Image de couverture de livre

SEMU: Singular Value Decomposition for Efficient Machine Unlearning

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Sendera, Marcin, Struski, Łukasz, Książek, Kamil, Musiol, Kryspin, Tabor, Jacek, Rymarczyk, Dawid
Format:	Preprint
Publié:	2025
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

SIDE: Sparse Information Disentanglement for Explainable Artificial Intelligence
par: Dubovik, Viktar, et autres
Publié: (2025)

InfoDisent: Explainability of Image Classification Models by Information Disentanglement
par: Struski, Łukasz, et autres
Publié: (2024)

ProMIL: Probabilistic Multiple Instance Learning for Medical Imaging
par: Struski, Łukasz, et autres
Publié: (2023)

ProtoSeg: Interpretable Semantic Segmentation with Prototypical Parts
par: Sacha, Mikołaj, et autres
Publié: (2023)

Bounding Evidence and Estimating Log-Likelihood in VAE
par: Struski, Łukasz, et autres
Publié: (2022)

ProPML: Probability Partial Multi-label Learning
par: Struski, Łukasz, et autres
Publié: (2024)

LAPLEX: The FFT of Learnable Laplace Kernels
par: Struski, Łukasz, et autres
Publié: (2026)

DAVE: Distribution-aware Attribution via ViT Gradient Decomposition
par: Wróbel, Adam, et autres
Publié: (2026)

PrAViC: Probabilistic Adaptation Framework for Real-Time Video Classification
par: Trędowicz, Magdalena, et autres
Publié: (2024)

SONG: Self-Organizing Neural Graphs
par: Struski, Łukasz, et autres
Publié: (2021)

LucidPPN: Unambiguous Prototypical Parts Network for User-centric Interpretable Computer Vision
par: Pach, Mateusz, et autres
Publié: (2024)

Stop Marginalizing My Dreams: Model Inversion via Laplace Kernel for Continual Learning
par: Krukowski, Patryk, et autres
Publié: (2026)

FeNeC: Enhancing Continual Learning via Feature Clustering with Neighbor- or Logit-Based Classification
par: Książek, Kamil, et autres
Publié: (2025)

Conceptualizing Embeddings: Sparse Disentanglement for Vision-Language Models
par: Kubaty, Piotr, et autres
Publié: (2026)

Tight Bounds for Jensen's Gap with Applications to Variational Inference
par: Mazur, Marcin, et autres
Publié: (2025)

PhAME: Phenotype-Aware Molecular Editing via Latent Diffusion
par: Janisiów, Łukasz, et autres
Publié: (2026)

HyperMask: Adaptive Hypernetwork-based Masks for Continual Learning
par: Książek, Kamil, et autres
Publié: (2023)

SHIELD: Secure Hypernetworks for Incremental Expansion Learning Defense
par: Krukowski, Patryk, et autres
Publié: (2025)

Hi-fi functional priors by learning activations
par: Sendera, Marcin, et autres
Publié: (2025)

Revisiting the Equivalence of Bayesian Neural Networks and Gaussian Processes: On the Importance of Learning Activations
par: Sendera, Marcin, et autres
Publié: (2024)

B-XAIC Dataset: Benchmarking Explainable AI for Graph Neural Networks Using Chemical Data
par: Proszewska, Magdalena, et autres
Publié: (2025)

Revisiting FunnyBirds evaluation framework for prototypical parts networks
par: Opłatek, Szymon, et autres
Publié: (2024)

Sparser, Better, Deeper, Stronger: Improving Sparse Training with Exact Orthogonal Initialization
par: Nowak, Aleksandra Irena, et autres
Publié: (2024)

BARRIER: Bounded Activation Regions for Robust Information Erasure
par: Miksa, Jan, et autres
Publié: (2026)

SoftSAE: Dynamic Top-K Selection for Adaptive Sparse Autoencoders
par: Stępień, Jakub, et autres
Publié: (2026)

Efficient GPU implementation of randomized SVD and its applications
par: Struski, Łukasz, et autres
Publié: (2021)

TORE: Token Recycling in Vision Transformers for Efficient Active Visual Exploration
par: Olszewski, Jan, et autres
Publié: (2023)

LapSum -- One Method to Differentiate Them All: Ranking, Sorting and Top-k Selection
par: Struski, Łukasz, et autres
Publié: (2025)

OMENN: One Matrix to Explain Neural Networks
par: Wróbel, Adam, et autres
Publié: (2024)

ProDG: Prototypes for Data-Free Generative Post-Hoc Explainability
par: Borycki, Piotr, et autres
Publié: (2026)

From discrete-time policies to continuous-time diffusion samplers: Asymptotic equivalences and faster training
par: Berner, Julius, et autres
Publié: (2025)

Minimal Ranks, Maximum Confidence: Parameter-efficient Uncertainty Quantification for LoRA
par: Marszałek, Patryk, et autres
Publié: (2025)

Bayesian Fine-tuning in Projected Subspaces
par: Dubovik, Viktar, et autres
Publié: (2026)

Outsourced diffusion sampling: Efficient posterior inference in latent spaces of generative models
par: Venkatraman, Siddarth, et autres
Publié: (2025)

HINT: Hypernetwork Approach to Training Weight Interval Regions in Continual Learning
par: Krukowski, Patryk, et autres
Publié: (2024)

LFA applied to CNNs: Efficient Singular Value Decomposition of Convolutional Mappings by Local Fourier Analysis
par: van Betteray, Antonia, et autres
Publié: (2025)

Augmentation-aware Self-supervised Learning with Conditioned Projector
par: Przewięźlikowski, Marcin, et autres
Publié: (2023)

`Just One More Sensor is Enough' -- Iterative Water Leak Localization with Physical Simulation and a Small Number of Pressure Sensors
par: Cholewa, Michał, et autres
Publié: (2024)

Efficient Verified Machine Unlearning For Distillation
par: Quan, Yijun, et autres
Publié: (2025)

Singular Value Decomposition on Kronecker Adaptation for Large Language Model
par: Chong, Yee Hin, et autres
Publié: (2025)