Image de couverture de livre

Learning High-Degree Parities: The Crucial Role of the Initialization

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Abbe, Emmanuel, Cornacchia, Elisabetta, Hązła, Jan, Kougang-Yombi, Donald
Format:	Preprint
Publié:	2024
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

A Quantitative Version of More Capable Channel Comparison
par: Kougang-Yombi, Donald, et autres
Publié: (2024)

Weight distribution bounds to relate minimum distance, list decoding, and symmetric channel performance
par: Kougang-Yombi, Donald, et autres
Publié: (2026)

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

Intransitive dice tournament is not quasirandom
par: Cornacchia, Elisabetta, et autres
Publié: (2020)

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

On the Minimal Degree Bias in Generalization on the Unseen for non-Boolean Functions
par: Pushkin, Denys, et autres
Publié: (2024)

Generalization on the Unseen, Logic Reasoning and Degree Curriculum
par: Abbe, Emmanuel, et autres
Publié: (2023)

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

On the Crucial Role of Initialization for Matrix Factorization
par: Li, Bingcong, et autres
Publié: (2024)

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

Transformation-Invariant Learning and Theoretical Guarantees for OOD Generalization
par: Montasser, Omar, et autres
Publié: (2024)

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

Goldilocks RL: Tuning Task Difficulty to Escape Sparse Rewards for Reasoning
par: Mahrooghi, Ilia, et autres
Publié: (2026)

$k$-server-bench: Automating Potential Discovery for the $k$-Server Conjecture
par: Brilliantov, Kirill, et autres
Publié: (2026)

The Crucial Role of Problem Formulation in Real-World Reinforcement Learning
par: Schäfer, Georg, et autres
Publié: (2025)

The merged-staircase property: a necessary and nearly sufficient condition for SGD learning of sparse functions on two-layer neural networks
par: Abbe, Emmanuel, et autres
Publié: (2022)

The Crucial Role of Samplers in Online Direct Preference Optimization
par: Shi, Ruizhe, et autres
Publié: (2024)

Inductive Domain Transfer In Misspecified Simulation-Based Inference
par: Senouf, Ortal, et autres
Publié: (2025)

How Far Can Transformers Reason? The Globality Barrier and Inductive Scratchpad
par: Abbe, Emmanuel, et autres
Publié: (2024)

Tokenizer Choice For LLM Training: Negligible or Crucial?
par: Ali, Mehdi, et autres
Publié: (2023)

Learning High-Dimensional Parity Functions with Product Networks using Gradient Descent
par: Larue, Guillaume, et autres
Publié: (2026)

Chain-of-Sketch: Enabling Global Visual Reasoning
par: Lotfi, Aryo, et autres
Publié: (2024)

Hardness of Learning Fixed Parities with Neural Networks
par: Shoshani, Itamar, et autres
Publié: (2025)

Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt Templates
par: Lyu, Kaifeng, et autres
Publié: (2024)

Loss Gap Parity for Fairness in Heterogeneous Federated Learning
par: Erraji, Brahim, et autres
Publié: (2026)

To Infinity and Beyond: Tool-Use Unlocks Length Generalization in State Space Models
par: Malach, Eran, et autres
Publié: (2025)

Boolformer: Symbolic Regression of Logic Functions with Transformers
par: d'Ascoli, Stéphane, et autres
Publié: (2023)

Learning Optimal Individualized Decision Rules with Conditional Demographic Parity
par: Cui, Wenhai, et autres
Publié: (2026)

Differential Adjusted Parity for Learning Fair Representations
par: Sahyouni, Bucher, et autres
Publié: (2025)

Computationally Efficient Replicable Learning of Parities and Applications
par: Noivirt, Moshe, et autres
Publié: (2026)

When can transformers reason with abstract symbols?
par: Boix-Adsera, Enric, et autres
Publié: (2023)

Demographic Parity Tails for Regression
par: Le, Naht Sinh, et autres
Publié: (2026)

Approximating the Number of Relevant Variables in a Parity Implies Proper Learning
par: Bshouty, Nader H., et autres
Publié: (2024)

RL for Reasoning by Adaptively Revealing Rationales
par: Amani, Mohammad Hossein, et autres
Publié: (2025)

SDGym: Low-Code Reinforcement Learning Environments using System Dynamics Models
par: Klu, Emmanuel, et autres
Publié: (2023)

Collaboration Between the City and Machine Learning Community is Crucial to Efficient Autonomous Vehicles Routing
par: Psarou, Anastasia, et autres
Publié: (2025)

Parity, Sensitivity, and Transformers
par: Kozachinskiy, Alexander, et autres
Publié: (2026)

Autocorrelation Matters: Understanding the Role of Initialization Schemes for State Space Models
par: Liu, Fusheng, et autres
Publié: (2024)

A Bioinformatic Approach Validated Utilizing Machine Learning Algorithms to Identify Relevant Biomarkers and Crucial Pathways in Gallbladder Cancer
par: Khatun, Rabea, et autres
Publié: (2024)

Unravelling the (In)compatibility of Statistical-Parity and Equalized-Odds
par: Bargh, Mortaza S., et autres
Publié: (2026)