Image de couverture de livre

Provably Reliable Classifier Guidance via Cross-Entropy Control

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Sahu, Sharan, Banerjee, Arisina, Wu, Yuchen
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

On the Provable Suboptimality of Momentum SGD in Nonstationary Stochastic Optimization
par: Sahu, Sharan, et autres
Publié: (2026)

Adapt or Forget: Provable Tradeoffs Between Adam and SGD in Nonstationary Optimization
par: Sahu, Sharan, et autres
Publié: (2026)

Online Distributionally Robust LLM Alignment via Regression to Relative Reward
par: Sahu, Sharan, et autres
Publié: (2025)

Towards Optimal Differentially Private Regret Bounds in Linear MDPs
par: Sahu, Sharan
Publié: (2025)

Provable Efficiency of Guidance in Diffusion Models for General Data Distribution
par: Li, Gen, et autres
Publié: (2025)

Efficient Controllable Diffusion via Optimal Classifier Guidance
par: Oertell, Owen, et autres
Publié: (2025)

Armijo Line-search Can Make (Stochastic) Gradient Descent Provably Faster
par: Vaswani, Sharan, et autres
Publié: (2025)

C$^2$FG: Control Classifier-Free Guidance via Score Discrepancy Analysis
par: Gao, Jiayang, et autres
Publié: (2026)

Transformers Provably Learn Algorithmic Solutions for Graph Connectivity, But Only with the Right Data
par: Ye, Qilin, et autres
Publié: (2025)

Stochastic Runge-Kutta Methods: Provable Acceleration of Diffusion Models
par: Wu, Yuchen, et autres
Publié: (2024)

Provable Maximum Entropy Manifold Exploration via Diffusion Models
par: De Santi, Riccardo, et autres
Publié: (2025)

On the Robustness of Distribution Support under Diffusion Guidance
par: Cao, Ruijia, et autres
Publié: (2026)

Diffusion Classifier Guidance for Non-robust Classifiers
par: Vaeth, Philipp, et autres
Publié: (2025)

CFG-Ctrl: Control-Based Classifier-Free Diffusion Guidance
par: Wang, Hanyang, et autres
Publié: (2026)

Improving Preference Extraction In LLMs By Identifying Latent Knowledge Through Classifying Probes
par: Maiya, Sharan, et autres
Publié: (2025)

Provably Reliable Conformal Prediction Sets in the Presence of Data Poisoning
par: Scholten, Yan, et autres
Publié: (2024)

Neural-Rendezvous: Provably Robust Guidance and Control to Encounter Interstellar Objects
par: Tsukamoto, Hiroyasu, et autres
Publié: (2022)

Dynamic Classifier-Free Diffusion Guidance via Online Feedback
par: Papalampidi, Pinelopi, et autres
Publié: (2025)

The Eigenvalues Entropy as a Classifier Evaluation Measure
par: Dembélé, Doulaye
Publié: (2025)

Classifier-Free Guidance: From High-Dimensional Analysis to Generalized Guidance Forms
par: Pavasovic, Krunoslav Lehman, et autres
Publié: (2025)

Provable Weak-to-Strong Generalization via Benign Overfitting
par: Wu, David X., et autres
Publié: (2024)

Provably Safeguarding a Classifier from OOD and Adversarial Samples: an Extreme Value Theory Approach
par: Atienza, Nicolas, et autres
Publié: (2025)

Conditional Diffusion Models with Classifier-Free Gibbs-like Guidance
par: Moufad, Badr, et autres
Publié: (2025)

Provably Safe Reinforcement Learning for Stochastic Reach-Avoid Problems with Entropy Regularization
par: Mazumdar, Abhijit, et autres
Publié: (2026)

Provable Memory Efficient Self-Play Algorithm for Model-free Reinforcement Learning
par: Li, Na, et autres
Publié: (2025)

Analysis of Classifier-Free Guidance Weight Schedulers
par: Wang, Xi, et autres
Publié: (2024)

Theoretical Insights for Diffusion Guidance: A Case Study for Gaussian Mixture Models
par: Wu, Yuchen, et autres
Publié: (2024)

Temper-Then-Tilt: Principled Unlearning for Generative Models through Tempering and Classifier Guidance
par: Block, Jacob L., et autres
Publié: (2026)

Adaptive Diffusion Guidance via Stochastic Optimal Control
par: Azangulov, Iskander, et autres
Publié: (2025)

Provably Robust Training of Quantum Circuit Classifiers Against Parameter Noise
par: Tecot, Lucas, et autres
Publié: (2025)

Margin-calibrated Classifier Guidance for Property-driven Synthesis Planning
par: Laabid, Najwa, et autres
Publié: (2026)

CFG-OEC: Classifier Free Guidance with Orthogonal Error Correction
par: Yang, Nakgyu, et autres
Publié: (2025)

Dynamic Model Predictive Shielding for Provably Safe Reinforcement Learning
par: Banerjee, Arko, et autres
Publié: (2024)

Studying Classifier(-Free) Guidance From a Classifier-Centric Perspective
par: Zhao, Xiaoming, et autres
Publié: (2025)

Efficient Distillation of Classifier-Free Guidance using Adapters
par: Jensen, Cristian Perez, et autres
Publié: (2025)

Reward Weighted Classifier-Free Guidance as Policy Improvement in Autoregressive Models
par: Peysakhovich, Alexander, et autres
Publié: (2026)

Multi-Task Curriculum Graph Contrastive Learning with Clustering Entropy Guidance
par: Zeng, Chusheng, et autres
Publié: (2024)

Diffusion Models without Classifier-free Guidance
par: Tang, Zhicong, et autres
Publié: (2025)

Classifier-Free Guidance is a Predictor-Corrector
par: Bradley, Arwen, et autres
Publié: (2024)

Coherence Mechanisms for Provable Self-Improvement
par: Mohri, Mehryar, et autres
Publié: (2025)