Cover Image

An Analytical Theory of Spectral Bias in the Learning Dynamics of Diffusion Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Binxu, Pehlevan, Cengiz
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Computer Vision and Pattern Recognition Statistics Theory 68T07, 60G15 F.2.2; G.1.2; G.3; I.2.6
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Quantum computer formulation of the FKP-operator eigenvalue problem for probabilistic learning on manifolds
by: Soize, Christian, et al.
Published: (2025)

From Tail Universality to Bernstein-von Mises: A Unified Statistical Theory of Semi-Implicit Variational Inference
by: Plummer, Sean
Published: (2025)

A Random Matrix Theory Perspective on the Consistency of Diffusion Models
by: Wang, Binxu, et al.
Published: (2026)

VORT: Adaptive Power-Law Memory for NLP Transformers
by: Mlaiki, Nabil
Published: (2026)

Drift and selection in LLM text ecosystems
by: Riis, Søren
Published: (2026)

Revisiting Unbiased Implicit Variational Inference
by: Pielok, Tobias, et al.
Published: (2025)

Implicit Bias and Invariance: How Hopfield Networks Efficiently Learn Graph Orbits
by: Murray, Michael, et al.
Published: (2025)

The Unreasonable Effectiveness of Gaussian Score Approximation for Diffusion Models and its Applications
by: Wang, Binxu, et al.
Published: (2024)

Understanding and Tackling Over-Dilution in Graph Neural Networks
by: Lee, Junhyun, et al.
Published: (2025)

Semi-Implicit Variational Inference via Kernelized Path Gradient Descent
by: Pielok, Tobias, et al.
Published: (2025)

RL-Exec: Impact-Aware Reinforcement Learning for Opportunistic Optimal Liquidation, Outperforms TWAP and a Book-Liquidity VWAP on BTC-USD Replays
by: Duflot, Enzo, et al.
Published: (2025)

Attribution Projection Calculus: A Novel Framework for Causal Inference in Bayesian Networks
by: Amin, M Ruhul
Published: (2025)

RANDSMAPs: Random-Feature/multi-Scale Neural Decoders with Mass Preservation
by: Patsatzis, Dimitrios G., et al.
Published: (2026)

Variance-Reduced Diffusion Sampling via Target Score Identity
by: Duston, Alois, et al.
Published: (2026)

Transient Acceleration and Cross-Dissipation Interference in Fisher-Regularized Wasserstein Gradient Flows
by: Farmer, Michael, et al.
Published: (2026)

Latent-Autoregressive GP-VAE Language Model
by: Ruffenach, Yves
Published: (2025)

Constant-Target Energy Matching: A Unified Framework for Continuous and Discrete Density Estimation
by: Zeng, Zhijun, et al.
Published: (2026)

Feature Learning in Wide Neural Networks under $μ$P: Identifiability and Sparse-Dictionary Decomposition of the Mean-Field Limit
by: Xodarev, Akmal
Published: (2026)

Learning Nonlinear Regime Transitions via Semi-Parametric State-Space Models
by: Hiremath, Prakul Sunil
Published: (2026)

SCNode: Spatial and Contextual Coordinates for Graph Representation Learning
by: Uddin, Md Joshem, et al.
Published: (2024)

S$^3$: Structured Sparsity Specification
by: Ghriss, Ayoub
Published: (2026)

Neural Networks for Tamed Milstein Approximation of SDEs with Additive Symmetric Jump Noise Driven by a Poisson Random Measure
by: Ramirez-Gonzalez, Jose-Hermenegildo, et al.
Published: (2025)

CDFlow: Building Invertible Layers with Circulant and Diagonal Matrices
by: Feng, Xuchen, et al.
Published: (2025)

Drift is a Sampling Error: SNR-Aware Power Distributions for Long-Horizon Robotic Planning
by: Chen, Kewei, et al.
Published: (2026)

Unified Unbiased Variance Estimation for Maximum Mean Discrepancy: Robust Finite-Sample Performance with Imbalanced Data and Exact Acceleration under Null and Alternative Hypotheses
by: Zhong, Shijie, et al.
Published: (2026)

SCOPE: Selective Conformal Optimized Pairwise LLM Judging
by: Badshah, Sher, et al.
Published: (2026)

Graph Coloring for Multi-Task Learning
by: Patapati, Santosh
Published: (2025)

Learning Variational Quantum Circuit Parameters with Classical Artificial Intelligence for Quantum Phase Transition Detection
by: Li, Xin, et al.
Published: (2025)

Law-Strength Frontiers and a No-Free-Lunch Result for Law-Seeking Reinforcement Learning on Volatility Law Manifolds
by: Zhang, Jian'an
Published: (2025)

Evaluating the Quality of the Quantified Uncertainty for (Re)Calibration of Data-Driven Regression Models
by: Wibbeke, Jelke, et al.
Published: (2025)

Categorical Invariants of Learning Dynamics
by: Tamim, Abdulrahman
Published: (2025)

Asymptotic Consistency and Generalization in Hybrid Models of Regularized Selection and Nonlinear Learning
by: Galvão, Luciano Ribeiro, et al.
Published: (2025)

metabeta -- A fast neural model for Bayesian mixed-effects regression
by: Kipnis, Alex, et al.
Published: (2025)

Primal-Dual Sample Complexity Bounds for Constrained Markov Decision Processes with Multiple Constraints
by: Buckley, Max, et al.
Published: (2025)

Dual-Channel Feature Fusion for Joint Prediction in Dynamic Signed Weighted Networks
by: Zhang, Gaoxin, et al.
Published: (2026)

PolyKAN: A Polyhedral Analysis Framework for Provable and Approximately Optimal KAN Compression
by: Zhang, Di
Published: (2025)

Application of Sensitivity Analysis Methods for Studying Neural Network Models
by: Miao, Jiaxuan, et al.
Published: (2025)

Bayesian Modeling of Collatz Stopping Times: A Probabilistic Machine Learning Perspective
by: Bonacorsi, Nicolò, et al.
Published: (2026)

Front-door Reducibility: Reducing ADMGs to the Standard Front-door Setting via a Graphical Criterion
by: Mao, Jianqiao, et al.
Published: (2025)

Caterpillar GNN: Replacing Message Passing with Efficient Aggregation
by: Černý, Marek
Published: (2025)