Imagen de Portada

A Theory of Online Learning with Autoregressive Chain-of-Thought Reasoning

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Doron-Arad, Ilan, Mehalel, Idan, Mossel, Elchanan
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Online Realizable Regression and Applications for ReLU Networks
por: Doron-Arad, Ilan, et al.
Publicado: (2026)

Why ReLU? A Bit-Model Dichotomy for Deep Network Training
por: Doron-Arad, Ilan, et al.
Publicado: (2026)

Online Learning of Neural Networks
por: Daniely, Amit, et al.
Publicado: (2025)

Sample Complexity of Autoregressive Reasoning: Chain-of-Thought vs. End-to-End
por: Hanneke, Steve, et al.
Publicado: (2026)

On the Hardness of Training Deep Neural Networks Discretely
por: Doron-Arad, Ilan
Publicado: (2024)

A Mathematical Model for Curriculum Learning for Parities
por: Cornacchia, Elisabetta, et al.
Publicado: (2023)

Most Convolutional Networks Suffer from Small Adversarial Perturbations
por: Daniely, Amit, et al.
Publicado: (2026)

Deterministic Apple Tasting
por: Chase, Zachary, et al.
Publicado: (2024)

Noise Sensitivity and Learning Lower Bounds for Hierarchical Functions
por: Li, Rupert, et al.
Publicado: (2025)

Some Theoretical Limitations of t-SNE
por: Li, Rupert, et al.
Publicado: (2026)

Bandit-Feedback Online Multiclass Classification: Variants and Tradeoffs
por: Filmus, Yuval, et al.
Publicado: (2024)

The Benefits of Temporal Correlations: SGD Learns k-Juntas from Random Walks Efficiently
por: Cornacchia, Elisabetta, et al.
Publicado: (2026)

A Tight Lower Bound for Non-stochastic Multi-armed Bandits with Expert Advice
por: Chase, Zachary, et al.
Publicado: (2025)

Sample-Efficient Linear Regression with Self-Selection Bias
por: Gaitonde, Jason, et al.
Publicado: (2024)

Better Models and Algorithms for Learning Ising Models from Dynamics
por: Gaitonde, Jason, et al.
Publicado: (2025)

Multiclass Online Learnability under Bandit Feedback
por: Raman, Ananth, et al.
Publicado: (2023)

A Theory of Learning with Autoregressive Chain of Thought
por: Joshi, Nirmit, et al.
Publicado: (2025)

Bypassing the Noisy Parity Barrier: Learning Higher-Order Markov Random Fields from Dynamics
por: Gaitonde, Jason, et al.
Publicado: (2024)

Low-dimensional Functions are Efficiently Learnable under Randomly Biased Distributions
por: Cornacchia, Elisabetta, et al.
Publicado: (2025)

Denoising distances beyond the volumetric barrier
por: Huang, Han, et al.
Publicado: (2026)

Reconstructing the Geometry of Random Geometric Graphs
por: Huang, Han, et al.
Publicado: (2024)

A Hierarchical Language Model with Predictable Scaling Laws and Provable Benefits of Reasoning
por: Gaitonde, Jason, et al.
Publicado: (2026)

Optimal Prediction Using Expert Advice and Randomized Littlestone Dimension
por: Filmus, Yuval, et al.
Publicado: (2023)

The Refutability Gap: Challenges in Validating Reasoning by Large Language Models
por: Mossel, Elchanan
Publicado: (2025)

Learning and Testing Convex Functions
por: Pinto Jr., Renato Ferreira, et al.
Publicado: (2025)

On Learning Verifiers and Implications to Chain-of-Thought Reasoning
por: Balcan, Maria-Florina, et al.
Publicado: (2025)

On Algorithmic Robustness of Corrupted Markov Chains
por: Gaitonde, Jason, et al.
Publicado: (2025)

Non-Linear Paging
por: Doron-Arad, Ilan, et al.
Publicado: (2024)

Fractured Chain-of-Thought Reasoning
por: Liao, Baohao, et al.
Publicado: (2025)

The Kinetics of Reasoning: How Chain-of-Thought Shapes Learning in Transformers?
por: Pengmei, Zihan, et al.
Publicado: (2025)

Regret-Oracle Complexity Tradeoffs in Agnostic Online Learning
por: Attias, Idan, et al.
Publicado: (2026)

Reasoning by Superposition: A Theoretical Perspective on Chain of Continuous Thought
por: Zhu, Hanlin, et al.
Publicado: (2025)

Eliciting Chain-of-Thought Reasoning for Time Series Analysis using Reinforcement Learning
por: Parker, Felix, et al.
Publicado: (2025)

Continuous Chain of Thought Enables Parallel Exploration and Reasoning
por: Gozeten, Halil Alperen, et al.
Publicado: (2025)

Reasoning Models Sometimes Output Illegible Chains of Thought
por: Jose, Arun
Publicado: (2025)

RL's Razor: Why Online Reinforcement Learning Forgets Less
por: Shenfeld, Idan, et al.
Publicado: (2025)

Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMs
por: Zhang, Xuan, et al.
Publicado: (2024)

Demystifying Long Chain-of-Thought Reasoning in LLMs
por: Yeo, Edward, et al.
Publicado: (2025)

Understanding Hidden Computations in Chain-of-Thought Reasoning
por: Bharadwaj, Aryasomayajula Ram
Publicado: (2024)

Unveiling Confirmation Bias in Chain-of-Thought Reasoning
por: Wan, Yue, et al.
Publicado: (2025)