Imagen de Portada

Position: A Theory of Deep Learning Must Include Compositional Sparsity

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Danhofer, David A., D'Ascenzo, Davide, Dubach, Rafael, Poggio, Tomaso
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Parameter Symmetry Potentially Unifies Deep Learning Theory
por: Ziyin, Liu, et al.
Publicado: (2025)

scDataset: Scalable Data Loading for Deep Learning on Large-Scale Single-Cell Omics
por: D'Ascenzo, Davide, et al.
Publicado: (2025)

pAI/MSc: ML Theory Research with Humans on the Loop
por: Abdelmoneum, Mahmoud, et al.
Publicado: (2026)

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

Hierarchical Reasoning Models: Perspectives and Misconceptions
por: Ge, Renee, et al.
Publicado: (2025)

Inducing Semi-Structured Sparsity by Masking for Efficient Model Inference in Convolutional Networks
por: Danhofer, David A.
Publicado: (2024)

The Generalized Turing Test: A Foundation for Comparing Intelligence
por: Mitropolsky, Daniel, et al.
Publicado: (2026)

On the Interplay Between Sparsity and Training in Deep Reinforcement Learning
por: Davelouis, Fatima, et al.
Publicado: (2025)

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

Spectral Geometry for Deep Learning: Compression and Hallucination Detection via Random Matrix Theory
por: Ettori, Davide
Publicado: (2026)

Training the Untrainable: Introducing Inductive Bias via Representational Alignment
por: Subramaniam, Vighnesh, et al.
Publicado: (2024)

Network Sparsity Unlocks the Scaling Potential of Deep Reinforcement Learning
por: Ma, Guozheng, et al.
Publicado: (2025)

Sparsity-Driven Plasticity in Multi-Task Reinforcement Learning
por: Todorov, Aleksandar, et al.
Publicado: (2025)

On the Sparsity of the Strong Lottery Ticket Hypothesis
por: Natale, Emanuele, et al.
Publicado: (2024)

The Cell Must Go On: Agar.io for Continual Reinforcement Learning
por: Mohamed, Mohamed A., et al.
Publicado: (2025)

Dynamic Sparsity: Challenging Common Sparsity Assumptions for Learning World Models in Robotic Reinforcement Learning Benchmarks
por: Pandaram, Muthukumar, et al.
Publicado: (2025)

Effective Interplay between Sparsity and Quantization: From Theory to Practice
por: Harma, Simla Burcu, et al.
Publicado: (2024)

Trustworthy AI Must Account for Interactions
por: Cresswell, Jesse C.
Publicado: (2025)

Learning Sparse Compositional Functions with Norm-Constrained Neural Networks
por: Huang, Shuo, et al.
Publicado: (2026)

Position: An Empirically Grounded Identifiability Theory Will Accelerate Self-Supervised Learning Research
por: Reizinger, Patrik, et al.
Publicado: (2025)

Simulating the Unseen: Crash Prediction Must Learn from What Did Not Happen
por: Li, Zihao, et al.
Publicado: (2025)

Knowledge Distillation Must Account for What It Loses
por: Wang, Wenshuo
Publicado: (2026)

Robot Learning with Sparsity and Scarcity
por: Xu, Jingxi
Publicado: (2025)

Efficient and Scalable Provenance Tracking for LLM-Generated Code Snippets
por: Gurioli, Andrea, et al.
Publicado: (2026)

Tool Building as a Path to "Superintelligence"
por: Koplow, David, et al.
Publicado: (2026)

A Sparsity Principle for Partially Observable Causal Representation Learning
por: Xu, Danru, et al.
Publicado: (2024)

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

When Labels Have Structure: Improving Image Classification with Hierarchy-Aware Cross-Entropy
por: Chan, April, et al.
Publicado: (2026)

Structure and Redundancy in Large Language Models: A Spectral Study via Random Matrix Theory
por: Ettori, Davide
Publicado: (2026)

Improving Decision Sparsity
por: Sun, Yiyang, et al.
Publicado: (2024)

Homeostasis and Sparsity in Transformer
por: Kotyuzanskiy, Leonid, et al.
Publicado: (2024)

Position: Categorical Deep Learning is an Algebraic Theory of All Architectures
por: Gavranović, Bruno, et al.
Publicado: (2024)

Polar Sparsity: High Throughput Batched LLM Inferencing with Scalable Contextual Sparsity
por: Shrestha, Susav, et al.
Publicado: (2025)

Sparsity-based Safety Conservatism for Constrained Offline Reinforcement Learning
por: Cho, Minjae, et al.
Publicado: (2024)

Reinforcement Learning With Sparse-Executing Actions via Sparsity Regularization
por: Pang, Jing-Cheng, et al.
Publicado: (2021)

Sparsity is All You Need: Rethinking Biological Pathway-Informed Approaches in Deep Learning
por: Caranzano, Isabella, et al.
Publicado: (2025)

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

Sparsity and Superposition in Mixture of Experts
por: Chaudhari, Marmik, et al.
Publicado: (2025)

Sparsity and Out-of-Distribution Generalization
por: Aaronson, Scott, et al.
Publicado: (2026)

Whatever Remains Must Be True: Filtering Drives Reasoning in LLMs, Shaping Diversity
por: Kruszewski, Germán, et al.
Publicado: (2025)