Image de couverture de livre

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

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Vastola, John J., Gershman, Samuel J., Rajan, Kanaka
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

A Variational Manifold Embedding Framework for Nonlinear Dimensionality Reduction
par: Vastola, John J., et autres
Publié: (2025)

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

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

Deep RL Needs Deep Behavior Analysis: Exploring Implicit Planning by Model-Free Agents in Open-Ended Environments
par: Simmons-Edler, Riley, et autres
Publié: (2025)

Derivatives of Stochastic Gradient Descent in parametric optimization
par: Iutzeler, Franck, et autres
Publié: (2024)

Fast weight programming and linear transformers: from machine learning to neurobiology
par: Irie, Kazuki, et autres
Publié: (2025)

Blending Complementary Memory Systems in Hybrid Quadratic-Linear Transformers
par: Irie, Kazuki, et autres
Publié: (2025)

Thermodynamic Natural Gradient Descent
par: Donatella, Kaelan, et autres
Publié: (2024)

Compact Rule-Based Classifier Learning via Gradient Descent
par: Fumanal-Idocin, Javier, et autres
Publié: (2025)

Artificial intelligence for science: The easy and hard problems
par: Battleday, Ruairidh M., et autres
Publié: (2024)

Multiclass Loss Geometry Matters for Generalization of Gradient Descent in Separable Classification
par: Schliserman, Matan, et autres
Publié: (2025)

Large Stepsize Gradient Descent for Logistic Loss: Non-Monotonicity of the Loss Improves Optimization Efficiency
par: Wu, Jingfeng, et autres
Publié: (2024)

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

A circuit for predicting hierarchical structure in-context in Large Language Models
par: Saanum, Tankred, et autres
Publié: (2025)

General Intelligence Requires Reward-based Pretraining
par: Han, Seungwook, et autres
Publié: (2025)

Successor-Predecessor Intrinsic Exploration
par: Yu, Changmin, et autres
Publié: (2023)

Distributed Gradient Descent for Functional Learning
par: Yu, Zhan, et autres
Publié: (2023)

Any-stepsize Gradient Descent for Separable Data under Fenchel-Young Losses
par: Bao, Han, et autres
Publié: (2025)

Key-value memory in the brain
par: Gershman, Samuel J., et autres
Publié: (2025)

A dimensional R2 regression metric
par: Yoo, Jaesung, et autres
Publié: (2026)

Neutron Reflectometry by Gradient Descent
par: Champneys, Max D., et autres
Publié: (2025)

Learning Tree-Based Models with Gradient Descent
par: Marton, Sascha
Publié: (2026)

Training Instabilities Induce Flatness Bias in Gradient Descent
par: Wang, Lawrence, et autres
Publié: (2025)

Occam Gradient Descent
par: Kausik, B. N.
Publié: (2024)

The Hidden Linear Structure in Score-Based Models and its Application
par: Wang, Binxu, et autres
Publié: (2023)

LossLens: Diagnostics for Machine Learning through Loss Landscape Visual Analytics
par: Xie, Tiankai, et autres
Publié: (2024)

Learning Associative Memories with Gradient Descent
par: Cabannes, Vivien, et autres
Publié: (2024)

In-context Learning and Gradient Descent Revisited
par: Deutch, Gilad, et autres
Publié: (2023)

Modified Loss of Momentum Gradient Descent: Fine-Grained Analysis
par: Cattaneo, Matias D., et autres
Publié: (2025)

Stopping Rules for Stochastic Gradient Descent via Anytime-Valid Confidence Sequences
par: Aolaritei, Liviu, et autres
Publié: (2025)

AI-Powered Autonomous Weapons Risk Geopolitical Instability and Threaten AI Research
par: Simmons-Edler, Riley, et autres
Publié: (2024)

Turning Stale Gradients into Stable Gradients: Coherent Coordinate Descent with Implicit Landscape Smoothing for Lightweight Zeroth-Order Optimization
par: Liang, Chen, et autres
Publié: (2026)

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

Learning Curves of Stochastic Gradient Descent in Kernel Regression
par: Zhang, Haihan, et autres
Publié: (2025)

Personalized Federated Learning with Exact Stochastic Gradient Descent
par: Nikoloutsopoulos, Sotirios, et autres
Publié: (2022)

Towards Learning Stochastic Population Models by Gradient Descent
par: Kreikemeyer, Justin N., et autres
Publié: (2024)

Partially Lazy Gradient Descent for Smoothed Online Learning
par: Mhaisen, Naram, et autres
Publié: (2026)

Why Depth Matters in Parallelizable Sequence Models: A Lie Algebraic View
par: Heo, Gyuryang, et autres
Publié: (2026)

Hybrid Coordinate Descent for Efficient Neural Network Learning Using Line Search and Gradient Descent
par: Hsiao, Yen-Che, et autres
Publié: (2024)

Stacking as Accelerated Gradient Descent
par: Agarwal, Naman, et autres
Publié: (2024)