Copertina

Branch Scaling Manifests as Implicit Architectural Regularization for Improving Generalization in Overparameterized ResNets

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Yu, Zixiong, Chen, Guhan, Lai, Jianfa, Li, Bohan, Tian, Songtao
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Machine Learning Statistics Theory
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Approximating Langevin Monte Carlo with ResNet-like Neural Network architectures
di: Miranda, Charles, et al.
Pubblicazione: (2023)

Divergence of Empirical Neural Tangent Kernel in Classification Problems
di: Yu, Zixiong, et al.
Pubblicazione: (2025)

Progressive Feedforward Collapse of ResNet Training
di: Wang, Sicong, et al.
Pubblicazione: (2024)

Overparameterization of deep ResNet: zero loss and mean-field analysis
di: Ding, Zhiyan, et al.
Pubblicazione: (2021)

Towards a Statistical Understanding of Neural Networks: Beyond the Neural Tangent Kernel Theories
di: Zhang, Haobo, et al.
Pubblicazione: (2024)

Extending Mean-Field Variational Inference via Entropic Regularization: Theory and Computation
di: Wu, Bohan, et al.
Pubblicazione: (2024)

Implicit Regularization Paths of Weighted Neural Representations
di: Du, Jin-Hong, et al.
Pubblicazione: (2024)

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

Batches Stabilize the Minimum Norm Risk in High Dimensional Overparameterized Linear Regression
di: Ioushua, Shahar Stein, et al.
Pubblicazione: (2023)

Generalization of Scaled Deep ResNets in the Mean-Field Regime
di: Chen, Yihang, et al.
Pubblicazione: (2024)

Collective Kernel EFT for Pre-activation ResNets
di: Kawase, Hidetoshi, et al.
Pubblicazione: (2026)

Implicit Regularization for Tubal Tensor Factorizations via Gradient Descent
di: Karnik, Santhosh, et al.
Pubblicazione: (2024)

Scaling ResNets in the Large-depth Regime
di: Marion, Pierre, et al.
Pubblicazione: (2022)

ResCP: Reservoir Conformal Prediction for Time Series Forecasting
di: Neglia, Roberto, et al.
Pubblicazione: (2025)

Frequentist Guarantees of Distributed (Non)-Bayesian Inference
di: Wu, Bohan, et al.
Pubblicazione: (2023)

Improved Scaling Laws in Linear Regression via Data Reuse
di: Lin, Licong, et al.
Pubblicazione: (2025)

On the Eigenvalue Decay Rates of a Class of Neural-Network Related Kernel Functions Defined on General Domains
di: Li, Yicheng, et al.
Pubblicazione: (2023)

A Unified Pair-GRPO Family: From Implicit to Explicit Preference Constraints for Stable and General RL Alignment
di: Yu, Hao
Pubblicazione: (2026)

Self-Regularized Learning Methods
di: Schölpple, Max, et al.
Pubblicazione: (2026)

Implicit Regularisation in Diffusion Models: An Algorithm-Dependent Generalisation Analysis
di: Farghly, Tyler, et al.
Pubblicazione: (2025)

Iterative Reweighted Framework Based Algorithms for Sparse Linear Regression with Generalized Elastic Net Penalty
di: Ding, Yanyun, et al.
Pubblicazione: (2024)

Higher-Order Regularization Learning on Hypergraphs
di: Weihs, Adrien, et al.
Pubblicazione: (2025)

Training Implicit Generative Models via an Invariant Statistical Loss
di: de Frutos, José Manuel, et al.
Pubblicazione: (2024)

Neural Collapse is Globally Optimal in Deep Regularized ResNets and Transformers
di: Súkeník, Peter, et al.
Pubblicazione: (2025)

Path Regularization: A Near-Complete and Optimal Nonasymptotic Generalization Theory for Multilayer Neural Networks and Double Descent Phenomenon
di: Yu, Hao
Pubblicazione: (2025)

Failure of uniform laws of large numbers for subdifferentials and beyond
di: Tian, Lai, et al.
Pubblicazione: (2025)

Generalized Power Priors for Improved Bayesian Inference with Historical Data
di: Kimura, Masanari, et al.
Pubblicazione: (2025)

Implicit Regularization and Generalization in Overparameterized Neural Networks
di: Johannsen, Zeran
Pubblicazione: (2026)

Bagged Regularized $k$-Distances for Anomaly Detection
di: Cai, Yuchao, et al.
Pubblicazione: (2023)

Optimal Ridge Regularization for Out-of-Distribution Prediction
di: Patil, Pratik, et al.
Pubblicazione: (2024)

Precise Asymptotics of Bagging Regularized M-estimators
di: Koriyama, Takuya, et al.
Pubblicazione: (2024)

Neural Networks Learn Generic Multi-Index Models Near Information-Theoretic Limit
di: Zhang, Bohan, et al.
Pubblicazione: (2025)

Arithmetic-Mean $μ$P for Modern Architectures: A Unified Learning-Rate Scale for CNNs and ResNets
di: Zhang, Haosong, et al.
Pubblicazione: (2025)

Monte Carlo inference for semiparametric Bayesian regression
di: Kowal, Daniel R., et al.
Pubblicazione: (2023)

Regularization can make diffusion models more efficient
di: Taheri, Mahsa, et al.
Pubblicazione: (2025)

Generalization of LiNGAM that allows confounding
di: Suzuki, Joe, et al.
Pubblicazione: (2024)

Spectrally-Corrected and Regularized QDA Classifier for Spiked Covariance Model
di: Luo, Wenya, et al.
Pubblicazione: (2025)

Finite-Particle Rates for Regularized Stein Variational Gradient Descent
di: He, Ye, et al.
Pubblicazione: (2026)

Importance Weighting Correction of Regularized Least-Squares for Target Shift
di: Gogolashvili, Davit
Pubblicazione: (2022)

Dropout Regularization Versus $\ell_2$-Penalization in the Linear Model
di: Clara, Gabriel, et al.
Pubblicazione: (2023)