Image de couverture de livre

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

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Doron-Arad, Ilan, Mehalel, Idan, Mossel, Elchanan
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

Online Realizable Regression and Applications for ReLU Networks
par: Doron-Arad, Ilan, et autres
Publié: (2026)

Why ReLU? A Bit-Model Dichotomy for Deep Network Training
par: Doron-Arad, Ilan, et autres
Publié: (2026)

Online Learning of Neural Networks
par: Daniely, Amit, et autres
Publié: (2025)

Sample Complexity of Autoregressive Reasoning: Chain-of-Thought vs. End-to-End
par: Hanneke, Steve, et autres
Publié: (2026)

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

A Mathematical Model for Curriculum Learning for Parities
par: Cornacchia, Elisabetta, et autres
Publié: (2023)

Most Convolutional Networks Suffer from Small Adversarial Perturbations
par: Daniely, Amit, et autres
Publié: (2026)

Deterministic Apple Tasting
par: Chase, Zachary, et autres
Publié: (2024)

Noise Sensitivity and Learning Lower Bounds for Hierarchical Functions
par: Li, Rupert, et autres
Publié: (2025)

Some Theoretical Limitations of t-SNE
par: Li, Rupert, et autres
Publié: (2026)

Bandit-Feedback Online Multiclass Classification: Variants and Tradeoffs
par: Filmus, Yuval, et autres
Publié: (2024)

The Benefits of Temporal Correlations: SGD Learns k-Juntas from Random Walks Efficiently
par: Cornacchia, Elisabetta, et autres
Publié: (2026)

A Tight Lower Bound for Non-stochastic Multi-armed Bandits with Expert Advice
par: Chase, Zachary, et autres
Publié: (2025)

Sample-Efficient Linear Regression with Self-Selection Bias
par: Gaitonde, Jason, et autres
Publié: (2024)

Better Models and Algorithms for Learning Ising Models from Dynamics
par: Gaitonde, Jason, et autres
Publié: (2025)

Multiclass Online Learnability under Bandit Feedback
par: Raman, Ananth, et autres
Publié: (2023)

A Theory of Learning with Autoregressive Chain of Thought
par: Joshi, Nirmit, et autres
Publié: (2025)

Bypassing the Noisy Parity Barrier: Learning Higher-Order Markov Random Fields from Dynamics
par: Gaitonde, Jason, et autres
Publié: (2024)

Low-dimensional Functions are Efficiently Learnable under Randomly Biased Distributions
par: Cornacchia, Elisabetta, et autres
Publié: (2025)

Denoising distances beyond the volumetric barrier
par: Huang, Han, et autres
Publié: (2026)

Reconstructing the Geometry of Random Geometric Graphs
par: Huang, Han, et autres
Publié: (2024)

A Hierarchical Language Model with Predictable Scaling Laws and Provable Benefits of Reasoning
par: Gaitonde, Jason, et autres
Publié: (2026)

Optimal Prediction Using Expert Advice and Randomized Littlestone Dimension
par: Filmus, Yuval, et autres
Publié: (2023)

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

Learning and Testing Convex Functions
par: Pinto Jr., Renato Ferreira, et autres
Publié: (2025)

On Learning Verifiers and Implications to Chain-of-Thought Reasoning
par: Balcan, Maria-Florina, et autres
Publié: (2025)

On Algorithmic Robustness of Corrupted Markov Chains
par: Gaitonde, Jason, et autres
Publié: (2025)

Non-Linear Paging
par: Doron-Arad, Ilan, et autres
Publié: (2024)

Fractured Chain-of-Thought Reasoning
par: Liao, Baohao, et autres
Publié: (2025)

The Kinetics of Reasoning: How Chain-of-Thought Shapes Learning in Transformers?
par: Pengmei, Zihan, et autres
Publié: (2025)

Regret-Oracle Complexity Tradeoffs in Agnostic Online Learning
par: Attias, Idan, et autres
Publié: (2026)

Reasoning by Superposition: A Theoretical Perspective on Chain of Continuous Thought
par: Zhu, Hanlin, et autres
Publié: (2025)

Eliciting Chain-of-Thought Reasoning for Time Series Analysis using Reinforcement Learning
par: Parker, Felix, et autres
Publié: (2025)

Continuous Chain of Thought Enables Parallel Exploration and Reasoning
par: Gozeten, Halil Alperen, et autres
Publié: (2025)

Reasoning Models Sometimes Output Illegible Chains of Thought
par: Jose, Arun
Publié: (2025)

RL's Razor: Why Online Reinforcement Learning Forgets Less
par: Shenfeld, Idan, et autres
Publié: (2025)

Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMs
par: Zhang, Xuan, et autres
Publié: (2024)

Demystifying Long Chain-of-Thought Reasoning in LLMs
par: Yeo, Edward, et autres
Publié: (2025)

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

Unveiling Confirmation Bias in Chain-of-Thought Reasoning
par: Wan, Yue, et autres
Publié: (2025)