Copertina

Lecture Notes on Linear Neural Networks: A Tale of Optimization and Generalization in Deep Learning

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Cohen, Nadav, Razin, Noam
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

What Makes Data Suitable for a Locally Connected Neural Network? A Necessary and Sufficient Condition Based on Quantum Entanglement
di: Alexander, Yotam, et al.
Pubblicazione: (2023)

Understanding Deep Learning via Notions of Rank
di: Razin, Noam
Pubblicazione: (2024)

Implicit Bias of Policy Gradient in Linear Quadratic Control: Extrapolation to Unseen Initial States
di: Razin, Noam, et al.
Pubblicazione: (2024)

Mathematics of Neural Networks (Lecture Notes Graduate Course)
di: Smets, Bart M. N.
Pubblicazione: (2024)

Inertial Navigation Meets Deep Learning: A Survey of Current Trends and Future Directions
di: Cohen, Nadav, et al.
Pubblicazione: (2023)

Contextual Plackett-Luce: An Efficient Neural Model for Probabilistic Sequence Selection under Ambiguity
di: Mizrachi, Noam, et al.
Pubblicazione: (2026)

When Errors Can Be Beneficial: A Categorization of Imperfect Rewards for Policy Gradient
di: Shang, Shuning, et al.
Pubblicazione: (2026)

The Implicit Bias of Structured State Space Models Can Be Poisoned With Clean Labels
di: Slutzky, Yonatan, et al.
Pubblicazione: (2024)

Why is Your Language Model a Poor Implicit Reward Model?
di: Razin, Noam, et al.
Pubblicazione: (2025)

Unintentional Unalignment: Likelihood Displacement in Direct Preference Optimization
di: Razin, Noam, et al.
Pubblicazione: (2024)

Classifying Overlapping Gaussian Mixtures in High Dimensions: From Optimal Classifiers to Neural Nets
di: Cohen, Khen, et al.
Pubblicazione: (2024)

What Makes a Reward Model a Good Teacher? An Optimization Perspective
di: Razin, Noam, et al.
Pubblicazione: (2025)

On the (Non) Injectivity of Piecewise Linear Janossy Pooling
di: Reshef, Ilai, et al.
Pubblicazione: (2025)

FSW-GNN: A Bi-Lipschitz WL-Equivalent Graph Neural Network
di: Sverdlov, Yonatan, et al.
Pubblicazione: (2024)

Deep Reinforcement Learning and The Tale of Two Temporal Difference Errors
di: Rojas, Juan Sebastian, et al.
Pubblicazione: (2026)

NdLinear: Preserving Multi-Dimensional Structure for Parameter-Efficient Neural Networks
di: Reneau, Alex, et al.
Pubblicazione: (2025)

Decoupled Weight Decay for Any $p$ Norm
di: Outmezguine, Nadav Joseph, et al.
Pubblicazione: (2024)

DSF-GAN: DownStream Feedback Generative Adversarial Network
di: Perets, Oriel, et al.
Pubblicazione: (2024)

Hierarchical Zero-Order Optimization for Deep Neural Networks
di: Cao, Sansheng, et al.
Pubblicazione: (2026)

Learning to Solve Combinatorial Optimization under Positive Linear Constraints via Non-Autoregressive Neural Networks
di: Wang, Runzhong, et al.
Pubblicazione: (2024)

Learning Dynamics of Deep Learning -- Force Analysis of Deep Neural Networks
di: Ren, Yi
Pubblicazione: (2025)

Conjugate Learning Theory: Uncovering the Mechanisms of Trainability and Generalization in Deep Neural Networks
di: Qi, Binchuan
Pubblicazione: (2026)

Learning Distinguishable Representations in Deep Q-Networks for Linear Transfer
di: Sathish, Sooraj, et al.
Pubblicazione: (2025)

Enhancing Deep Learning with Optimized Gradient Descent: Bridging Numerical Methods and Neural Network Training
di: Ma, Yuhan, et al.
Pubblicazione: (2024)

Learning Shrinks the Hard Tail: Training-Dependent Inference Scaling in a Solvable Linear Model
di: Levi, Noam
Pubblicazione: (2026)

A Relational Inductive Bias for Dimensional Abstraction in Neural Networks
di: Campbell, Declan, et al.
Pubblicazione: (2024)

Outcome-Based RL Provably Leads Transformers to Reason, but Only With the Right Data
di: Ran-Milo, Yuval, et al.
Pubblicazione: (2026)

Decoding Generalization from Memorization in Deep Neural Networks
di: Ketha, Simran, et al.
Pubblicazione: (2025)

Optimizing Deep Neural Networks using Safety-Guided Self Compression
di: Zbeeb, Mohammad, et al.
Pubblicazione: (2025)

Monotone and Separable Set Functions: Characterizations and Neural Models
di: Sarangi, Soutrik, et al.
Pubblicazione: (2025)

Addressing Spectral Bias of Deep Neural Networks by Multi-Grade Deep Learning
di: Fang, Ronglong, et al.
Pubblicazione: (2024)

When and How to Canonize: A Generalization Perspective
di: Sverdlov, Yonatan, et al.
Pubblicazione: (2026)

Solving Deep Reinforcement Learning Tasks with Evolution Strategies and Linear Policy Networks
di: Wong, Annie, et al.
Pubblicazione: (2024)

Quantifying the Pre-training Dividend: Generative versus Latent Self-Supervised Learning for Time Series Foundation Models
di: Major, Noam, et al.
Pubblicazione: (2026)

Reconstructing Deep Neural Networks: Unleashing the Optimization Potential of Natural Gradient Descent
di: Liu, Weihua, et al.
Pubblicazione: (2024)

Vanishing Gradients in Reinforcement Finetuning of Language Models
di: Razin, Noam, et al.
Pubblicazione: (2023)

Cross-Entropy Optimization for Hyperparameter Optimization in Stochastic Gradient-based Approaches to Train Deep Neural Networks
di: Li, Kevin, et al.
Pubblicazione: (2024)

Linear Mode Connectivity in Sparse Neural Networks
di: McDermott, Luke, et al.
Pubblicazione: (2023)

A Generalization Bound for Nearly-Linear Networks
di: Golikov, Eugene
Pubblicazione: (2024)

Understanding Optimization in Deep Learning with Central Flows
di: Cohen, Jeremy M., et al.
Pubblicazione: (2024)