A Training-Time Diagnostic for Generalization via the Log-Alignment Ratio
Fuente:
arXiv
Saved in:
| Main Authors: | Shehper, Ali, Vaswani, Ashish |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
Efficient Federated Low Rank Matrix Completion
by: Abbasi, Ahmed Ali, et al.
Published: (2024)
by: Abbasi, Ahmed Ali, et al.
Published: (2024)
A Logic for Expressing Log-Precision Transformers
by: Merrill, William, et al.
Published: (2022)
by: Merrill, William, et al.
Published: (2022)
AltGDmin: Alternating GD and Minimization for Partly-Decoupled (Federated) Optimization
by: Vaswani, Namrata
Published: (2025)
by: Vaswani, Namrata
Published: (2025)
Sample Complexity Bounds for Linear Constrained MDPs with a Generative Model
by: Liu, Xingtu, et al.
Published: (2025)
by: Liu, Xingtu, et al.
Published: (2025)
Armijo Line-search Can Make (Stochastic) Gradient Descent Provably Faster
by: Vaswani, Sharan, et al.
Published: (2025)
by: Vaswani, Sharan, et al.
Published: (2025)
Improving OOD Generalization of Pre-trained Encoders via Aligned Embedding-Space Ensembles
by: Peng, Shuman, et al.
Published: (2024)
by: Peng, Shuman, et al.
Published: (2024)
A Little Depth Goes a Long Way: The Expressive Power of Log-Depth Transformers
by: Merrill, William, et al.
Published: (2025)
by: Merrill, William, et al.
Published: (2025)
Gradient-Weight Alignment as a Train-Time Proxy for Generalization in Classification Tasks
by: Hölzl, Florian A., et al.
Published: (2025)
by: Hölzl, Florian A., et al.
Published: (2025)
Fast and Sample Efficient Multi-Task Representation Learning in Stochastic Contextual Bandits
by: Lin, Jiabin, et al.
Published: (2024)
by: Lin, Jiabin, et al.
Published: (2024)
Efficient Training of Boltzmann Generators Using Off-Policy Log-Dispersion Regularization
by: Schopmans, Henrik, et al.
Published: (2026)
by: Schopmans, Henrik, et al.
Published: (2026)
Byzantine-Resilient Federated PCA and Low Rank Column-wise Sensing
by: Singh, Ankit Pratap, et al.
Published: (2023)
by: Singh, Ankit Pratap, et al.
Published: (2023)
Noisy Low Rank Column-wise Sensing
by: Singh, Ankit Pratap, et al.
Published: (2024)
by: Singh, Ankit Pratap, et al.
Published: (2024)
Density-Informed VAE (DiVAE): Reliable Log-Prior Probability via Density Alignment Regularization
by: Alessi, Michele, et al.
Published: (2025)
by: Alessi, Michele, et al.
Published: (2025)
Subliminal Effects in Your Data: A General Mechanism via Log-Linearity
by: Aden-Ali, Ishaq, et al.
Published: (2026)
by: Aden-Ali, Ishaq, et al.
Published: (2026)
OneLog: Towards End-to-End Training in Software Log Anomaly Detection
by: Hashemi, Shayan, et al.
Published: (2021)
by: Hashemi, Shayan, et al.
Published: (2021)
Convergence of Steepest Descent and Adam under Non-Uniform Smoothness
by: Vaswani, Sharan, et al.
Published: (2026)
by: Vaswani, Sharan, et al.
Published: (2026)
Dissecting Discrete Soft Actor-Critic: Limitations and Principled Alternatives
by: Asad, Reza, et al.
Published: (2025)
by: Asad, Reza, et al.
Published: (2025)
From Inverse Optimization to Feasibility to ERM
by: Mishra, Saurabh, et al.
Published: (2024)
by: Mishra, Saurabh, et al.
Published: (2024)
(Accelerated) Noise-adaptive Stochastic Heavy-Ball Momentum
by: Dang, Anh, et al.
Published: (2024)
by: Dang, Anh, et al.
Published: (2024)
Real-Time Evaluation Models for RAG: Who Detects Hallucinations Best?
by: Sardana, Ashish
Published: (2025)
by: Sardana, Ashish
Published: (2025)
Training-Free Generation of Protein Sequences from Small Family Alignments via Stochastic Attention
by: Varner, Jeffrey D.
Published: (2026)
by: Varner, Jeffrey D.
Published: (2026)
Towards Parameter-Free Temporal Difference Learning
by: Li, Yunxiang, et al.
