Copertina

Unraveling the Enigma of Double Descent: An In-depth Analysis through the Lens of Learned Feature Space

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Gu, Yufei, Zheng, Xiaoqing, Aste, Tomaso
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

Information Filtering Networks: Theoretical Foundations, Generative Methodologies, and Real-World Applications
di: Aste, Tomaso
Pubblicazione: (2025)

Class-wise Activation Unravelling the Engima of Deep Double Descent
di: Gu, Yufei
Pubblicazione: (2024)

Deep Limit Order Book Forecasting
di: Briola, Antonio, et al.
Pubblicazione: (2024)

HLOB -- Information Persistence and Structure in Limit Order Books
di: Briola, Antonio, et al.
Pubblicazione: (2024)

Compositional Sparsity as an Inductive Bias for Neural Architecture Design
di: Lin, Hongyu, et al.
Pubblicazione: (2026)

Granger Causality Detection with Kolmogorov-Arnold Networks
di: Lin, Hongyu, et al.
Pubblicazione: (2024)

On Double Descent in Reinforcement Learning with LSTD and Random Features
di: Brellmann, David, et al.
Pubblicazione: (2023)

Double Descent as a Lens for Sample Efficiency in Autoregressive vs. Discrete Diffusion Models
di: Fraij, Ahmad, et al.
Pubblicazione: (2025)

Graph Regularized PCA
di: Briola, Antonio, et al.
Pubblicazione: (2026)

Unified View of Grokking, Double Descent and Emergent Abilities: A Perspective from Circuits Competition
di: Huang, Yufei, et al.
Pubblicazione: (2024)

Automated Feature Labeling with Token-Space Gradient Descent
di: Schulz, Julian, et al.
Pubblicazione: (2025)

Unraveling Syntax: How Language Models Learn Context-Free Grammars
di: Schulz, Laura Ying, et al.
Pubblicazione: (2025)

Bayesian Double Descent
di: Polson, Nick, et al.
Pubblicazione: (2025)

Manipulating Sparse Double Descent
di: Zhang, Ya Shi
Pubblicazione: (2024)

On The Presence of Double-Descent in Deep Reinforcement Learning
di: Veselý, Viktor, et al.
Pubblicazione: (2025)

Unraveling the Gradient Descent Dynamics of Transformers
di: Song, Bingqing, et al.
Pubblicazione: (2024)

Robust Predictive Uncertainty and Double Descent in Contaminated Bayesian Random Features
di: Caprio, Michele, et al.
Pubblicazione: (2026)

On efficiently computable functions, deep networks and sparse compositionality
di: Poggio, Tomaso
Pubblicazione: (2025)

Neural Feature Learning in Function Space
di: Xu, Xiangxiang, et al.
Pubblicazione: (2023)

Dropout Drops Double Descent
di: Yang, Tian-Le, et al.
Pubblicazione: (2023)

Understanding the Double Descent Phenomenon in Deep Learning
di: Lafon, Marc, et al.
Pubblicazione: (2024)

Hypernym Bias: Unraveling Deep Classifier Training Dynamics through the Lens of Class Hierarchy
di: Malashin, Roman, et al.
Pubblicazione: (2025)

On the Lipschitz Constant of Deep Networks and Double Descent
di: Gamba, Matteo, et al.
Pubblicazione: (2023)

Double Descent and Other Interpolation Phenomena in GANs
di: Luzi, Lorenzo, et al.
Pubblicazione: (2021)

BloomGML: Graph Machine Learning through the Lens of Bilevel Optimization
di: Zheng, Amber Yijia, et al.
Pubblicazione: (2024)

Space of Data through the Lens of Multilevel Graph
di: Caputo, Marco, et al.
Pubblicazione: (2025)

GNNX-BENCH: Unravelling the Utility of Perturbation-based GNN Explainers through In-depth Benchmarking
di: Kosan, Mert, et al.
Pubblicazione: (2023)

How Does Gradient Descent Learn Features -- A Local Analysis for Regularized Two-Layer Neural Networks
di: Zhou, Mo, et al.
Pubblicazione: (2024)

Understanding and Mitigating Bottlenecks of State Space Models through the Lens of Recency and Over-smoothing
di: Wang, Peihao, et al.
Pubblicazione: (2024)

Asymptotic Behavior of Multi--Task Learning: Implicit Regularization and Double Descent Effects
di: Alrashdi, Ayed M., et al.
Pubblicazione: (2026)

Two Speeds of Learning: A Representation-Readout Decomposition of Grokking and Double Descent
di: Chou, Chi-Ning, et al.
Pubblicazione: (2026)

Generalization Error Analysis for Selective State-Space Models Through the Lens of Attention
di: Honarpisheh, Arya, et al.
Pubblicazione: (2025)

Unraveling the Single Tangent Space Fallacy: An Analysis and Clarification for Applying Riemannian Geometry in Robot Learning
di: Jaquier, Noémie, et al.
Pubblicazione: (2023)

Unraveling Spatio-Temporal Foundation Models via the Pipeline Lens: A Comprehensive Review
di: Fang, Yuchen, et al.
Pubblicazione: (2025)

Topological Invariance and Breakdown in Learning
di: Yang, Yongyi, et al.
Pubblicazione: (2025)

Calibration through the Lens of Interpretability
di: Torabian, Alireza, et al.
Pubblicazione: (2024)

Best-of-N through the Smoothing Lens: KL Divergence and Regret Analysis
di: Aminian, Gholamali, et al.
Pubblicazione: (2025)

The Double Descent Behavior in Two Layer Neural Network for Binary Classification
di: Abeykoon, Chathurika S, et al.
Pubblicazione: (2025)

Ubiquity of Emergent Hebbian Dynamics in Regularized Learning
di: Koplow, David, et al.
Pubblicazione: (2025)

Limited Memory Online Gradient Descent for Kernelized Pairwise Learning with Dynamic Averaging
di: AlQuabeh, Hilal, et al.
Pubblicazione: (2024)