Image de couverture de livre

Class-wise Activation Unravelling the Engima of Deep Double Descent

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteur principal:	Gu, Yufei
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

Unraveling the Enigma of Double Descent: An In-depth Analysis through the Lens of Learned Feature Space
par: Gu, Yufei, et autres
Publié: (2023)

Deep Exploration of Epoch-wise Double Descent in Noisy Data: Signal Separation, Large Activation, and Benign Overfitting
par: Kubo, Tomoki, et autres
Publié: (2026)

On the Lipschitz Constant of Deep Networks and Double Descent
par: Gamba, Matteo, et autres
Publié: (2023)

On The Presence of Double-Descent in Deep Reinforcement Learning
par: Veselý, Viktor, et autres
Publié: (2025)

Unified View of Grokking, Double Descent and Emergent Abilities: A Perspective from Circuits Competition
par: Huang, Yufei, et autres
Publié: (2024)

Understanding the Double Descent Phenomenon in Deep Learning
par: Lafon, Marc, et autres
Publié: (2024)

Bayesian Double Descent
par: Polson, Nick, et autres
Publié: (2025)

Manipulating Sparse Double Descent
par: Zhang, Ya Shi
Publié: (2024)

Unraveling the Gradient Descent Dynamics of Transformers
par: Song, Bingqing, et autres
Publié: (2024)

Transformers Trained via Gradient Descent Can Provably Learn a Class of Teacher Models
par: Zhang, Chenyang, et autres
Publié: (2026)

Dropout Drops Double Descent
par: Yang, Tian-Le, et autres
Publié: (2023)

Double Descent and Other Interpolation Phenomena in GANs
par: Luzi, Lorenzo, et autres
Publié: (2021)

Class-wise Generalization Error: an Information-Theoretic Analysis
par: Laakom, Firas, et autres
Publié: (2024)

Reducing Class-wise Confusion for Incremental Learning with Disentangled Manifolds
par: Chen, Huitong, et autres
Publié: (2025)

Towards Class-wise Robustness Analysis
par: Medi, Tejaswini, et autres
Publié: (2024)

Linear-time One-Class Classification with Repeated Element-wise Folding
par: Raitoharju, Jenni
Publié: (2024)

Hypernym Bias: Unraveling Deep Classifier Training Dynamics through the Lens of Class Hierarchy
par: Malashin, Roman, et autres
Publié: (2025)

The Double Descent Behavior in Two Layer Neural Network for Binary Classification
par: Abeykoon, Chathurika S, et autres
Publié: (2025)

Class-wise Balancing Data Replay for Federated Class-Incremental Learning
par: Qi, Zhuang, et autres
Publié: (2025)

On Double Descent in Reinforcement Learning with LSTD and Random Features
par: Brellmann, David, et autres
Publié: (2023)

Harmonized Gradient Descent for Class Imbalanced Data Stream Online Learning
par: Zhou, Han, et autres
Publié: (2025)

Conformal Prediction for Class-wise Coverage via Augmented Label Rank Calibration
par: Shi, Yuanjie, et autres
Publié: (2024)

Towards Understanding Epoch-wise Double descent in Two-layer Linear Neural Networks
par: Olmin, Amanda, et autres
Publié: (2024)

AWP: Activation-Aware Weight Pruning and Quantization with Projected Gradient Descent
par: Liu, Jing, et autres
Publié: (2025)

Towards Fair Class-wise Robustness: Class Optimal Distribution Adversarial Training
par: Zhi, Hongxin, et autres
Publié: (2025)

Efficient Search for Customized Activation Functions with Gradient Descent
par: Strack, Lukas, et autres
Publié: (2024)

Class-wise Federated Unlearning: Harnessing Active Forgetting with Teacher-Student Memory Generation
par: Li, Yuyuan, et autres
Publié: (2023)

A Characterization Theorem for Equivariant Networks with Point-wise Activations
par: Pacini, Marco, et autres
Publié: (2024)

Double Descent as a Lens for Sample Efficiency in Autoregressive vs. Discrete Diffusion Models
par: Fraij, Ahmad, et autres
Publié: (2025)

OUIDecay: Adaptive Layer-wise Weight Decay for CNNs Using Online Activation Patterns
par: Fernández-Hernández, Alberto, et autres
Publié: (2026)

Variational Stochastic Gradient Descent for Deep Neural Networks
par: Chen, Haotian, et autres
Publié: (2024)

Analog Physical Systems Can Exhibit Double Descent
par: Dillavou, Sam, et autres
Publié: (2025)

Activation-Descent Regularization for Input Optimization of ReLU Networks
par: Yu, Hongzhan, et autres
Publié: (2024)

Least Squares Regression Can Exhibit Under-Parameterized Double Descent
par: Li, Xinyue, et autres
Publié: (2023)

Activation Compression of Graph Neural Networks using Block-wise Quantization with Improved Variance Minimization
par: Eliassen, Sebastian, et autres
Publié: (2023)

Asymptotic Behavior of Multi--Task Learning: Implicit Regularization and Double Descent Effects
par: Alrashdi, Ayed M., et autres
Publié: (2026)

Double Descent and Overfitting under Noisy Inputs and Distribution Shift for Linear Denoisers
par: Kausik, Chinmaya, et autres
Publié: (2023)

Two Speeds of Learning: A Representation-Readout Decomposition of Grokking and Double Descent
par: Chou, Chi-Ning, et autres
Publié: (2026)

Changing the Kernel During Training Leads to Double Descent in Kernel Regression
par: Allerbo, Oskar
Publié: (2023)

Robust Predictive Uncertainty and Double Descent in Contaminated Bayesian Random Features
par: Caprio, Michele, et autres
Publié: (2026)