Image de couverture de livre

Scaling Exponents Across Parameterizations and Optimizers

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Everett, Katie, Xiao, Lechao, Wortsman, Mitchell, Alemi, Alexander A., Novak, Roman, Liu, Peter J., Gur, Izzeddin, Sohl-Dickstein, Jascha, Kaelbling, Leslie Pack, Lee, Jaehoon, Pennington, Jeffrey
Format:	Preprint
Publié:	2024
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

Training LLMs over Neurally Compressed Text
par: Lester, Brian, et autres
Publié: (2024)

The boundary of neural network trainability is fractal
par: Sohl-Dickstein, Jascha
Publié: (2024)

General-Purpose In-Context Learning by Meta-Learning Transformers
par: Kirsch, Louis, et autres
Publié: (2022)

The Hot Mess of AI: How Does Misalignment Scale With Model Intelligence and Task Complexity?
par: Hägele, Alexander, et autres
Publié: (2026)

4+3 Phases of Compute-Optimal Neural Scaling Laws
par: Paquette, Elliot, et autres
Publié: (2024)

Which Reconstruction Model Should a Robot Use? Routing Image-to-3D Models for Cost-Aware Robotic Manipulation
par: Anand, Akash, et autres
Publié: (2026)

Rational Inverse Reasoning
par: Zandonati, Ben, et autres
Publié: (2025)

Embodied Uncertainty-Aware Object Segmentation
par: Fang, Xiaolin, et autres
Publié: (2024)

Scaling Collapse Reveals Universal Dynamics in Compute-Optimally Trained Neural Networks
par: Qiu, Shikai, et autres
Publié: (2025)

Beyond Human Data: Scaling Self-Training for Problem-Solving with Language Models
par: Singh, Avi, et autres
Publié: (2023)

Guided Exploration for Efficient Relational Model Learning
par: Feng, Annie, et autres
Publié: (2025)

What Planning Problems Can A Relational Neural Network Solve?
par: Mao, Jiayuan, et autres
Publié: (2023)

Rethinking Conventional Wisdom in Machine Learning: From Generalization to Scaling
par: Xiao, Lechao
Publié: (2024)

Levels of AGI for Operationalizing Progress on the Path to AGI
par: Morris, Meredith Ringel, et autres
Publié: (2023)

Trust the PRoC3S: Solving Long-Horizon Robotics Problems with LLMs and Constraint Satisfaction
par: Curtis, Aidan, et autres
Publié: (2024)

Towards Practical Finite Sample Bounds for Motion Planning in TAMP
par: Shaw, Seiji, et autres
Publié: (2024)

One-Shot Manipulation Strategy Learning by Making Contact Analogies
par: Liu, Yuyao, et autres
Publié: (2024)

SceneComplete: Open-World 3D Scene Completion in Cluttered Real World Environments for Robot Manipulation
par: Agarwal, Aditya, et autres
Publié: (2024)

Guiding Long-Horizon Task and Motion Planning with Vision Language Models
par: Yang, Zhutian, et autres
Publié: (2024)

Combining Planning and Diffusion for Mobility with Unknown Dynamics
par: Ravan, Yajvan, et autres
Publié: (2024)

Compositional Generative Modeling: A Single Model is Not All You Need
par: Du, Yilun, et autres
Publié: (2024)

Training Language Models on the Knowledge Graph: Insights on Hallucinations and Their Detectability
par: Hron, Jiri, et autres
Publié: (2024)

Reduce, Reuse, Recycle: Compositional Generation with Energy-Based Diffusion Models and MCMC
par: Du, Yilun, et autres
Publié: (2023)

Distilled Feature Fields Enable Few-Shot Language-Guided Manipulation
par: Shen, William, et autres
Publié: (2023)

AI Organizations are More Effective but Less Aligned than Individual Agents
par: Shen, Judy Hanwen, et autres
Publié: (2026)

Exposing Limitations of Language Model Agents in Sequential-Task Compositions on the Web
par: Furuta, Hiroki, et autres
Publié: (2023)

Streaming Flow Policy: Simplifying diffusion/flow-matching policies by treating action trajectories as flow trajectories
par: Jiang, Sunshine, et autres
Publié: (2025)

"Set It Up!": Functional Object Arrangement with Compositional Generative Models
par: Xu, Yiqing, et autres
Publié: (2024)

GCS*: Forward Heuristic Search on Implicit Graphs of Convex Sets
par: Chia, Shao Yuan Chew, et autres
Publié: (2024)

Functional Risk Minimization
par: Alet, Ferran, et autres
Publié: (2024)

DiMSam: Diffusion Models as Samplers for Task and Motion Planning under Partial Observability
par: Fang, Xiaolin, et autres
Publié: (2023)

"Set It Up": Functional Object Arrangement with Compositional Generative Models (Journal Version)
par: Xu, Yiqing, et autres
Publié: (2025)

LLM-Guided Probabilistic Program Induction for POMDP Model Estimation
par: Curtis, Aidan, et autres
Publié: (2025)

From Pixels to Predicates: Learning Symbolic World Models via Pretrained Vision-Language Models
par: Athalye, Ashay, et autres
Publié: (2024)

Partially Observable Task and Motion Planning with Uncertainty and Risk Awareness
par: Curtis, Aidan, et autres
Publié: (2024)

A Strong Gravitational Lens Is Worth a Thousand Dark Matter Halos: Inference on Small-Scale Structure Using Sequential Methods
par: Wagner-Carena, Sebastian, et autres
Publié: (2024)

O PEDIATRA E SUA FUNÇÃO APOSTÓLICA: PERCEPÇÕES DE MÉDICOS RESIDENTES SOBRE SUAS PRÁTICAS
par: Paulo Dickstein
Publié: (2017)

The Amazing Journey of Reason
par: Alemi, Mario
Publié: (2020)

Exploring the Reasons Behind Iranian TEFL Graduate Students’ Academic Failure
par: Minoo Alemi
Publié: (2021)

Predicate Invention for Bilevel Planning
par: Silver, Tom, et autres
Publié: (2022)