Cover Image

The Memory Perturbation Equation: Understanding Model's Sensitivity to Data

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Nickl, Peter, Xu, Lu, Tailor, Dharmesh, Möllenhoff, Thomas, Khan, Mohammad Emtiyaz
Format:	Preprint
Published:	2023
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Optimization Guarantees for Square-Root Natural-Gradient Variational Inference
by: Kumar, Navish, et al.
Published: (2025)

SVRG and Beyond via Posterior Correction
by: Daheim, Nico, et al.
Published: (2025)

How to Weight Multitask Finetuning? Fast Previews via Bayesian Model-Merging
by: Maldonado, Hugo Monzón, et al.
Published: (2024)

Model Merging by Uncertainty-Based Gradient Matching
by: Daheim, Nico, et al.
Published: (2023)

Knowledge Adaptation as Posterior Correction
by: Khan, Mohammad Emtiyaz
Published: (2025)

Information Geometry of Variational Bayes
by: Khan, Mohammad Emtiyaz
Published: (2025)

Improving LoRA with Variational Learning
by: Cong, Bai, et al.
Published: (2025)

Variational Low-Rank Adaptation Using IVON
by: Cong, Bai, et al.
Published: (2024)

Variational Learning is Effective for Large Deep Networks
by: Shen, Yuesong, et al.
Published: (2024)

Connecting Federated ADMM to Bayes
by: Swaroop, Siddharth, et al.
Published: (2025)

Joint Model and Data Sparsification via the Marginal Likelihood
by: Timans, Alexander, et al.
Published: (2026)

Variational Learning Induces Adaptive Label Smoothing
by: Yang, Sin-Han, et al.
Published: (2025)

Compact Memory for Continual Logistic Regression
by: Jung, Yohan, et al.
Published: (2025)

Federated ADMM from Bayesian Duality
by: Möllenhoff, Thomas, et al.
Published: (2025)

Conformal Prediction via Regression-as-Classification
by: Guha, Etash, et al.
Published: (2024)

A Bayesian Information-Theoretic Approach to Data Attribution
by: Tailor, Dharmesh, et al.
Published: (2026)

Log-Normal Multiplicative Dynamics for Stable Low-Precision Training of Large Networks
by: Nishida, Keigo, et al.
Published: (2025)

Natural Variational Annealing for Multimodal Optimization
by: LeMinh, Tâm, et al.
Published: (2025)

Learning the optimal state-feedback via supervised imitation learning
by: Tailor, Dharmesh, et al.
Published: (2019)

Improving Perturbation-based Explanations by Understanding the Role of Uncertainty Calibration
by: Decker, Thomas, et al.
Published: (2025)

Uncertainty-Aware Decoding with Minimum Bayes Risk
by: Daheim, Nico, et al.
Published: (2025)

Understanding Transformer from the Perspective of Associative Memory
by: Zhong, Shu, et al.
Published: (2025)

A Cost-Sensitive Transformer Model for Prognostics Under Highly Imbalanced Industrial Data
by: Beikmohammadi, Ali, et al.
Published: (2024)

Validation, Robustness, and Accuracy of Perturbation-Based Sensitivity Analysis Methods for Time-Series Deep Learning Models
by: Wang, Zhengguang
Published: (2024)

PerturbDiff: Functional Diffusion for Single-Cell Perturbation Modeling
by: Yuan, Xinyu, et al.
Published: (2026)

Uncertainty Estimation on Graphs with Structure Informed Stochastic Partial Differential Equations
by: Xu, Fred, et al.
Published: (2025)

Positive-Unlabeled Diffusion Models for Preventing Sensitive Data Generation
by: Takahashi, Hiroshi, et al.
Published: (2025)

Exploring the Landscape for Generative Sequence Models for Specialized Data Synthesis
by: Zbeeb, Mohammad, et al.
Published: (2024)

The Bayesian Learning Rule
by: Khan, Mohammad Emtiyaz, et al.
Published: (2021)

Honest Lying: Understanding Memory Confabulation in Reflexive Agents
by: Dixit, Prakhar, et al.
Published: (2026)

Variational Learning Finds Flatter Solutions at the Edge of Stability
by: Ghosh, Avrajit, et al.
Published: (2025)

Why Uncertainty Calibration Matters for Reliable Perturbation-based Explanations
by: Decker, Thomas, et al.
Published: (2025)

Certified Robustness against Sparse Adversarial Perturbations via Data Localization
by: Pal, Ambar, et al.
Published: (2024)

Perturbation-Induced Linearization: Constructing Unlearnable Data with Solely Linear Classifiers
by: Liu, Jinlin, et al.
Published: (2026)

Position: agentic AI orchestration should be Bayes-consistent
by: Papamarkou, Theodore, et al.
Published: (2026)

Taming Sensitive Weights : Noise Perturbation Fine-tuning for Robust LLM Quantization
by: Wang, Dongwei, et al.
Published: (2024)

Understanding and Improving Model Averaging in Federated Learning on Heterogeneous Data
by: Zhou, Tailin, et al.
Published: (2023)

Dynamic Logistic Ensembles with Recursive Probability and Automatic Subset Splitting for Enhanced Binary Classification
by: Khan, Mohammad Zubair, et al.
Published: (2024)

The Trap of Trajectory: Towards Understanding and Mitigating Spurious Correlations in Agentic Memory
by: Tang, Luoxi, et al.
Published: (2026)

Interpretable Perturbation Modeling Through Biomedical Knowledge Graphs
by: Passigan, Pascal, et al.
Published: (2025)