Imagen de Portada

Gradient Descent as Loss Landscape Navigation: a Normative Framework for Deriving Learning Rules

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Vastola, John J., Gershman, Samuel J., Rajan, Kanaka
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

A Variational Manifold Embedding Framework for Nonlinear Dimensionality Reduction
por: Vastola, John J., et al.
Publicado: (2025)

Dynamical symmetries in the fluctuation-driven regime: an application of Noether's theorem to noisy dynamical systems
por: Vastola, John J.
Publicado: (2025)

Generalization through variance: how noise shapes inductive biases in diffusion models
por: Vastola, John J.
Publicado: (2025)

Deep RL Needs Deep Behavior Analysis: Exploring Implicit Planning by Model-Free Agents in Open-Ended Environments
por: Simmons-Edler, Riley, et al.
Publicado: (2025)

Derivatives of Stochastic Gradient Descent in parametric optimization
por: Iutzeler, Franck, et al.
Publicado: (2024)

Fast weight programming and linear transformers: from machine learning to neurobiology
por: Irie, Kazuki, et al.
Publicado: (2025)

Blending Complementary Memory Systems in Hybrid Quadratic-Linear Transformers
por: Irie, Kazuki, et al.
Publicado: (2025)

Thermodynamic Natural Gradient Descent
por: Donatella, Kaelan, et al.
Publicado: (2024)

Compact Rule-Based Classifier Learning via Gradient Descent
por: Fumanal-Idocin, Javier, et al.
Publicado: (2025)

Artificial intelligence for science: The easy and hard problems
por: Battleday, Ruairidh M., et al.
Publicado: (2024)

Multiclass Loss Geometry Matters for Generalization of Gradient Descent in Separable Classification
por: Schliserman, Matan, et al.
Publicado: (2025)

Large Stepsize Gradient Descent for Logistic Loss: Non-Monotonicity of the Loss Improves Optimization Efficiency
por: Wu, Jingfeng, et al.
Publicado: (2024)

Quadratic Gradient: A Unified Framework Bridging Gradient Descent and Newton-Type Methods by Synthesizing Hessians and Gradients
por: Chiang, John
Publicado: (2022)

A circuit for predicting hierarchical structure in-context in Large Language Models
por: Saanum, Tankred, et al.
Publicado: (2025)

General Intelligence Requires Reward-based Pretraining
por: Han, Seungwook, et al.
Publicado: (2025)

Successor-Predecessor Intrinsic Exploration
por: Yu, Changmin, et al.
Publicado: (2023)

Distributed Gradient Descent for Functional Learning
por: Yu, Zhan, et al.
Publicado: (2023)

Any-stepsize Gradient Descent for Separable Data under Fenchel-Young Losses
por: Bao, Han, et al.
Publicado: (2025)

Key-value memory in the brain
por: Gershman, Samuel J., et al.
Publicado: (2025)

A dimensional R2 regression metric
por: Yoo, Jaesung, et al.
Publicado: (2026)

Neutron Reflectometry by Gradient Descent
por: Champneys, Max D., et al.
Publicado: (2025)

Learning Tree-Based Models with Gradient Descent
por: Marton, Sascha
Publicado: (2026)

The Hidden Linear Structure in Score-Based Models and its Application
por: Wang, Binxu, et al.
Publicado: (2023)

Training Instabilities Induce Flatness Bias in Gradient Descent
por: Wang, Lawrence, et al.
Publicado: (2025)

Occam Gradient Descent
por: Kausik, B. N.
Publicado: (2024)

LossLens: Diagnostics for Machine Learning through Loss Landscape Visual Analytics
por: Xie, Tiankai, et al.
Publicado: (2024)

Learning Associative Memories with Gradient Descent
por: Cabannes, Vivien, et al.
Publicado: (2024)

In-context Learning and Gradient Descent Revisited
por: Deutch, Gilad, et al.
Publicado: (2023)

Modified Loss of Momentum Gradient Descent: Fine-Grained Analysis
por: Cattaneo, Matias D., et al.
Publicado: (2025)

AI-Powered Autonomous Weapons Risk Geopolitical Instability and Threaten AI Research
por: Simmons-Edler, Riley, et al.
Publicado: (2024)

Stopping Rules for Stochastic Gradient Descent via Anytime-Valid Confidence Sequences
por: Aolaritei, Liviu, et al.
Publicado: (2025)

Turning Stale Gradients into Stable Gradients: Coherent Coordinate Descent with Implicit Landscape Smoothing for Lightweight Zeroth-Order Optimization
por: Liang, Chen, et al.
Publicado: (2026)

Gradient Descent with Provably Tuned Learning-rate Schedules
por: Sharma, Dravyansh
Publicado: (2025)

Learning Curves of Stochastic Gradient Descent in Kernel Regression
por: Zhang, Haihan, et al.
Publicado: (2025)

Personalized Federated Learning with Exact Stochastic Gradient Descent
por: Nikoloutsopoulos, Sotirios, et al.
Publicado: (2022)

Towards Learning Stochastic Population Models by Gradient Descent
por: Kreikemeyer, Justin N., et al.
Publicado: (2024)

Partially Lazy Gradient Descent for Smoothed Online Learning
por: Mhaisen, Naram, et al.
Publicado: (2026)

Why Depth Matters in Parallelizable Sequence Models: A Lie Algebraic View
por: Heo, Gyuryang, et al.
Publicado: (2026)

Hybrid Coordinate Descent for Efficient Neural Network Learning Using Line Search and Gradient Descent
por: Hsiao, Yen-Che, et al.
Publicado: (2024)

Stacking as Accelerated Gradient Descent
por: Agarwal, Naman, et al.
Publicado: (2024)