Image de couverture de livre

The Benefits of Temporal Correlations: SGD Learns k-Juntas from Random Walks Efficiently

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Cornacchia, Elisabetta, Mikulincer, Dan, 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

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

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

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

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

Sample-Efficient Linear Regression with Self-Selection Bias
par: Gaitonde, Jason, 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)

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

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

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

A Theory of Online Learning with Autoregressive Chain-of-Thought Reasoning
par: Doron-Arad, Ilan, et autres
Publié: (2026)

Learning with Shallow Neural Networks on Cluster-Structured Features
par: Cornacchia, Elisabetta, et autres
Publié: (2026)

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

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

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

Monotonicity, Topology, and Convexity of Recurrence in Random Walks
par: Li, Rupert, et autres
Publié: (2024)

Is this correct? Let's check!
par: Ben-Eliezer, Omri, et autres
Publié: (2022)

Random Subwords and Billiard Walks in Affine Weyl Groups
par: Defant, Colin, et autres
Publié: (2025)

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

Size and depth of monotone neural networks: interpolation and approximation
par: Mikulincer, Dan, et autres
Publié: (2022)

Learning High-Degree Parities: The Crucial Role of the Initialization
par: Abbe, Emmanuel, et autres
Publié: (2024)

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

Comparison Theorems for the Mixing Times of Systematic and Random Scan Dynamics
par: Gaitonde, Jason, et autres
Publié: (2024)

Positive Distribution Shift as a Framework for Understanding Tractable Learning
par: Medvedev, Marko, et autres
Publié: (2026)

Learning Juntas under Markov Random Fields
par: Chandrasekaran, Gautam, et autres
Publié: (2025)

RQP-SGD: Differential Private Machine Learning through Noisy SGD and Randomized Quantization
par: Feng, Ce, et autres
Publié: (2024)

On the Statistical Benefits of Temporal Difference Learning
par: Cheikhi, David, et autres
Publié: (2023)

MindFlayer SGD: Efficient Parallel SGD in the Presence of Heterogeneous and Random Worker Compute Times
par: Maranjyan, Artavazd, et autres
Publié: (2024)

Towards Understanding Transformers in Learning Random Walks
par: Shi, Wei, et autres
Publié: (2025)

Biased Local SGD for Efficient Deep Learning on Heterogeneous Systems
par: Lim, Jihyun, et autres
Publié: (2025)

Repelling Random Walks
par: Reid, Isaac, et autres
Publié: (2023)

Revisiting Random Walks for Learning on Graphs
par: Kim, Jinwoo, et autres
Publié: (2024)

Reconstructing Riemannian Metrics From Random Geometric Graphs
par: Huang, Han, et autres
Publié: (2025)

Trustworthy Efficient Communication for Distributed Learning using LQ-SGD Algorithm
par: Li, Hongyang, et autres
Publié: (2025)

Balancing Utility and Privacy: Dynamically Private SGD with Random Projection
par: Jiang, Zhanhong, et autres
Publié: (2025)

Correlating Cross-Iteration Noise for DP-SGD using Model Curvature
par: Gu, Xin, et autres
Publié: (2025)

Communication-Efficient Federated Learning by Exploiting Spatio-Temporal Correlations of Gradients
par: Zheng, Shenlong, et autres
Publié: (2026)

Differentially Private Decentralized Learning with Random Walks
par: Cyffers, Edwige, et autres
Publié: (2024)

Learning Long Range Dependencies on Graphs via Random Walks
par: Chen, Dexiong, et autres
Publié: (2024)

Convolutional Persistence Transforms
par: Solomon, Elchanan, et autres
Publié: (2022)