Published: (2026)
by: Li, Yunxiang, et al.
Published: (2026)
Towards Principled, Practical Policy Gradient for Bandits and Tabular MDPs
by: Lu, Michael, et al.
Published: (2024)
by: Lu, Michael, et al.
Published: (2024)
Diffusion Secant Alignment for Score-Based Density Ratio Estimation
by: Chen, Wei, et al.
Published: (2025)
by: Chen, Wei, et al.
Published: (2025)
BSO: Safety Alignment Is Density Ratio Matching
by: Nguyen, Tien-Phat, et al.
Published: (2026)
by: Nguyen, Tien-Phat, et al.
Published: (2026)
FusionLog: Cross-System Log-based Anomaly Detection via Fusion of General and Proprietary Knowledge
by: Zhao, Xinlong, et al.
Published: (2025)
by: Zhao, Xinlong, et al.
Published: (2025)
Spectrum: Targeted Training on Signal to Noise Ratio
by: Hartford, Eric, et al.
Published: (2024)
by: Hartford, Eric, et al.
Published: (2024)
Test-Time Alignment via Hypothesis Reweighting
by: Lee, Yoonho, et al.
Published: (2024)
by: Lee, Yoonho, et al.
Published: (2024)
Towards Noise-adaptive, Problem-adaptive (Accelerated) Stochastic Gradient Descent
by: Vaswani, Sharan, et al.
Published: (2021)
by: Vaswani, Sharan, et al.
Published: (2021)
ETS: Energy-Guided Test-Time Scaling for Training-Free RL Alignment
by: Li, Xiuyu, et al.
Published: (2026)
by: Li, Xiuyu, et al.
Published: (2026)
Log Optimization Simplification Method for Predicting Remaining Time
by: Ye, Jianhong, et al.
Published: (2025)
by: Ye, Jianhong, et al.
Published: (2025)
Augmented Lagrangian Method for Last-Iterate Convergence for Constrained MDPs
by: Lu, Michael, et al.
Published: (2026)
by: Lu, Michael, et al.
Published: (2026)
SigDiffusions: Score-Based Diffusion Models for Time Series via Log-Signature Embeddings
by: Barancikova, Barbora, et al.
Published: (2024)
by: Barancikova, Barbora, et al.
Published: (2024)
FastLogAD: Log Anomaly Detection with Mask-Guided Pseudo Anomaly Generation and Discrimination
by: Lin, Yifei, et al.
Published: (2024)
by: Lin, Yifei, et al.
Published: (2024)
Length Generalization with Log-Depth Recurrent Units
by: Pert, Charles, et al.
Published: (2026)
by: Pert, Charles, et al.
Published: (2026)
A Log-Linear Analytics Approach to Cost Model Regularization for Inpatient Stays through Diagnostic Code Merging
by: Lu, Chi-Ken, et al.
Published: (2025)
by: Lu, Chi-Ken, et al.
Published: (2025)
Exploring the Dynamic Scheduling Space of Real-Time Generative AI Applications on Emerging Heterogeneous Systems
by: Karami, Rachid, et al.
Published: (2025)
by: Karami, Rachid, et al.
Published: (2025)
Log-Normal Multiplicative Dynamics for Stable Low-Precision Training of Large Networks
by: Nishida, Keigo, et al.
Published: (2025)
by: Nishida, Keigo, et al.
Published: (2025)
Distributional Evaluation of Generative Models via Relative Density Ratio
by: Xu, Yuliang, et al.
Published: (2025)
by: Xu, Yuliang, et al.
Published: (2025)
LogSyn: A Few-Shot LLM Framework for Structured Insight Extraction from Unstructured General Aviation Maintenance Logs
by: Agarwal, Devansh, et al.
Published: (2025)
by: Agarwal, Devansh, et al.
Published: (2025)
Similar Items
-
Efficient Federated Low Rank Matrix Completion
by: Abbasi, Ahmed Ali, et al.
Published: (2024) -
A Logic for Expressing Log-Precision Transformers
by: Merrill, William, et al.
Published: (2022) -
AltGDmin: Alternating GD and Minimization for Partly-Decoupled (Federated) Optimization
by: Vaswani, Namrata
Published: (2025) -
Sample Complexity Bounds for Linear Constrained MDPs with a Generative Model
by: Liu, Xingtu, et al.
Published: (2025) -
Armijo Line-search Can Make (Stochastic) Gradient Descent Provably Faster
by: Vaswani, Sharan, et al.
Published: (2025)