Copertina

More is Better in Modern Machine Learning: when Infinite Overparameterization is Optimal and Overfitting is Obligatory

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Simon, James B., Karkada, Dhruva, Ghosh, Nikhil, Belkin, Mikhail
Natura:	Preprint
Pubblicazione:	2023
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

The lazy (NTK) and rich ($μ$P) regimes: a gentle tutorial
di: Karkada, Dhruva
Pubblicazione: (2024)

Predicting kernel regression learning curves from only raw data statistics
di: Karkada, Dhruva, et al.
Pubblicazione: (2025)

Closed-Form Training Dynamics Reveal Learned Features and Linear Structure in Word2Vec-like Models
di: Karkada, Dhruva, et al.
Pubblicazione: (2025)

Benign, Tempered, or Catastrophic: A Taxonomy of Overfitting
di: Mallinar, Neil, et al.
Pubblicazione: (2022)

Alternating Gradient Flows: A Theory of Feature Learning in Two-layer Neural Networks
di: Kunin, Daniel, et al.
Pubblicazione: (2025)

On the Emergence of Linear Analogies in Word Embeddings
di: Korchinski, Daniel J., et al.
Pubblicazione: (2025)

A Gap Between the Gaussian RKHS and Neural Networks: An Infinite-Center Asymptotic Analysis
di: Kumar, Akash, et al.
Pubblicazione: (2025)

There Will Be a Scientific Theory of Deep Learning
di: Simon, Jamie, et al.
Pubblicazione: (2026)

Linear Recursive Feature Machines provably recover low-rank matrices
di: Radhakrishnan, Adityanarayanan, et al.
Pubblicazione: (2024)

Symmetry in language statistics shapes the geometry of model representations
di: Karkada, Dhruva, et al.
Pubblicazione: (2026)

Machine Unlearning under Overparameterization
di: Block, Jacob L., et al.
Pubblicazione: (2025)

More is Less: Inducing Sparsity via Overparameterization
di: Chou, Hung-Hsu, et al.
Pubblicazione: (2021)

An Agnostic View on the Cost of Overfitting in (Kernel) Ridge Regression
di: Zhou, Lijia, et al.
Pubblicazione: (2023)

On the Nystrom Approximation for Preconditioning in Kernel Machines
di: Abedsoltan, Amirhesam, et al.
Pubblicazione: (2023)

Testing for Overfitting
di: Schmidt, James
Pubblicazione: (2023)

The Features at Convergence Theorem: a first-principles alternative to the Neural Feature Ansatz for how networks learn representations
di: Boix-Adsera, Enric, et al.
Pubblicazione: (2025)

Revisiting Optimism and Model Complexity in the Wake of Overparameterized Machine Learning
di: Patil, Pratik, et al.
Pubblicazione: (2024)

Negotiated Representations to Prevent Overfitting in Machine Learning Applications
di: Korhan, Nuri, et al.
Pubblicazione: (2023)

Understanding Inverse Reinforcement Learning under Overparameterization: Non-Asymptotic Analysis and Global Optimality
di: Zhang, Ruijia, et al.
Pubblicazione: (2025)

Overfitting In Contrastive Learning?
di: Rabin, Zachary, et al.
Pubblicazione: (2024)

Transfer Learning of Linear Regression with Multiple Pretrained Models: Benefiting from More Pretrained Models via Overparameterization Debiasing
di: Boharon, Daniel, et al.
Pubblicazione: (2026)

How Does Overparameterization Affect Machine Unlearning of Deep Neural Networks?
di: Alon, Gal, et al.
Pubblicazione: (2025)

Context-Scaling versus Task-Scaling in In-Context Learning
di: Abedsoltan, Amirhesam, et al.
Pubblicazione: (2024)

Breaking Data Symmetry is Needed For Generalization in Feature Learning Kernels
di: Bernal, Marcel Tomàs, et al.
Pubblicazione: (2026)

An Analytical Model for Overparameterized Learning Under Class Imbalance
di: Mor, Eliav, et al.
Pubblicazione: (2025)

Near Optimal Best Arm Identification for Clustered Bandits
di: Yash, et al.
Pubblicazione: (2025)

Mildly Overparameterized ReLU Networks on Orthogonal Data: Incremental Learning and Implicit Bias
di: Town, James, et al.
Pubblicazione: (2026)

Catching rationalization in the act: detecting motivated reasoning before and after CoT via activation probing
di: Mirtaheri, Parsa, et al.
Pubblicazione: (2026)

Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective
di: Laakom, Firas, et al.
Pubblicazione: (2025)

Better, Not Just More: Data-Centric Machine Learning for Earth Observation
di: Roscher, Ribana, et al.
Pubblicazione: (2023)

The Interpolating Information Criterion for Overparameterized Models
di: Hodgkinson, Liam, et al.
Pubblicazione: (2023)

Theoretical Limitations of Ensembles in the Age of Overparameterization
di: Dern, Niclas, et al.
Pubblicazione: (2024)

How Does Overparameterization Affect Features?
di: Duzgun, Ahmet Cagri, et al.
Pubblicazione: (2024)

Adaptive Benign Overfitting (ABO): Overparameterized RLS for Online Learning in Non-stationary Time-series
di: Mijares, Luis Ontaneda, et al.
Pubblicazione: (2026)

Privacy for Free in the Overparameterized Regime
di: Bombari, Simone, et al.
Pubblicazione: (2024)

Mirror Descent on Reproducing Kernel Banach Spaces
di: Kumar, Akash, et al.
Pubblicazione: (2024)

General and Efficient Steering of Unconditional Diffusion
di: Wang, Qingsong, et al.
Pubblicazione: (2026)

Preconditioned Gradient Descent for Overparameterized Nonconvex Burer--Monteiro Factorization with Global Optimality Certification
di: Zhang, Gavin, et al.
Pubblicazione: (2022)

Learning Causality for Modern Machine Learning
di: Chen, Yongqiang
Pubblicazione: (2025)

Efficient Compression of Overparameterized Deep Models through Low-Dimensional Learning Dynamics
di: Kwon, Soo Min, et al.
Pubblicazione: (2023)