Copertina

How DNNs break the Curse of Dimensionality: Compositionality and Symmetry Learning

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Jacot, Arthur, Choi, Seok Hoan, Wen, Yuxiao
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Machine Learning Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Which Frequencies do CNNs Need? Emergent Bottleneck Structure in Feature Learning
di: Wen, Yuxiao, et al.
Pubblicazione: (2024)

Bottleneck Structure in Learned Features: Low-Dimension vs Regularity Tradeoff
di: Jacot, Arthur
Pubblicazione: (2023)

Hamiltonian Mechanics of Feature Learning: Bottleneck Structure in Leaky ResNets
di: Jacot, Arthur, et al.
Pubblicazione: (2024)

The Blessing and Curse of Dimensionality in Safety Alignment
di: Teo, Rachel S. Y., et al.
Pubblicazione: (2025)

Mixed Dynamics In Linear Networks: Unifying the Lazy and Active Regimes
di: Tu, Zhenfeng, et al.
Pubblicazione: (2024)

Saddle-To-Saddle Dynamics in Deep ReLU Networks: Low-Rank Bias in the First Saddle Escape
di: Bantzis, Ioannis, et al.
Pubblicazione: (2025)

Mixture of Experts Softens the Curse of Dimensionality in Operator Learning
di: Kratsios, Anastasis, et al.
Pubblicazione: (2024)

CNNs Avoid Curse of Dimensionality by Learning on Patches
di: Madala, Vamshi C., et al.
Pubblicazione: (2022)

Symmetry breaking for inductive logic programming
di: Cropper, Andrew, et al.
Pubblicazione: (2025)

An Analysis and Mitigation of the Reversal Curse
di: Lv, Ang, et al.
Pubblicazione: (2023)

Carbon Intensity-Aware Adaptive Inference of DNNs
di: Jung, Jiwan
Pubblicazione: (2024)

CEAR: Certified Ensemble Adversarial Robustness in DNNs
di: Sadig, Daniel, et al.
Pubblicazione: (2026)

The Curse of Depth in Large Language Models
di: Sun, Wenfang, et al.
Pubblicazione: (2025)

Dispelling the Curse of Singularities in Neural Network Optimizations
di: Cao, Hengjie, et al.
Pubblicazione: (2026)

The Factorization Curse: Which Tokens You Predict Underlie the Reversal Curse and More
di: Kitouni, Ouail, et al.
Pubblicazione: (2024)

Rapid Deployment of DNNs for Edge Computing via Structured Pruning at Initialization
di: Eccles, Bailey J., et al.
Pubblicazione: (2024)

CFASL: Composite Factor-Aligned Symmetry Learning for Disentanglement in Variational AutoEncoder
di: Jung, Hee-Jun, et al.
Pubblicazione: (2024)

Return-to-Go Is More Than a Number: Q-Guided Alignment for Return-Conditioned Supervised Learning
di: Yang, Yuxiao, et al.
Pubblicazione: (2026)

ECQ$^{\text{x}}$: Explainability-Driven Quantization for Low-Bit and Sparse DNNs
di: Becking, Daniel, et al.
Pubblicazione: (2021)

Know What You Don't Know: Selective Prediction for Early Exit DNNs
di: Bajpai, Divya Jyoti, et al.
Pubblicazione: (2025)

Efficient Triple Modular Redundancy for Reliability Enhancement of DNNs Using Explainable AI
di: Soroush, Kimia, et al.
Pubblicazione: (2025)

Relationship between Uncertainty in DNNs and Adversarial Attacks
di: Ogonna, Mabel, et al.
Pubblicazione: (2024)

Random weights of DNNs and emergence of fixed points
di: Berlyand, L., et al.
Pubblicazione: (2025)

The Curse and Blessing of Mean Bias in FP4-Quantized LLM Training
di: Cao, Hengjie, et al.
Pubblicazione: (2026)

HAWX: A Hardware-Aware FrameWork for Fast and Scalable ApproXimation of DNNs
di: Nazari, Samira, et al.
Pubblicazione: (2026)

On the Curses of Future and History in Future-dependent Value Functions for Off-policy Evaluation
di: Zhang, Yuheng, et al.
Pubblicazione: (2024)

Handling Long and Richly Constrained Tasks through Constrained Hierarchical Reinforcement Learning
di: Lu, Yuxiao, et al.
Pubblicazione: (2023)

Deep Learning as a Convex Paradigm of Computation: Minimizing Circuit Size with ResNets
di: Jacot, Arthur
Pubblicazione: (2025)

Base Models Know How to Reason, Thinking Models Learn When
di: Venhoff, Constantin, et al.
Pubblicazione: (2025)

Towards Reliable LLM Evaluation: Correcting the Winner's Curse in Adaptive Benchmarking
di: Xu, Yang, et al.
Pubblicazione: (2026)

Breaking the Curse of Repulsion: Optimistic Distributionally Robust Policy Optimization for Off-Policy Generative Recommendation
di: Jiang, Jie, et al.
Pubblicazione: (2026)

Symmetry Reveals Layerwise Dynamics: How Transformers Perform In-Context Classification
di: Lutz, Patrick, et al.
Pubblicazione: (2026)

Recursive Introspection: Teaching Language Model Agents How to Self-Improve
di: Qu, Yuxiao, et al.
Pubblicazione: (2024)

Quantum Circuit Structure Optimization for Quantum Reinforcement Learning
di: Son, Seok Bin, et al.
Pubblicazione: (2025)

Sparsely-Supervised Data Assimilation via Physics-Informed Schrödinger Bridge
di: Bu, Dohyun, et al.
Pubblicazione: (2026)

DART: Input-Difficulty-AwaRe Adaptive Threshold for Early-Exit DNNs
di: Patne, Parth, et al.
Pubblicazione: (2026)

Learning Efficiency Meets Symmetry Breaking
di: Bai, Yingbin, et al.
Pubblicazione: (2025)

Balanced Online Class-Incremental Learning via Dual Classifiers
di: Wen, Shunjie, et al.
Pubblicazione: (2025)

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond
di: Ke, Yekun, et al.
Pubblicazione: (2024)

DUEL: Duplicate Elimination on Active Memory for Self-Supervised Class-Imbalanced Learning
di: Choi, Won-Seok, et al.
Pubblicazione: (2024)