Copertina

Theory of Minimal Weight Perturbations in Deep Networks and its Applications for Low-Rank Activated Backdoor Attacks

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Evans, Bethan, Tanner, Jared
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning Information Theory
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Model Merging by Output-Space Projection
di: Evans, Bethan, et al.
Pubblicazione: (2026)

How Controlling the Variance can Improve Training Stability of Sparsely Activated DNNs and CNNs
di: Dent, Emily, et al.
Pubblicazione: (2026)

Theoretical Guarantees for Low-Rank Compression of Deep Neural Networks
di: Zhang, Shihao, et al.
Pubblicazione: (2025)

Learning to Compress: Local Rank and Information Compression in Deep Neural Networks
di: Patel, Niket, et al.
Pubblicazione: (2024)

Byzantine-Resilient Federated PCA and Low Rank Column-wise Sensing
di: Singh, Ankit Pratap, et al.
Pubblicazione: (2023)

Guaranteed Nonconvex Low-Rank Tensor Estimation via Scaled Gradient Descent
di: Wu, Tong
Pubblicazione: (2025)

Information-Theoretic Guarantees for Recovering Low-Rank Tensors from Symmetric Rank-One Measurements
di: Kızıldağ, Eren C.
Pubblicazione: (2025)

Scaled Gradient Descent for Ill-Conditioned Low-Rank Matrix Recovery with Optimal Sampling Complexity
di: Li, Zhenxuan, et al.
Pubblicazione: (2026)

Backdoor Attack against One-Class Sequential Anomaly Detection Models
di: Cheng, He, et al.
Pubblicazione: (2024)

A Generalized Information Bottleneck Theory of Deep Learning
di: Westphal, Charles, et al.
Pubblicazione: (2025)

Application of Deep Learning in Biological Data Compression
di: Zou, Chunyu
Pubblicazione: (2025)

The Maximum von Neumann Entropy Principle: Theory and Applications in Machine Learning
di: Wu, Youqi, et al.
Pubblicazione: (2026)

On the Theory of Continual Learning with Gradient Descent for Neural Networks
di: Taheri, Hossein, et al.
Pubblicazione: (2025)

Output-Constrained Lossy Source Coding With Application to Rate-Distortion-Perception Theory
di: Xie, Li, et al.
Pubblicazione: (2024)

Koopman-Based Generalization of Deep Reinforcement Learning With Application to Wireless Communications
di: Termehchi, Atefeh, et al.
Pubblicazione: (2025)

Efficient Wireless Federated Learning via Low-Rank Gradient Factorization
di: Guo, Mingzhao, et al.
Pubblicazione: (2024)

Information-Theoretic Generalization Bounds for Deep Neural Networks
di: He, Haiyun, et al.
Pubblicazione: (2024)

Advancing Deep Active Learning & Data Subset Selection: Unifying Principles with Information-Theory Intuitions
di: Kirsch, Andreas
Pubblicazione: (2024)

Convexity in Disguise: A Theoretical Framework for Nonconvex Low-Rank Matrix Estimation
di: Cui, Chengyu, et al.
Pubblicazione: (2026)

Minimal Communication-Cost Statistical Learning
di: Sefidgaran, Milad, et al.
Pubblicazione: (2024)

Best Arm Identification with Minimal Regret
di: Yang, Junwen, et al.
Pubblicazione: (2024)

One Word is Enough: Minimal Adversarial Perturbations for Neural Text Ranking
di: Karmakar, Tanmay, et al.
Pubblicazione: (2026)

Deep Adaptive Rate Allocation in Volatile Heterogeneous Wireless Networks
di: Maglione, Gregorio, et al.
Pubblicazione: (2026)

On Unbiased Low-Rank Approximation with Minimum Distortion
di: Barnes, Leighton Pate, et al.
Pubblicazione: (2025)

Stabilization of Perturbed Loss Function: Differential Privacy without Gradient Noise
di: Habib, Salman, et al.
Pubblicazione: (2025)

A Link between Coding Theory and Cross-Validation with Applications
di: Pahikkala, Tapio, et al.
Pubblicazione: (2021)

Automatic Rank Determination for Low-Rank Adaptation via Submodular Function Maximization
di: Gao, Yihang, et al.
Pubblicazione: (2025)

Neural Weight Norm = Kolmogorov Complexity
di: Musat, Tiberiu
Pubblicazione: (2026)

Testing Dependency of Weighted Random Graphs
di: Oren, Mor, et al.
Pubblicazione: (2024)

Stabilizing Private LASSO under Heterogeneous Covariates via Anisotropic Objective Perturbation
di: Tanzawa, Haruka, et al.
Pubblicazione: (2026)

Low Rank Field-Weighted Factorization Machines for Low Latency Item Recommendation
di: Shtoff, Alex, et al.
Pubblicazione: (2024)

Asymmetry of the Relative Entropy in the Regularization of Empirical Risk Minimization
di: Daunas, Francisco, et al.
Pubblicazione: (2024)

Deep Unfolded Fractional Optimization for Maximizing Robust Throughput in 6G Networks
di: Bui, Anh Thi, et al.
Pubblicazione: (2026)

Trustworthy Actionable Perturbations
di: Friedbaum, Jesse, et al.
Pubblicazione: (2024)

Empirical Risk Minimization with Relative Entropy Regularization
di: Perlaza, Samir M., et al.
Pubblicazione: (2022)

Near-optimal Rank Adaptive Inference of High Dimensional Matrices
di: Zheng, Frédéric, et al.
Pubblicazione: (2025)

Equivalence of the Empirical Risk Minimization to Regularization on the Family of f-Divergences
di: Daunas, Francisco, et al.
Pubblicazione: (2024)

Friendly Attacks to Improve Channel Coding Reliability
di: Kurmukova, Anastasiia, et al.
Pubblicazione: (2024)

Rank-1 Matrix Completion with Gradient Descent and Small Random Initialization
di: Kim, Daesung, et al.
Pubblicazione: (2022)

Vendi Information Gain for Active Learning and its Application to Ecology
di: Nguyen, Quan, et al.
Pubblicazione: (2025)