Cover Image

Deep Neural Networks Tend To Extrapolate Predictably

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Kang, Katie, Setlur, Amrith, Tomlin, Claire, Levine, Sergey
Format:	Preprint
Published:	2023
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

What Do Learning Dynamics Reveal About Generalization in LLM Reasoning?
by: Kang, Katie, et al.
Published: (2024)

Scaling Test-Time Compute Without Verification or RL is Suboptimal
by: Setlur, Amrith, et al.
Published: (2025)

Unfamiliar Finetuning Examples Control How Language Models Hallucinate
by: Kang, Katie, et al.
Published: (2024)

Lower Bounds for Public-Private Learning under Distribution Shift
by: Setlur, Amrith, et al.
Published: (2025)

Reasoning Cache: Continual Improvement Over Long Horizons via Short-Horizon RL
by: Wu, Ian, et al.
Published: (2026)

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs
by: Setlur, Amrith, et al.
Published: (2025)

Exact Unlearning of Finetuning Data via Model Merging at Scale
by: Kuo, Kevin, et al.
Published: (2025)

On the Benefits of Public Representations for Private Transfer Learning under Distribution Shift
by: Thaker, Pratiksha, et al.
Published: (2023)

Multitask Learning Can Improve Worst-Group Outcomes
by: Kulkarni, Atharva, et al.
Published: (2023)

POPE: Learning to Reason on Hard Problems via Privileged On-Policy Exploration
by: Qu, Yuxiao, et al.
Published: (2026)

A Stable Whitening Optimizer for Efficient Neural Network Training
by: Frans, Kevin, et al.
Published: (2025)

RL on Incorrect Synthetic Data Scales the Efficiency of LLM Math Reasoning by Eight-Fold
by: Setlur, Amrith, et al.
Published: (2024)

Reuse your FLOPs: Scaling RL on Hard Problems by Conditioning on Very Off-Policy Prefixes
by: Setlur, Amrith, et al.
Published: (2026)

PaRCE: Probabilistic and Reconstruction-based Competency Estimation for CNN-based Image Classification
by: Pohland, Sara, et al.
Published: (2024)

Explaining Low Perception Model Competency with High-Competency Counterfactuals
by: Pohland, Sara, et al.
Published: (2025)

Value-Based Deep RL Scales Predictably
by: Rybkin, Oleh, et al.
Published: (2025)

RLAD: Training LLMs to Discover Abstractions for Solving Reasoning Problems
by: Qu, Yuxiao, et al.
Published: (2025)

InT: Self-Proposed Interventions Enable Credit Assignment in LLM Reasoning
by: Yang, Matthew Y. R., et al.
Published: (2026)

Hacking Predictors Means Hacking Cars: Using Sensitivity Analysis to Identify Trajectory Prediction Vulnerabilities for Autonomous Driving Security
by: Gibson, Marsalis, et al.
Published: (2024)

Physical Simulation for Multi-agent Multi-machine Tending
by: Abdalwhab, Abdalwhab, et al.
Published: (2024)

Mechanistic interpretability for steering vision-language-action models
by: Häon, Bear, et al.
Published: (2025)

Infinite-Horizon Reach-Avoid Zero-Sum Games via Deep Reinforcement Learning
by: Li, Jingqi, et al.
Published: (2022)

Learning Multi-agent Multi-machine Tending by Mobile Robots
by: Abdalwhab, Abdalwhab, et al.
Published: (2024)

Safety Filters for Black-Box Dynamical Systems by Learning Discriminating Hyperplanes
by: Lavanakul, Will, et al.
Published: (2024)

Rewarding Progress: Scaling Automated Process Verifiers for LLM Reasoning
by: Setlur, Amrith, et al.
Published: (2024)

Manifold-Orthogonal Dual-spectrum Extrapolation for Parameterized Physics-Informed Neural Networks
by: Liang, Zhangyong, et al.
Published: (2026)

Predicting Emergent Capabilities by Finetuning
by: Snell, Charlie, et al.
Published: (2024)

Optimizing Test-Time Compute via Meta Reinforcement Fine-Tuning
by: Qu, Yuxiao, et al.
Published: (2025)

Bayesian Neural Scaling Law Extrapolation with Prior-Data Fitted Networks
by: Lee, Dongwoo, et al.
Published: (2025)

Beyond Interpolation: Extrapolative Reasoning with Reinforcement Learning and Graph Neural Networks
by: Grillo, Niccolò, et al.
Published: (2025)

Function Extrapolation with Neural Networks and Its Application for Manifolds
by: Hay, Guy, et al.
Published: (2024)

QED-Nano: Teaching a Tiny Model to Prove Hard Theorems
by: LM-Provers, et al.
Published: (2026)

Through a Steerable Lens: Magnifying Neural Network Interpretability via Phase-Based Extrapolation
by: Mahdisoltani, Farzaneh, et al.
Published: (2025)

Enhancing Quantum Variational Algorithms with Zero Noise Extrapolation via Neural Networks
by: Bhattacharjee, Subhasree, et al.
Published: (2024)

On Logical Extrapolation for Mazes with Recurrent and Implicit Networks
by: Knutson, Brandon, et al.
Published: (2024)

Gait Switching and Enhanced Stabilization of Walking Robots with Deep Learning-based Reachability: A Case Study on Two-link Walker
by: Xia, Xingpeng, et al.
Published: (2024)

Trend Extrapolation for Technology Forecasting: Leveraging LSTM Neural Networks for Trend Analysis of Space Exploration Vessels
by: Tsai, Peng-Hung, et al.
Published: (2025)

Conformalized Link Prediction on Graph Neural Networks
by: Zhao, Tianyi, et al.
Published: (2024)

Extrapolability Improvement of Machine Learning-Based Evapotranspiration Models via Domain-Adversarial Neural Networks
by: Shi, Haiyang
Published: (2024)

Why Cannot Neural Networks Master Extrapolation? Insights from Physical Laws
by: Dakhmouche, Ramzi, et al.
Published: (2025)