Cover Image

On the Provable Performance Guarantee of Efficient Reasoning Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zeng, Hao, Huang, Jianguo, Jing, Bingyi, Wei, Hongxin, An, Bo
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence Machine Learning Statistics Theory
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Conditional Performance Guarantee for Large Reasoning Models
by: Huang, Jianguo, et al.
Published: (2026)

RACER: Risk-Aware Calibrated Efficient Routing for Large Language Models
by: Hao, Sai, et al.
Published: (2026)

HyPAC: Cost-Efficient LLMs-Human Hybrid Annotation with PAC Error Guarantees
by: Zeng, Hao, et al.
Published: (2026)

Parametric Scaling Law of Tuning Bias in Conformal Prediction
by: Zeng, Hao, et al.
Published: (2025)

Model-agnostic Selective Labeling with Provable Statistical Guarantees
by: Huang, Huipeng, et al.
Published: (2025)

TorchCP: A Python Library for Conformal Prediction
by: Huang, Jianguo, et al.
Published: (2024)

A Computational Theory for Efficient Mini Agent Evaluation with Causal Guarantees
by: Yan, Hedong
Published: (2025)

Provable Training Data Identification for Large Language Models
by: Liu, Zhenlong, et al.
Published: (2025)

A note on the impossibility of conditional PAC-efficient reasoning in large language models
by: Zeng, Hao
Published: (2025)

Provable Reward-Agnostic Preference-Based Reinforcement Learning
by: Zhan, Wenhao, et al.
Published: (2023)

Provable Robust Overfitting Mitigation in Wasserstein Distributionally Robust Optimization
by: Liu, Shuang, et al.
Published: (2025)

Pessimism in the Face of Confounders: Provably Efficient Offline Reinforcement Learning in Partially Observable Markov Decision Processes
by: Lu, Miao, et al.
Published: (2022)

Can Generative Artificial Intelligence Survive Data Contamination? Theoretical Guarantees under Contaminated Recursive Training
by: Wang, Kevin, et al.
Published: (2026)

Characteristic Learning for Provable One Step Generation
by: Ding, Zhao, et al.
Published: (2024)

Transformers as Decision Makers: Provable In-Context Reinforcement Learning via Supervised Pretraining
by: Lin, Licong, et al.
Published: (2023)

U-Nets as Belief Propagation: Efficient Classification, Denoising, and Diffusion in Generative Hierarchical Models
by: Mei, Song
Published: (2024)

Path Regularization: A Near-Complete and Optimal Nonasymptotic Generalization Theory for Multilayer Neural Networks and Double Descent Phenomenon
by: Yu, Hao
Published: (2025)

A Unified Pair-GRPO Family: From Implicit to Explicit Preference Constraints for Stable and General RL Alignment
by: Yu, Hao
Published: (2026)

Efficient Sampling with Discrete Diffusion Models: Sharp and Adaptive Guarantees
by: Dmitriev, Daniil, et al.
Published: (2026)

Conditional Generative Models are Provably Robust: Pointwise Guarantees for Bayesian Inverse Problems
by: Altekrüger, Fabian, et al.
Published: (2023)

Absorb and Converge: Provable Convergence Guarantee for Absorbing Discrete Diffusion Models
by: Liang, Yuchen, et al.
Published: (2025)

Guaranteed Recovery of Unambiguous Clusters
by: Mazooji, Kayvon, et al.
Published: (2025)

Navigating the Exploration-Exploitation Tradeoff in Inference-Time Scaling of Diffusion Models
by: Su, Xun, et al.
Published: (2025)

Efficient Knowledge Distillation via Curriculum Extraction
by: Gupta, Shivam, et al.
Published: (2025)

Fine-tuning can Help Detect Pretraining Data from Large Language Models
by: Zhang, Hengxiang, et al.
Published: (2024)

Greedy Sampling Is Provably Efficient for RLHF
by: Wu, Di, et al.
Published: (2025)

Improved Guarantees for Heterogeneous Treatment-Effect Estimation via Matrix Completion
by: Mehrotra, Anay, et al.
Published: (2026)

Reject, Resample, Repeat: Understanding Parallel Reasoning in Language Model Inference
by: Golowich, Noah, et al.
Published: (2026)

On the Statistical Capacity of Deep Generative Models
by: Tam, Edric, et al.
Published: (2025)

Foundations of Top-$k$ Decoding For Language Models
by: Noarov, Georgy, et al.
Published: (2025)

Counterfactual Generative Modeling with Variational Causal Inference
by: Wu, Yulun, et al.
Published: (2024)

Cross-regularization: Adaptive Model Complexity through Validation Gradients
by: Brito, Carlos Stein
Published: (2025)

Training Implicit Generative Models via an Invariant Statistical Loss
by: de Frutos, José Manuel, et al.
Published: (2024)

Diffusion Models and the Manifold Hypothesis: Log-Domain Smoothing is Geometry Adaptive
by: Farghly, Tyler, et al.
Published: (2025)

Identifiability of Potentially Degenerate Gaussian Mixture Models With Piecewise Affine Mixing
by: Xu, Danru, et al.
Published: (2026)

Learning Interpretable Concepts: Unifying Causal Representation Learning and Foundation Models
by: Rajendran, Goutham, et al.
Published: (2024)

Finite-Particle Convergence Rates for Conservative and Non-Conservative Drifting Models
by: Balasubramanian, Krishnakumar
Published: (2026)

Adapting to Unknown Low-Dimensional Structures in Score-Based Diffusion Models
by: Li, Gen, et al.
Published: (2024)

On the Statistical Properties of Generative Adversarial Models for Low Intrinsic Data Dimension
by: Chakraborty, Saptarshi, et al.
Published: (2024)

Evaluating LLMs When They Do Not Know the Answer: Statistical Evaluation of Mathematical Reasoning via Comparative Signals
by: Dong, Zihan, et al.
Published: (2026)