Copertina

A Combinatorial Theory of Dropout: Subnetworks, Graph Geometry, and Generalization

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autore principale:	Dhayalkar, Sahil Rajesh
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

The Geometry of ReLU Networks through the ReLU Transition Graph
di: Dhayalkar, Sahil Rajesh
Pubblicazione: (2025)

Attention as Binding: A Vector-Symbolic Perspective on Transformer Reasoning
di: Dhayalkar, Sahil Rajesh
Pubblicazione: (2025)

Reasoning Stabilization Point: A Training-Time Signal for Stable Evidence and Shortcut Reliance
di: Dhayalkar, Sahil Rajesh
Pubblicazione: (2026)

Neural Networks as Universal Finite-State Machines: A Constructive Deterministic Finite Automaton Theory
di: Dhayalkar, Sahil Rajesh
Pubblicazione: (2025)

Dynamic Context Adaptation and Information Flow Control in Transformers: Introducing the Evaluator Adjuster Unit and Gated Residual Connections
di: Dhayalkar, Sahil Rajesh
Pubblicazione: (2024)

Discrete Functional Geometry of ReLU Networks via ReLU Transition Graphs
di: Dhayalkar, Sahil Rajesh
Pubblicazione: (2025)

Symbolic Feedforward Networks for Probabilistic Finite Automata: Exact Simulation and Learnability
di: Dhayalkar, Sahil Rajesh
Pubblicazione: (2025)

Logic-Gated Time-Shared Feedforward Networks for Alternating Finite Automata: Exact Simulation and Learnability
di: Dhayalkar, Sahil Rajesh
Pubblicazione: (2026)

A Constructive Framework for Nondeterministic Automata via Time-Shared, Depth-Unrolled Feedforward Networks
di: Dhayalkar, Sahil Rajesh
Pubblicazione: (2025)

Human Activity Recognition using Smartphones
di: Sonawane, Mayur, et al.
Pubblicazione: (2024)

Instilling Inductive Biases with Subnetworks
di: Zhang, Enyan, et al.
Pubblicazione: (2023)

Geometry-Aware Probabilistic Circuits via Voronoi Tessellations
di: Sidheekh, Sahil, et al.
Pubblicazione: (2026)

Model Parallelism With Subnetwork Data Parallelism
di: Singh, Vaibhav, et al.
Pubblicazione: (2025)

Exploring Subnetwork Interactions in Heterogeneous Brain Network via Prior-Informed Graph Learning
di: Liu, Siyu, et al.
Pubblicazione: (2026)

Memory Constrained Dynamic Subnetwork Update for Transfer Learning
di: Quélennec, Aël, et al.
Pubblicazione: (2025)

FedSI: Federated Subnetwork Inference for Efficient Uncertainty Quantification
di: Chen, Hui, et al.
Pubblicazione: (2024)

The Multiple Ticket Hypothesis: Random Sparse Subnetworks Suffice for RLVR
di: Adewuyi, Israel, et al.
Pubblicazione: (2026)

Building Expressive and Tractable Probabilistic Generative Models: A Review
di: Sidheekh, Sahil, et al.
Pubblicazione: (2024)

Graph Q-Learning for Combinatorial Optimization
di: Dax, Victoria M., et al.
Pubblicazione: (2024)

Mirage: Model-Agnostic Graph Distillation for Graph Classification
di: Gupta, Mridul, et al.
Pubblicazione: (2023)

Reinforcement Learning Fine-Tunes a Sparse Subnetwork in Large Language Models
di: Balashov, Andrii
Pubblicazione: (2025)

Continual Deep Learning on the Edge via Stochastic Local Competition among Subnetworks
di: Christophides, Theodoros, et al.
Pubblicazione: (2024)

Permutation Picture of Graph Combinatorial Optimization Problems
di: Min, Yimeng
Pubblicazione: (2024)

Combinatorial Optimization with Automated Graph Neural Networks
di: Liu, Yang, et al.
Pubblicazione: (2024)

Tula: Optimizing Time, Cost, and Generalization in Distributed Large-Batch Training
di: Tyagi, Sahil, et al.
Pubblicazione: (2026)

Stochastic Collapse: How Gradient Noise Attracts SGD Dynamics Towards Simpler Subnetworks
di: Chen, Feng, et al.
Pubblicazione: (2023)

Localising Dropout Variance in Twin Networks
di: Doyle, Cooper
Pubblicazione: (2025)

Discovering Knowledge-Critical Subnetworks in Pretrained Language Models
di: Bayazit, Deniz, et al.
Pubblicazione: (2023)

Decision-focused Graph Neural Networks for Combinatorial Optimization
di: Liu, Yang, et al.
Pubblicazione: (2024)

Task-specific Subnetwork Discovery in Reinforcement Learning for Autonomous Underwater Navigation
di: Liu, Yi-Ling, et al.
Pubblicazione: (2026)

Graph Reinforcement Learning for Combinatorial Optimization: A Survey and Unifying Perspective
di: Darvariu, Victor-Alexandru, et al.
Pubblicazione: (2024)

Combinatorial Creativity: A New Frontier in Generalization Abilities
di: Schapiro, Samuel, et al.
Pubblicazione: (2025)

Generative Urban Flow Modeling: From Geometry to Airflow with Graph Diffusion
di: Giral, Francisco, et al.
Pubblicazione: (2025)

Survey on Generalization Theory for Graph Neural Networks
di: Vasileiou, Antonis, et al.
Pubblicazione: (2025)

STRCMP: Integrating Graph Structural Priors with Language Models for Combinatorial Optimization
di: Li, Xijun, et al.
Pubblicazione: (2025)

Annealing Machine-assisted Learning of Graph Neural Network for Combinatorial Optimization
di: Loyola, Pablo, et al.
Pubblicazione: (2025)

Revealing Combinatorial Reasoning of GNNs via Graph Concept Bottleneck Layer
di: Niu, Yue, et al.
Pubblicazione: (2026)

Tracing the Path to Grokking: Embeddings, Dropout, and Network Activation
di: Salah, Ahmed, et al.
Pubblicazione: (2025)

Routing the Lottery: Adaptive Subnetworks for Heterogeneous Data
di: Stefanski, Grzegorz, et al.
Pubblicazione: (2026)

Self-Predictive Representations for Combinatorial Generalization in Behavioral Cloning
di: Lawson, Daniel, et al.
Pubblicazione: (2025)