk, and synthetic data audits can quantify this risk.
problem Fine-tuning LLMs on privacy-sensitive data introduces privacy risk.
method Generate synthetic canaries via high-temperature sampling from LLMs.
result Synthetic canaries are high-influence outliers that ensure strong audits.
New models explain heavy-tailed behavior in neural networks.
problem Heavy-tailed spectral densities in neural networks.
method High-temperature Marchenko-Pastur (HTMP) ensemble models.
result Heavy-tailed behavior arises from three factors: data structure, training temperature, and eigenvector entropy.
Distillation affects some classes more than others, impacting fairness and bias.
problem Distillation affects some classes more than others, impacting fairness and bias.
method Examined class-wise accuracy and fairness metrics (DPD, EOD) on models trained with different datasets.
result Increasing the distillation temperature improves the distilled student model's fairness and individual fairness.
A model predicts how hyperparameters affect pruning performance.
problem Predicting the impact of hyperparameters on pruning performance.
method Phenomenological model using temperature-like and load-like parameters.
result A sharp transition phenomenon in pruning performance.
Quantum computing at room temperature achieves high accuracy in image classification.
problem Classifying images with single photons at room temperature.
method Optical transformation of quantum state to exploit interference and entanglement.
result Theoretical accuracy of 41.27% for MNIST and 36.14% for Fashion-MNIST.
CNN detects phase transitions in Potts models without prior knowledge.
problem Detecting phase transitions in q q q -state Potts models using deep learning. method Trained a deep CNN on Ising model spin configurations and temperatures, then tested on Potts model images.
result Deep CNN accurately detects phase transitions in Potts models, including high- and low-temperature regions.
CNN accurately reconstructs lattice topology with strong thermal fluctuations.
problem Reconstructing lattice topology with strong thermal fluctuations and unbalanced data.
method Deep convolutional neural network (CNN) mapping local magnetic moments to coupling probabilities.
result CNN accurately reconstructs lattice topology where thermal fluctuations dominate.
Enhanced Zika spread forecasting using topological data analysis.
problem Challenging prediction of Zika virus spread due to nonlinear spatio-temporal dependency and lack of historical records.
method Integrates topological data analysis, specifically persistent homology, into predictive machine learning models.
result Ensemble forecasting improves Zika spread predictions in Brazil.
New method interprets quantum many-body snapshots for phase detection.
problem Classifying phases of matter from quantum simulations.
method Confusion learning with correlation convolutional neural networks.
result Network detects changes in thermodynamic properties of quantum systems.
Unified approach learns Ising models from various dynamics and data types.
problem Efficiently learning Ising model parameters from data under diverse conditions.
method Simple logistic regression approach, generalizing existing algorithms.
result Logistic regression succeeds in multiple new settings where assumptions are violated.
The study optimizes simulated annealing's cooling schedule for better performance.
problem Designing optimal cooling schedules for simulated annealing to improve its performance.
method Analyzed the cooling schedule's impact on simulated annealing's performance and provided sample and simulation complexity results.
result Optimal cooling schedules can be found with a small number of samples, improving the algorithm's runtime or success rate.
Statistical mechanics helps understand sparse linear regression limits.
problem Understanding limits of sparse linear regression solutions.
method Replica method from statistical mechanics.
result Wide parameter region where local search algorithms can find ground state.
Automated neural network potentials achieve coupled cluster accuracy for protonated water clusters.
problem Creating highly accurate potential energy surfaces for chemical systems.
method Automated fitting of neural network potentials to ab initio reference calculations.
result Single potential energy surface for H3O+ to H9O4+ clusters at essentially converged coupled cluster accuracy.
This paper optimizes a power-to-heat system using reinforcement learning for cost minimization under uncertain conditions.
problem Optimizing a power-to-heat system with fluctuating renewable energy sources.
method Stochastic optimal control, reinforcement learning (Q-learning).
result Reinforcement learning provides an efficient solution to the optimization problem.